A Compression Perspective on Simplicity Bias

Tom Marty; Eric Elmoznino; Leo Gagnon; Tejas Kasetty; Mizu Nishikawa-Toomey; Sarthak Mittal; Guillaume Lajoie; Dhanya Sridhar

cs.LGMar 26, 2026

A Compression Perspective on Simplicity Bias

Authors: Tom Marty, Eric Elmoznino, Leo Gagnon, Tejas Kasetty, Mizu Nishikawa-Toomey, Sarthak Mittal, Guillaume Lajoie, Dhanya Sridhar

Organizations: Mila – Quebec AI Institute · Université de Montréal

Abstract

Deep neural networks exhibit a simplicity bias, a well-documented tendency to favor simple functions over complex ones. In this work, we cast new light on this phenomenon through the lens of the Minimum Description Length principle, formalizing supervised learning as a problem of optimal two-part lossless compression. Our theory explains how simplicity bias governs feature selection in neural networks through a fundamental trade-off between model complexity (the cost of describing the hypothesis) and predictive power (the cost of describing the data). Our framework predicts that as the amount of available training data increases, learners transition through qualitatively different features -- from simple spurious shortcuts to complex features -- only when the reduction in data encoding cost justifies the increased model complexity. Consequently, we identify distinct data regimes where increasing data promotes robustness by ruling out trivial shortcuts, and conversely, regimes where limiting data can act as a form of complexity-based regularization, preventing the learning of unreliable complex environmental cues. We validate our theory on a semi-synthetic benchmark showing that the feature selection of neural networks follows the same trajectory of solutions as optimal two-part compressors.

Figures & tables

Figure 1: (a) In a supervised setting, some features causally relate to the label (e.g., phenotypical characteristics), while others are spurious (e.g., background of the image). A Bayesian solution leverages all available features. (b) Total expected compression cost as a function of training dataset size $N$ . Each line represents the two-part description length of a candidate model. The MDL-optimal learner selects the model achieving the lowest total cost at each $N$ , inducing transitions between qualitatively different solutions as the amount of data increases.

Figure 2: Comparison of the compression view and the learning view for Scenario A and B. (a) Compression envelopes on a log-log scale: each line shows the total two-part description length of a candidate predictor as a function of dataset size

N

. (b) Accuracy on held-out datasets as a function of

N

: solid lines are empirical measurements, dashed lines are reported metrics of the MDL-optimal solution. (c) Permutation feature importance (accuracy drop after shuffling each feature): a higher drop indicates stronger reliance on that feature.

Panel of Figure 3 — Figure 3: Empirical vs. theoretical transition point $N$ for varying task characteristics. Each point is one experimental configuration; the dashed line is the identity $N_{\text{theory}}=N_{\text{empirical}}$ . (a) Reducing the predictiveness of a feature increases its compression rate disadvantage, causing the transition to occur earlier. (b) Increasing the complexity of a feature inflates its description cost, causing the transition to occur earlier. In both cases, the proximity to the diagonal indicates that our MDL-based theory accurately predicts the observed feature switch as measured by our proxy.

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Figure C.1 : Example samples from the EMNIST-based benchmark we curated, featuring the three types of features we presented in Section 2.3 : the digit shape (robust feature), the color (simple spurious feature) and the watermark (complex environmental-cue). The label is determined by the digit value, while the color and watermark are correlated with the label in an environment-dependent way.

Parameter	Symbol	Description	Values
Environment & Spurious Correlation
flip_prob	$p_{\text{flip}}$	Label noise probability	$\{0,0.01,\ldots,0.1\}$
spur_prob	$p_{e}$	Relative proportion of environments	$\{0,0.02,\ldots,0.2\}$ or $0.5$
uninformative_majority	—	Randomize color in majority env	True , False
Watermark Configuration
watermark_bank_size	$K$	Distinct patterns per environment	$1$ to $100$ (log-spaced)

Appendix

Table E.1 : Hyperparameters for the Watermarked CMNIST Experiments

Neural Network Generalization

Neural network generalization studies why trained models perform well on unseen data and how architecture, data, and training shape that ability.

See all 305 papers

Pointwise Generalization in Deep Neural Networks
May 18, 2026Shaojie Li, Yunbei XuNeural Network Generalization Representation Learning
National University of Singapore
Selection Plateau and a Sparsity-Dependent Hierarchy of Pruning Features
May 10, 2026Guangqi Li, Yongxin LiSparse Neural Networks Neural Network Compression
Zaozhuang University, Zaozhuang, Shandong, China
Quantifying and Optimizing Simplicity via Polynomial Representations
May 28, 2026Tianren Zhang, Xiangxin Li, Minghao Xiao +2Neural Network Generalization Low-Degree Polynomial Method
Department of Automation, Tsinghua University, Beijing, China.

May 18, 2026J/K move · Enter open · S save

Pointwise Generalization in Deep Neural Networks

Shaojie Li, Yunbei Xu

National University of Singapore

Neural Network Generalization Representation Learning Generalization Bounds

Open paper AskPDF arXiv

We address the fundamental question of why deep neural networks generalize by establishing a pointwise generalization theory for fully connected networks. This framework resolves long-standing barriers to characterizing the rich nonlinear feature-learning regime and builds a new statistical foundation for representation learning. For each trained model, we characterize the hypothesis via a pointwise Riemannian Dimension, derived from the eigenvalues of the learned feature representations across layers. This establishes a principled framework for deriving hypothesis-dependent, representation-aware generalization bounds. These bounds offer a systematic upgrade over approaches based on model size, products of norms, and infinite-width linearizations, yielding guarantees that are orders of magnitude tighter in both theory and experiment. Analytically, we identify the structural properties and mathematical principles that explain the tractability of deep networks. Empirically, the pointwise Riemannian Dimension exhibits substantial feature compression, decreases with increased over-parameterization, and captures the implicit bias of optimizers. Taken together, our results indicate that deep networks are mathematically tractable in practical regimes and that their generalization is sharply explained by pointwise, feature-spectrum-aware complexity.

Abstract

Neural Network Generalization

Explore similar work

Pointwise Generalization in Deep Neural Networks

Selection Plateau and a Sparsity-Dependent Hierarchy of Pruning Features

Quantifying and Optimizing Simplicity via Polynomial Representations