Information Bottleneck

Also known as IB

Overview

Information Bottleneck methods seek compact representations that preserve information relevant to a task while discarding irrelevant details. Common approaches include variational and conditional bottlenecks, mutual-information or rate-distortion objectives, and contrastive or structured regularizers. They are used in learning robust features, protecting privacy, explaining predictions, and limiting communication or memory in agents and multimodal systems. A central challenge is choosing and optimizing the compression level: too little compression retains nuisance information, while too much removes evidence needed for the task, and the right balance depends on the setting.

Latest papers

62 papers7 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

Nov 13, 2026

Why Finite Intelligence Works in an Infinite World: A Mathematical Theory

An information system often has to learn before it knows what it will be asked. A finite representation can succeed without recording an infinite environment in full when those asks share collective structure, rather than demand unrelated facts scattered arbitrarily across it. We formalize this phenomenon through future-task information, the minimum retained information needed to preserve decision value relative to the available evidence. A joint decision-regret state records posterior comparisons among actions for every permitted task. Under compactness assumptions, every retained representation admits a calibrated replacement based on this state, preserving all task regrets without increasing information; the resulting information-regret curve equals an operational coding rate. Two exact boundaries govern finite preservation: weak-star closure for a fixed action count, and the singular mass of the source-evidence law when all finite action menus are admitted. Collective structure determines information requirements beyond individual-question difficulty. Families with identical source laws, pairwise task metrics, and individual-task rates can have different high-resolution exponents. Covariance-identical coordinate and parity families have different exact rate-distortion curves, with optimal parity retention characterized by a sharp Fourier-entropy inequality. For balanced nested task families, refinement sizes and weighted reach determine the rate within an additive constant, attained by prefix coding under explicit decay conditions. Nonlinear learning and computational separations distinguish preservation from efficient discovery and use. The proposed mathematical theory identifies which shared decision requirements allow finite information to remain useful for infinitely many possible purposes.
Nov 8, 2026

TIB: Sample-wise Tempered Information Bottleneck for Multimodal Attribution beyond Alignment Assumption

Multimodal (e.g. vision-language, in this work) attribution aims to interpret the models without access to ground-truth explanatory supervision. Existing multimodal attribution methods typically rely on paired modalities as proxy supervision, implicitly assuming that image-text pairs are semantically aligned. Information bottleneck (IB)-based attribution methods follow this general paradigm and instantiate it through a global sufficiency-compression objective. In realistic multimodal datasets, however, this assumption is frequently violated due to partial semantic misalignment and unreliable cross-modal correspondences. Through theoretical analysis, we show that, under such misalignment, information-bottleneck-based attribution objectives exhibit a structural limitation: by assuming equal reliability across all proxy supervision signals, they induce posterior over-contraction and forced explanations. To address this issue, we propose TIB, a sample-wise Tempered Information Bottleneck framework that adaptively modulates attribution strength according to cross-modal reliability, without assuming semantic alignment. Extensive experiments on controlled benchmarks and large-scale datasets show the effectiveness of the proposed approach, while also validating the identified failure mode.
Oct 26, 2026

What Should an Information Bottleneck Encoder Learn? Separating Representation Learning from Rate Control

The information bottleneck (IB) trades compression of an input XX against prediction of a target YY through a multiplier β=1/λβ=1/λ, yet each operating point is usually served by training, or fully conditioning, a new encoder. For jointly Gaussian data, we show that the IB solution factorizes as A(β)=D(β)WA(β)=D(β)W: the information-bearing directions WW do not depend on ββ, and ββ acts only through scalar gains. We ask whether this separation of representation from rate control survives beyond Gaussian models, treating the budget as a given operating parameter rather than a quantity to be optimized. For a budget-free representation F(X)F(X), the separation gap is controlled by the sufficiency deficit εF=I(X;Y∣F(X))ε_F=I(X;Y\mid F(X)): We show there is at least εFε_F in the worst case for finite inputs, and it is bounded uniformly in λλ by a function of εFε_F for finite label alphabets. The same certificate extends to a new target distribution and to pooled multi-domain data, where a conditional-alignment term appears. On MNIST, SVHN, CIFAR-10 and STL-10 (10 seeds, eight prespecified budgets), a frozen CNN representation with one compressor--decoder pair per budget reduces estimated training multiply--accumulate operations (MACs) by 7.7×7.7\times and wall-clock time by about 2×2\times relative to end-to-end VIBs, and attains higher budget-averaged accuracy (65.6%65.6\% versus 57.3%57.3\% per domain; 67.1%67.1\% versus 57.1%57.1\% pooled), with the advantage concentrated at strong compression, where the VIBs collapse. At weak compression (λ≤0.036λ\le0.036), VIB has higher cross-entropy and ECE; its surrogate Lagrangian is higher per domain, indistinguishable from the pooled VIB in the macro average, and lower on the pooled test set.
Oct 26, 2026

Intrinsic Information Rates of Summaries in Simulation-Based Inference

Simulation-based inference often encodes observations YY into a fixed-dimensional summary SS, with the posterior conditioning only on SS. While exact preservation often requires infinite information, any such summary imposes a finite information budget on inference which is rarely an explicit choice or measurement. In this paper, we make the budget explicit by modeling the summary as a lossy channel from YY to SS, and ask two questions: how large must the budget be, and how best is it spent? First, we show for parametric models that this budget, measured by the mutual information I(Y;S)I(Y;S), grows unboundedly as the posterior concentrates, even when fixed-dimensional sufficient statistics exist. More generally, the required budget is set by the distribution of the random posterior, and we bound it from above by quantizing posteriors and from below by converses that weight each posterior state by its probability. Second, we show that a finite budget is best spent stochastically. Under a common-support condition on the simulator, covering the continuous observation spaces typical of simulators, a deterministic summary necessarily loses something: a stochastic summary achieves strictly lower distortion than every deterministic summary and every time-shared mixture of deterministic summaries at every positive budget too small for exact preservation. Motivated by these results, we insert a binary bottleneck into neural posterior estimators, measure each trained summary's rate, and compare summaries at matched rate. Across four simulator benchmarks and several encoder families, stochastic bottlenecks achieve favorable rate--loss tradeoffs, and architecture rankings change at different information budgets.
Oct 25, 2026

Multi-view Semantic-aware Resource Allocation for Edge AI

Semantic communication is emerging as a pivotal paradigm to overcome wireless resource scarcity in 6G networks. This paper proposes a novel end-to-end framework for semantics-aware resource allocation in multi-user Edge AI. We extend the Opportunistic Information Bottleneck (OIB) to a multi-view setting, termed the Multi-view Gaussian Information Bottleneck (MGIB), by fusing complementary source views without variational approximation or network retraining. A resource allocation framework is then formulated for joint compression-level selection, transmission mode selection (i.e., the number of active sources per group), and PRB assignment. The problem is formulated as a Mixed-Integer Linear Program (MILP), solved efficiently via a proposed Lagrangian Relaxation (LR) algorithm, and benchmarked against the NP-hard optimal solution. Simulations demonstrate that the proposed LR scheme achieves near-optimal utility, and doubles PRB efficiency versus average allocation.
Oct 21, 2026

Optimal Multitask Representations Under a Rate Constraint: An Information Bottleneck Analysis

Which pretraining objective yields the best representation for downstream tasks under an information budget? We formalize this problem as a multitask information bottleneck, using a mutual information constraint to model incomplete information retention. For Gaussian inputs and tasks, we characterize optimal representations and show that a weakly task-aligned specialist can outperform a reconstruction generalist at low rates but lose at high rates. We also construct task families for which every fixed Gaussian prediction objective incurs arbitrarily large relative regret, driven by reversals in optimal allocation priorities. Conversely, the average task information matrix defines an objective with a uniform relative-regret bound controlled by maximum task SNR. CelebA and dSprites experiments illustrate that compression can change which pretraining objective performs best, and even task-aware training can reverse which downstream task is better preserved as rate increases.
Oct 21, 2026

SICAF: Time-Varying Focus Bottleneck for Self-Supervised Event-Based Optical Flow with Spiking Neural Network

Event-based optical flow estimation achieves high temporal resolution and dynamic range by exploiting asynchronous events, while self-supervised learning provides an effective solution to the absence of ground-truth labels. Spiking neural networks (SNNs), as brain-inspired models, process information through asynchronous spikes, naturally aligning with optical flow events. However, the temporal irregularity across event streams hinders the compact extraction of spatiotemporal features, while the absence of explicit labels leads to spurious correlations, thereby increasing redundancy within latent representations. In this paper, we propose a novel 'Compactly Compress, Time-varying Focus' training strategy. We present SICAF (Spikes Information Compression And Focus) framework that formulates the learning process as a constrained optimization with temporal modulation. It encourages self-supervised SNNs to extract compact latent representations while preventing over-compression that would discard temporal saliency. To better enable feature selectivity across time steps, we design an estimator with learnable temporal attention, achieving context awareness with cross-time dependencies. Experimental results on several datasets demonstrate that SICAF achieves state-of-the-art performance in self-supervised SNNs, with a 8.14% improvement in AEE on the MVSEC dataset and a 13.49% increase in robustness under white-box adversarial attacks.
Oct 20, 2026

Robust Representation Learning for Spiking Neural Networks based on Conditional Information Bottleneck

Spiking Neural Networks (SNNs) have shown great potential for low-power neuromorphic computing due to their event-driven processing and spatiotemporal sparsity, but they remain vulnerable to input perturbations, hardware-intrinsic noise, and adversarial attacks in real-world deployment. We attribute this vulnerability partly to input-specific hidden representations learned by standard SNNs trained with conventional cross-entropy loss, as our information-plane analysis empirically shows that substantial input-related information can still be retained after label-predictive information becomes stable. To address this issue, we propose SCIB, a simple yet effective robust learning objective for SNNs based on the Conditional Information Bottleneck. Different from conventional variational IB methods, SCIB replaces the mutual information compression term I(X;S)I(X;S) with the conditional mutual information I(X;S∣Y)I(X;S|Y) and derives a tractable variational upper bound. Moreover, it introduces a learnable class-conditional prior instead of a label-agnostic isotropic Gaussian prior, improving the expressiveness of variational compression and encouraging class-structured representations when combined with the supervised classification objective. Systematic experiments on Fashion-MNIST, CIFAR-10, and CIFAR-100 under external environmental noise, neuromorphic hardware noise, and adversarial attacks show that SCIB improves robustness over standard SNNs and IB-based baselines under most evaluated noise conditions, improves adversarial accuracy under the evaluated attacks without using adversarial training, and reduces the SynOps-based single-sample inference energy consumption by 24.9% relative to an unconstrained SNN baseline.
Oct 7, 2026

Quasi-Binarized Autoencoders: An Architecture-Independent Information Bottleneck for Medical Image Anomaly Detection

Unsupervised anomaly detection, which learns only from normal images, is a central task in medical image analysis and remains an open problem. Reconstruction-based methods pass an image through an encoder-decoder network trained on normal data and detect anomalies from the residual between the image and its reconstruction. This works only if the information passed from the encoder to the decoder is limited; otherwise the network learns an identity mapping and reconstructs anomalies too. This limit is usually imposed through architectural choices, tuned per dataset, that cannot be stated in bits. We introduce the quasi-binarizing (QB) layer, which squashes each latent element into [0, 1] and adds Laplace noise of scale 1/epsilon. Each element is then epsilon-locally differentially private, and the mutual information between an image and its reconstruction is bounded by a quantity that depends only on epsilon and the number of QB elements, whatever the encoder and decoder. Placing a QB layer on every encoder-decoder path, including all skip connections, we build QBAE, a seven-level attention U-Net with 32,768 QB elements. On the seven datasets of the MedIAnomaly benchmark, QBAE with one architecture and one configuration reaches a mean image-level AUROC of 0.828, the highest among methods that do not adapt to each dataset, and the best reported results on BraTS2021 (AUROC 0.911, pixel-level AP 0.838). The noise is kept at test time, so that every reconstruction satisfies the bound. Without input corruption, the bottleneck alone prevents identity collapse (mean AUROC 0.805 vs. 0.590). Code is available at https://github.com/hanaokalog/MedIAnomalyQB.
Oct 6, 2026

IronMan: Information-Constrained Video-Action Learning for Robot Manipulation

Video Action Models (VAMs) couple visual dynamics modeling with action generation for robot manipulation. However, video representations are not naturally suited to action generation, as exposing the action policy to excessive visual detail can impair its generalization ability. Therefore, we introduce IronMan (Information-constRained videO-actioN learning for robot MANipulation), a robust video-action learning framework built on the information bottleneck principle. The core principle of this framework is to impose information constraints that suppress irrelevant visual information while preserving action-relevant dynamics cues. IronMan employs a dynamics-aware bottleneck that distills noisy, entangled one-step video features into compact world representations. Extensive simulation and real-world experiments demonstrate strong in-distribution (ID) performance and out-of-distribution (OOD) robustness while maintaining efficient inference. IronMan achieves success rates of 99.0% on LIBERO and 79.4% on RoboTwin clean2clean, outperforming all the evaluated baselines. Under OOD shifts, IronMan achieves a success rate of 79.1% on LIBERO-Plus, exceeding the strongest baseline by 10.4 percentage points. Project page: https://youngsoul0731.github.io/ironman-project-page/
Oct 5, 2026

On the Cardinality of Optimal Representations in the Binary-Source Information Bottleneck

The information bottleneck (IB) seeks a representation UU of a source XX that retains as much information as possible about a target YY, subject to a constraint on I(U;X)I(U;X). A classical argument shows that it suffices to consider representations with at most ∣X∣+1|\mathcal{X}|+1 symbols, and this bound is known to be tight whenever ∣X∣≥3|\mathcal{X}| \geq 3. We show that the binary case behaves differently: if XX is binary and YY is finite, then for every joint distribution of (X,Y)(X,Y) and every rate constraint, the IB optimum is attained by a binary UU. Hence the bound ∣U∣≤∣X∣+1|\mathcal{U}| \leq |\mathcal{X}|+1 sharpens to ∣U∣≤∣X∣|\mathcal{U}| \leq |\mathcal{X}| for binary sources. The proof combines a separating hyperplane argument with the observation that, for a binary source, the ratio of the second derivatives of the two entropy functions involved is concave.
Oct 1, 2026

Rethinking the Information Bottleneck: Structured Decomposition under Label-Induced Partitions

Standard information bottleneck (IB) regularization constrains representations via a single scalar I(Z;X), implicitlytreating all information as homogeneous. However, a single global compression control couples label-relevant structurewith residual within-condition variation, rather than regulating their allocation independently, allowing nuisanceinformation to persist in learned representations. For example, in medical imaging applications, residual variation oftenstems from acquisition conditions, background factors, or subject-specific appearance. This issue becomes particularlypronounced in data-limited settings, where models tend to overfit such variation, hindering generalization. While existingregularization methods can stabilize training, control capacity, or shape representation geometry, they do not explicitlyseparate nuisance-like variation from task-supporting structure. To address this limitation, we revisit IB from a structuredperspective based on a label-induced partition, where condition-level structure and within-condition information playdistinct roles. This leads to a dual-bottleneck formulation: a standard KL term controls global information capacity, while aconditional KL term targets within-condition information. We show that the conditional KL admits an exact decompositioninto a within-condition information term and a prior-mismatch term, explaining its alignment with the design objective.With a simplex-structured conditional prior, the method provides controllable latent geometry and integrates seamlesslyinto existing pipelines. Experiments on classification and segmentation show the clearest gains in low-data classificationand consistent improvements across dense prediction benchmarks.
Sep 29, 2026

Mutual Information Constrained Chernoff Bottleneck

The classical information bottleneck (IB) measures the relevance of a representation UU of XX to a target YY by I(U;Y)I(U;Y), which does not directly characterize the error of downstream decisions. For a binary hypothesis YY inferred from many separately encoded observations, the optimal error exponent is the Chernoff information between the two conditional distributions of UU given YY. We study the mutual information constrained Chernoff bottleneck, which seeks an encoder that maximizes this Chernoff information subject to a rate constraint I(U;X)≤RI(U;X) \leq R. We show that its optimal value C(R)C(R) increases strictly up to R=H(V)R = H(V), where VV merges the symbols of XX with equal likelihood ratio, remains at the uncompressed exponent beyond, and, unlike the IB curve, need not be concave. We further show that k+1k+1 outputs suffice to attain C(R)C(R), where kk is the cardinality of VV. We propose an alternating algorithm that updates the encoder via a generalized Blahut--Arimoto algorithm and the Chernoff parameter ss via a nonlinear equation, and prove that its iterates remain feasible, with nondecreasing and convergent Chernoff information. Comparing with the classical IB for nn samples, we show that, whenever the two objectives disagree, the IB encoder has the smaller equivocation H(Y∣Un)H(Y|U^{n}) at n=1n = 1, whereas the Chernoff bottleneck has the smaller error probability and equivocation for all large nn. Numerical experiments confirm the theory, and on real topic-detection data from the 20 Newsgroups corpus, compressing each word to only 17%17\% of its entropy retains 90%90\% of the error exponent and nearly the accuracy of the uncompressed classifier.
Sep 29, 2026

Information Bottleneck-Guided Adaptive Hypergraph Transformer for Brain Disease Diagnosis

Exploring high-order correlations and long-range dependencies in brain networks holds significant value for both neuroscience research and clinical diagnosis. However, previous studies have lacked a unified integration of high-order and long-range dependency information in brain networks, and there is substantial redundancy behind various types of information. These issues limit their effectiveness in the diagnosis of brain diseases. To address this, we propose an Information Bottleneck-Guided Adaptive HyperGraph Transformer (IBAHGT). By incorporating the information bottleneck (IB) principle, this approach enables adaptive learning of high-order correlations and both short- and long-range dependencies within a unified framework for brain network analysis, achieving high-precision brain disease diagnosis. IBAHGT consists of three key components: an information bottleneck-guided adaptive hypergraph convolution, which introduces a novel hypergraph information bottleneck (HIB) principle to adaptively learn hypergraph message-passing weights between nodes and hyperedges, optimizes information flow and captures high-order information in brain networks that is maximally informative and minimally redundant (MIMR). The Transformer encoder captures global information within brain networks through the attention mechanism, specifically modeling short- and long-range dependencies. An information bottleneck-guided node-level adaptive fusion employs the IB principle to learn independent weights for each node, facilitating the fine-grained integration of high-order information and global information to obtain an efficient representation for downstream tasks. Extensive experiments demonstrate that the proposed method outperforms current state-of-the-art methods and can identify biomarkers for clinical applications.
Sep 28, 2026

Attention-based Hierarchical Variational Information Bottleneck for Robust Multi-Agent Communication under Variable Bandwidth

Learning-based multi-agent communication under limited bandwidth does not only require deciding what to communicate, but also structuring messages so that partial transmissions remain useful. We study this problem under prefix truncation, where only the first part of each message is received. To address it, we propose AH-VIB, an attention-based autoregressive variational communication model that combines a variational information bottleneck (VIB) with sequential message generation and a hierarchical robustness loss. We evaluate AH-VIB on a custom cooperative object-inspection and occupancy-mapping task, where agents equipped with a limited field-of-view sensor coordinate to scan inspection objects in an occupancy-grid world, under variable and fixed bandwidth conditions, and compare it against MADDPG, CommNet, a flat VIB baseline, and an autoregressive MLP ablation. AH-VIB achieves competitive mean return while improving performance reliability under the most constrained bandwidth conditions. These results indicate that AH-VIB improves the reliability and graceful degradation of learned communication under bandwidth constraints.
Sep 12, 2026

SGWIB:Sliced Gromov-Wasserstein Information Bottleneck for Video Highlight Detection

Video highlight detection aims to identify temporally important segments that capture the most informative or engaging events in a video. Reliable prediction therefore requires not only discriminative segment representations but also preservation of the temporal relationships among neighboring and distant segments. The information bottleneck principle has proven effective for learning compact and task-relevant representations, yet it has not been explored for video highlight detection, and applying conventional formulations directly would overlook inter-segment relational structure and distort highlight relevant temporal organization during compression. We therefore introduce the Sliced Gromov-Monge Gap (SGMG), a structure aware regularizer that measures the excess relational distortion induced by a prescribed source-to-bottleneck mapping relative to an optimal sliced structural correspondence. Building on SGMG, we develop SGWIB, an information-bottleneck framework for single-modal video highlight detection that learns compact bottleneck representations while preserving inter-segment temporal structure. We further introduce Home-Away-Related Contextual Pseudo-Labels and a contextual disentanglement module that reduce sports-specific contextual bias by separating highlight oriented information from contextual patterns. Experiments on MrHiSum and MoSu show that SGWIB attains the best Kendall's tau, Spearman's rho, mAP@50, and mAP@30 among the compared single-modal methods on both datasets. On MrHiSum, the visual model improves the strongest previous results by 0.031, 0.031, 0.87, and 0.75 on these four metrics, respectively. These results show that structure-aware information-bottleneck regularization combined with contextual disentanglement improves segment-level highlight prediction.
Sep 10, 2026

Beyond Argmax: A Mechanistic Study of Semantic Retention in Frozen Foundation-Model Composition for Generalized Few-Shot 3D Segmentation

Classical classifier-combination work distinguishes score-level fusion from hard decision-level voting. We revisit this distinction where independently pretrained, frozen foundation models are composed at inference time for generalized few-shot 3D segmentation. We ask: how much useful semantic information is lost when heterogeneous sources are collapsed to a single class before they can interact? We answer with a same-input semantic-retention intervention. Dense RegionPLC and sparse cross-view SAM3 evidence, model weights, masks, geometry, vocabularies, and fusion rules are frozen; only the number of semantic alternatives retained before interaction is varied via a matched top-k ladder. On 156 held-out ScanNet200 scenes, top-1 reaches 28.47 harmonic-mean (HM) IoU while full distribution fusion reaches 34.87 HM (+6.40, 95% CI [+5.24,+7.64]). The pattern replicates on 50 ScanNet++ scenes: 23.02 vs. 26.50 HM (+3.48, 95% CI [+1.64,+5.93]). The conclusion is robust: full-distribution HM is stable across sparse-source weights 0.3--0.7; alternative operators (max, geometric pooling) also outperform top-1; and a GroundingDINO--SAM2.1 source-replacement diagnostic shows monotonic HM increase from 14.77 to 18.75 with full retention. Calibration diagnostics reveal opposite miscalibration of the two sources, yet correcting calibration does not eliminate the retention advantage. Across datasets and source stacks, most information is recovered by retaining a compact set of plausible alternatives. The contribution is a controlled diagnosis of premature semantic collapse as a repeatable information bottleneck in heterogeneous frozen-model composition.
Sep 2, 2026

Pose accuracy is not grasp reliability: residual pose posteriors improve simulated robotic grasp planning

Model-based robotic grasping estimates an object's six-dimensional (6D) pose and plans on its mesh as if that pose were exact. We show that this assumption reduces simulated grasp success even when the pose passes the standard accuracy test. We built LM-Grasp, a benchmark of 15{,}800 real LINEMOD RGB-D images with grasp outcomes simulated on scanned meshes. FoundationPose meets the ADD(-S) criterion (mean model-point error below 10% of the object diameter) on 0.997 of test scenes, yet planning on its estimate succeeds in 0.791 of scenes, compared with 0.856 using the annotated pose. Because the estimator reports no uncertainty, we build a pose posterior from its own errors on annotated training frames, resampled from frames with similar observable fit, and score each grasp by its mean success across sampled poses and four equally weighted physics scenarios. Without retraining the estimator, posterior planning yields 0.859 (difference from the annotated-pose result +0.003; 95% scene-wise paired-bootstrap interval [−-0.003, +0.009]). This interval is compatible with no difference and a small shortfall; we did not conduct an equivalence test. For pose errors of 5 to 10% of the diameter, simulated success rises from 0.796 to 0.984. Among test scenes assigned singleton-success conformal prediction sets, observed held-out precision is 0.972, compared with 0.904 for the point-estimate planner; these are empirical precision estimates, not conditional guarantees. On occluded LM-O scenes never used for tuning, posterior planning closes 66% of the gap to the annotated pose.
Sep 2, 2026

Synergistic Information Disentanglement for Omni-modal Slide Representation Learning in Computational Pathology

In computational pathology (CPath), developing omni-modal self-supervised learning (SSL) models that integrate histology, genomics, and clinical reports enables transferable representation learning for whole slide images (WSIs). Existing approaches implicitly force heterogeneous modalities into a uniform latent space by contrastive alignment, causing modality collapse where unique, synergistic diagnostic signals (termed as Φ\mathrmΦ) are discarded in favor of trivial redundancy. We hypothesize that the strongest task-agnostic SSL training signal stems from distilling the synergistic interactions over merely aligning shared redundancy. To this end, we introduce \textsc{Φ\mathrmΦ-Omni}, a synergistic information disentanglement framework grounded in Partial Information Decomposition (PID) theory for slide representation learning. Unlike standard contrastive approaches, \textsc{Φ\mathrmΦ-Omni} employs a Synergistic Information Bottleneck (SIB) regulated by the proposed ΦID\mathrmΦ\text{ID} objective, which explicitly suppresses marginal redundancy while maximizing irreducible synergy, thereby distilling high-order cross-modal interactions. Following pretraining on breast (nn=1031) and lung (nn=919) cohorts, \textsc{Φ\mathrmΦ-Omni} demonstrates superior few-shot performance across five independent external datasets spanning eight tasks compared to supervised and SSL baselines. Source code is available here.
Aug 26, 2026

Towards A Unified Information Bottleneck Framework for Time Series Explanations

Explaining deep learning models operating on time series data is crucial in various applications that require transparent and interpretable insights into model behavior. {Existing explanation methods generally fall into two categories: attribution-based explanations, which identify the temporal regions most responsible for a prediction, and counterfactual explanations, which reveal how an input should be modified to alter the model's decision.} {Despite valuable insights, these two fields are largely studied independently. This disconnect leaves attribution methods lacking causal validation, while counterfactual methods suffer from severe instability, producing adversarial-like noise instead of meaningful explanations.} In this work, we revisit time-series explainability from an information-theoretic perspective and show that existing explainers are vulnerable to trivial solutions and distributional shifts. To address these limitations, we propose a unified objective function for explainable time series learning that bridges attribution and counterfactual reasoning within a single framework. Building upon the Information Bottleneck principle, our formulation explicitly prevents trivial explanations and out-of-distribution counterfactuals. {Based on this objective function, we introduce {\modelname}, a novel explanation framework that learns a parametric transformation network to construct explanation-embedded instances, where preserved information yields attribution explanations and controlled information removal produces stable counterfactual explanations.} We evaluate {\modelname} on synthetic and real-world benchmarks against state-of-the-art baselines. Extensive quantitative and qualitative results show that {\modelname} consistently outperforms competing methods, yielding faithful attributions and stable counterfactual explanations.
Aug 17, 2026

GRIP: Grounded Reasoning via Information-Restricted Premises

High-capacity encoders in retrieval-augmented generation (RAG) can let the query dominate the latent state, leaving retrieved evidence functionally irrelevant. We call this failure mode query dominance. To address it, we introduce GRIP (Grounded Reasoning via Information-Restricted Premises), which imposes capacity asymmetry: the decoder keeps full-dimensional access to the query, while retrieved evidence passes through a severe stochastic bottleneck. This forces the evidence channel to encode only the residual information unavailable from the query. Across five reasoning benchmarks, GRIP outperforms strong iterative baselines, cuts a query--latent mutual-information diagnostic by roughly 30×\times (14.8 →\to 0.47 bits), and reduces hallucination by 73%. Residual-alignment analysis further shows that the bottleneck output occupies subspaces less aligned with the query than baseline representations.
Aug 11, 2026

Information Bottleneck under Perfect Privacy

In this work, we study the information bottleneck under perfect privacy, with particular emphasis on the active-rate regime, where the representation-rate constraint is binding and directly limits the achievable utility. The goal is to construct a representation that preserves utility-relevant information while remaining statistically independent of a sensitive variable. This exact independence requirement introduces an additional constraint beyond the classical rate-relevance tradeoff and must be explicitly incorporated into the optimization. To this end, we develop an alternating direction method of multipliers (ADMM)-based method tailored to the resulting problem structure. Under suitable regularity conditions, we establish global convergence of the generated sequence, characterize its convergence rate through the Kurdyka-Lojasiewicz exponent, and extend the analysis to inexact block updates.
Jul 30, 2026

Information Bottleneck Learning for Faithful Time Series Forecasting Explanations

As forecasts increasingly drive decisions in fields such as energy, transportation, and healthcare, understanding the historical data behind these predictions has become as crucial as the predictions themselves. Although existing interpretable-by-design forecasters reveal their internal structures, they offer no guarantee that these structures faithfully reflect the underlying evidence driving the predictions. In contrast, while faithfulness-oriented methods explicitly verify model behavior, they are almost exclusively designed for post-hoc classification tasks. To bridge this gap, we propose IB-Forecast, an inherently interpretable multivariate time-series forecasting framework. It decomposes forecasting into a learned periodic component and a residual component computed with explainable masks over input tokens. With a budget-constrained information bottleneck, end-to-end optimization enables users to directly control explanation sparsity. With a rigorous faithfulness evaluation protocol, extensive experiments demonstrate that IB-Forecast matches the forecasting error of leading black-box models while providing faithful explanations at no additional inference cost. Furthermore, under a matched sparsity budget, these native explanations consistently surpass gradient-based, occlusion-based, and optimization-based baselines across all evaluated datasets. Ultimately, whereas the native explanations of existing interpretable forecasters exhibit poor faithfulness, IB-Forecast guarantees high explanation fidelity, requiring only 14-20% of the observations to deliver low-error predictions.
Jul 25, 2026

Towards Dual-Brain Minimal Sufficient Representation for Vision-Language Navigation

Vision-and-Language Navigation in continuous environments (VLN-CE) requires an agent to ground language in egocentric observations and plan in unseen scenes. Although recent multimodal large models and world-model-based methods have improved navigation, they often preserve excessive task-irrelevant detail, weakening generalization and increasing computational burden. We propose BrainNav, a navigation framework grounded in the Principle of Minimal Sufficiency. BrainNav consists of three components: a Logical Anchor Model that implements instruction-aware selective perception to suppress environmental noise, a Minimalist Constraint Alignment module that serves as a compact cross-modal bottleneck, efficiently synchronizing discrete linguistic intent with continuous latent dynamics while filtering out redundant information, and a Compression World Model that predicts action-conditioned states within a condensed, low-rank latent space. These modules align semantic intent with spatial perception, enhancing the agent's robustness and efficiency in complex tasks. Experiments show that BrainNav improves over prior SOTA by 2.0 % / 1.0 in SR/SPL on R2R-CE val-unseen and 0.94 % / 0.78 on RxR-CE val-unseen. These results indicate that minimally sufficient world representations provide an effective foundation for robust VLN.
Jul 24, 2026

Indexing: the Beginning and the End

We study information bottlenecks in modern deep-learning architectures -- RNNs, softmax transformers, linear-attention transformers and state-space models -- through the lens of the indexing primitive. In this primitive, the input consists of nn bits and one integer ii from 11 to nn called the index, and the output equals the value of the ii-th bit. We introduce causal complexity for masked architectures. We show that architectures with low causal complexity cannot solve the indexing primitive in any constant number of layers when the index appears at the end of the input. In particular, this limitation applies to low-parameter RNNs, SSMs and masked linear-attention transformers. In contrast, small softmax transformers can solve it in one layer, while non-masked linear-attention transformers can solve it in 2, which separates them from their masked counterparts. In turn, when the index appears at the beginning, we show that small RNNs are capable of solving this task in 1 layer, while all the other architectures require 2. All our impossibility results are unconditional and apply even to models that employ infinite-precision real arithmetic. Moreover, experiments for up to n=64n=64 qualitatively align with our theory: configurations with low-parameter theoretical solutions learn the indexing task easily, while configurations that do not admit such theoretical solutions struggle to learn as the sequence length grows.
Jul 24, 2026

Rethinking Layer-Wise Information Allocation for Vision Foundation Model Adaptation

Vision foundation models are increasingly reused as frozen backbones for downstream visual recognition, making parameter-efficient adaptation a central problem. Prompt-based adaptation, including Visual Prompt Tuning (VPT), provides a lightweight way to specialize these models, but its layer-wise behavior remains poorly understood: performance is sensitive to prompt depth, placement, and task distribution, and gains on standard in-domain benchmarks do not always translate into robust generalization. We argue that this limitation is not solely an optimization issue, but a layer-wise information allocation issue: existing prompt-based methods lack principled control over what prompt-conditioned representations should preserve, suppress, and propagate across depth. Inspired by the Information Bottleneck principle, we introduce Prompted Information Bottlenecks (PIB), a framework that regularizes layer-wise compression-sufficiency trade-offs and promotes a more coherent cross-layer information path. The key idea is that effective adaptation should be minimal yet sufficient, retaining task-relevant local evidence in earlier layers while progressively discarding nuisance factors and redundant details in deeper layers. Extensive experiments show that PIB achieves strong performance across 34 datasets, reaching 92.1% on FGVC, 93.01% on HTA, and 77.33% on VTAB-1k, while tuning only 0.35% parameters on average across the main settings. Beyond benchmark accuracy, PIB helps explain the non-monotonic behavior of prompt capacity scaling, reduces shortcut reliance, and improves robustness under distribution shift and fine-grained recognition settings. These results position PIB as both a practical method and an information-allocation perspective for adapting frozen vision foundation models. Our code is available at https://github.com/itsnotacie/MM-26-PIB
Jul 22, 2026

External Clustering Validation by the Homogeneity-Parsimony Trade-off

Scalar metrics are often used to evaluate clusterings against known classes, but they can obscure a fundamental trade-off: clusterings should be informative about class labels while avoiding unnecessary fragmentation. Here we describe normalized scores of cluster homogeneity and parsimony that quantify this trade-off. These scores build on the information bottleneck principle, modified to not reward lossy compression. We show by example and mathematical proof that our definitions of these scores have the intuitive property of varying monotonically under cluster refinement in contrast to related proposals. Extending the information-theoretic framework beyond Shannon entropies, we furthermore derive set-matching and pair-based counterparts of the homogeneity and parsimony scores. These unify commonly used evaluation criteria and show that, in the pair-based setting, the homogeneity-parsimony trade-off recovers the receiver operating characteristic of binary classifiers. We demonstrate the framework's utility for feature selection and algorithm comparison, illustrating how considering scores jointly can clarify clustering operating points and identify Pareto-optimal solutions.
Jul 17, 2026

When Do Multi-Agent Systems Help? An Information Bottleneck Perspective

LLM powered multi-agent systems (MAS) have emerged as a promising paradigm for complex tasks. However, their advantages over single-agent systems (SAS) remain unclear, with performance varying inconsistently across settings. Here, we provide an information bottleneck perspective on elucidating the differences between MAS and SAS. Specifically, our key observation is that a SAS accumulates its full reasoning trace in one shared context, while a MAS uses isolated local contexts connected by bounded relay messages. We show that, under infinite relay bandwidth, any SAS can be simulated by a MAS that transmits the full upstream context. Thus, the nontrivial advantage of MAS arises under bounded relays, where compression introduces a fundamental trade-off: reducing redundant context can improve efficiency, but may also incur loss of task-relevant information. We formalize this trade-off as an information bottleneck controlled by an effective parameter ββ, which captures how the balance shifts with model capability, and shows that MAS gains arise when context reduction outweighs relay information loss. We conduct 18 controlled experiments across five benchmarks and three model scales to validate our theoretical studies. We observe that MAS consistently helps when relays are near-sufficient, especially for weaker models. In contrast, MAS gains shrink or reverse when relays incur information loss, especially for stronger models that can already extract useful information from redundant context and thus gain little from compression. Our study shows that multi-agent design is fundamentally an information-bottleneck optimization problem. This perspective explains when bounded inter-agent communication helps or hurts.
Jul 17, 2026

Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content

Language models encode text as subword tokens, raw bytes, or rendered pixels, but these encodings are usually compared under modeling constraints that expose different amounts of linguistic content to models across different languages. We instead ask what each encoding preserves when both the content and the downstream capacity are controlled. Using verified parallel sentences across thirteen languages and five scripts, we compare tokens, bytes, and pixels through a shared bottleneck whose width is swept to trace rate-utility frontiers. This separates three quantities that are often conflated: the number of input positions an encoding creates, the latent capacity available after encoding, and the task-relevant information that survives compression. We evaluate three utilities: surface form preservation, cross-lingual sentence alignment, and topic classification. No encoding dominates across tasks or capacity regimes. Pixels preserve surface form best, bytes preserve cross-lingual alignment best, especially in same-script multilingual settings, and tokens support topic prediction best. These performances are not explained by sequence length alone. Short inputs can discard useful meaning, while long inputs can preserve information that compresses well. Choosing an encoding is therefore not a fixed preference for tokens, bytes, or pixels, but a rate-utility tradeoff that depends on the task, language mix, capacity regime, and compute budget.
Jul 15, 2026

The SIGReg Objective as Variational Free Energy: A Theoretical Active-Inference Account of JEPA World Models

Joint-Embedding Predictive Architectures (JEPAs) are the dominant design for latent world models, yet they are usually justified by empirical performance rather than a normative principle. We show that the choice of anti-collapse regulariser determines whether a JEPA's training objective, a prediction loss plus a weighted embedding regulariser, is a valid Active Inference (AIF) variational free energy. We organise four non-contrastive regularisers (VICReg, LogDet, PairDist, and SIGReg) into an entropy-estimator hierarchy indexed by a prior-miscalibration gap, and show that the gap's sign, whether the estimator bounds the latent entropy from above or below, decides whether the AIF surprise bound survives: VICReg and LogDet are unsafe upper bounds, PairDist a safe lower bound, and SIGReg eliminates the gap. We then prove a correspondence theorem: under the standard constant-noise encoder model and successful SIGReg enforcement (isotropic-Gaussian embeddings), the gap vanishes, the objective becomes an exact information bottleneck, the surprise bound is preserved, and the latent goal cost becomes an exact proxy for AIF pragmatic value, whereas VICReg leaves an irreducible second-order anisotropy term. We extend the correspondence to multi-step expected free energy, ensemble epistemic value, and a learned-policy regime, and we identify the one AIF term no current JEPA world model computes: the state-epistemic value, a future-state coverage signal. The predictions differ in kind, not degree, and are stated here as theoretical consequences left for empirical test in separate work; full proofs are in Appendix A, and the algebraic core of every result is machine-verified in Lean 4 (Appendix D).