Monotonicity

Follow this topic Ask about this topic

Momentum

12 papers in the last four weeks, up 200% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 71

All topics

Measuring Learned Monotone Temporal Aggregation at Matched Admissibility
Oct 4, 2026Yew Lee TanMonotonicity
This work was conducted in a personal capacity; the views expressed are the author’s own.
Fixing a Model That Learned Worse Cancer Means Lower Risk: Monotonic Constraints in Bladder Cancer Recurrence Prediction
Oct 1, 2026Saram Abbas, David Thomas, Naeem Soomro +3Multidisciplinary Tumor Boards Multicenter Evaluation
School of Engineering, Newcastle University, Newcastle upon Tyne, UK · Electronics and Computer Science, University of Southampton, Southampton, UK · Department of Urology, Freeman Hospital, Newcastle upon Tyne, UK +1
Elicitation and Decision Geometry in Single-Index Bandits
Sep 28, 2026Sakshi Arya, Cheng Soon OngMonotonicity Reward Functions
Case Western Reserve University, USA · CSIRO, Australia
Query Expansion and Key Specialization in Transformer Attention Geometry
Sep 28, 2026Vidit Gupta, Siddhesh Nadkarni, Mihik Chaudhari +2Transformer Attention Transformer Architectures
Dwarkadas J. Sanghvi College of Engineering Mumbai, India
Iterative Atom Refinement: A Monotonicity Principle for Dictionary Learning
Sep 20, 2026Alexander Christie, Miguel Moscoso, Alexei Novikov +2Unsupervised Dictionary Learning Iterative Refinement
Department of Mathematics, Stanford University, Stanford, CA 94305, USA · Department of Mathematics, Universidad Carlos III de Madrid, Leganés, Madrid 28911, Spain · Department of Mathematics, Pennsylvania State University, University Park, PA 16802, USA +1
Falling Trees: A Model Class for Interpretable Risk Prioritization
Sep 20, 2026Varun Babbar, Zachery Boner, Margo Seltzer +1Decision Trees Risk Stratification
Department of Computer Science, Duke University, Durham, NC, USA · Department of Computer Science, University of British Columbia, Vancouver, BC, CA.
Minimax-Optimal Online Contract Design with Unrestricted Bounded Contracts
Sep 17, 2026Rui Ai, David Simchi-Levi, Han ZhongContracts Monotonicity
Massachusetts Institute of Technology · Shanghai Jiao Tong University
Causal Discovery via Transformed Low-Rank Quantile Surfaces
Sep 15, 2026Ryo Kamimura, Thong PhamCausal Modeling Quantile Regression
1Shiga University · 3RIKEN AIP · 2The University of Osaka
Anchored Sequential Deliberation
Sep 15, 2026Sijing Tu, Ashish GoelDeliberation Collective Behaviors
Management Science and Engineering, Stanford University
Thompson Sampling for Non-Monotone Convex Ridge Bandits: Monotonicity Is Not Needed for Polynomial Regret
Sep 11, 2026Xuan LiThompson Sampling Convex Loss
University of New South Wales, Sydney, Australia
Nonmaximal sums of maximally monotone operators under Rockafellar's constraint qualification
Sep 9, 2026Weifeng YangMonotone Variational Inequalities Monotonicity
Beyond Top Words: MonoTM for Topic Modeling with Interpretable Monosemantic Features
Sep 9, 2026Una Joh, Bei YuTopic Modeling Semantic Representations
School of Information Studies Syracuse University
Reasoning Shortcuts and Value Symmetries: What Symmetry Permits, Architecture Realizes, and Optimization Selects
Aug 11, 2026Xin XuSymmetry Symbol-
Carnegie Mellon University · University of Pennsylvania
Invertible Logits Transformation for Accuracy-Preserving Post-Hoc Uncertainty Calibration
Aug 11, 2026Lening Zhao, Qipeng Zhan, Li ShenLogit Lens Post-Hoc
University of Pennsylvania
Online Learning of Scale Parameters in Score-Driven Filters
Aug 10, 2026Fabrizio Lillo, Giulia Livieri, Gianluca PalmariMirror Descent Sequential Scaling
Scuola Normale Superiore, Piazza dei Cavalieri 7, Pisa, Italy · Department of Statistics, London School of Economics and Political Science, Columbia House, 69 Aldwych, London, United Kingdom
Latent World Models with Monotone Planning Costs for Image-Goal Navigation
Aug 10, 2026Amirhosein Chahe, Siwei Cai, Lifeng ZhouLatent World Models Object Goal Navigation
Drexel University
Provable Limits and Certified Deferral for Verbalized Uncertainty in Small Language Models
Aug 5, 2026Jianru ShenConfidence Calibration Small Large Language Models
University of Montana, Missoula, MT 59812, USA
Caliber: Cross-Architecture Extraction-Cost Control for Score-Returning APIs
Aug 2, 2026Chi Wang, Hanwen Wang, Yu Xia +2Model-Agnostic Defense Cross-Architecture Generalization
University of Queensland, Brisbane, Australia · Adelaide University, Adelaide, Australia · Beijing Technology and Business University, Beijing, China +1
TraceViT: Grounded Trace Supervision for Visual Abstract Reasoning
Jul 31, 2026Binnan Liu, Yechi Ma, Tian Xie +1Visual Reasoning Traces
1Zhejiang University · 2Zhejiang Lab
Transcript-Managed Transformers: Monotone Multi-Agent Collapse and Universality with Two Pop-Enabled Transcripts
Jul 31, 2026Sergey SalishevAutomata Transcript
AI Foundry San Francisco, CA, USA
Representative Sets in Propositional Abduction
Jul 23, 2026Johannes Schmidt, Mohamed Maizia, Victor Lagerkvist +1Abductive Reasoning Monotonicity
Jönköping University · Jönköping University, Linköping University · Linköping University
Physically Constrained Federated Additive Models for O-RAN SLA-Risk Prediction
Jul 23, 2026Aubida A. Al-Hameed, Mohammed M. H. Qazzaz, Maryam Hafeez +1Open Radio Access Networks Conformal Risk Control
College of Electronics Engineering, Ninevah University, Mosul, Iraq · School of Electronic and Electrical Engineering, University of Leeds, Leeds, UK
Selection Shapes the Boundary: A Preregistered Replication of Monotonicity and Label Agreement in Unselected NLI Populations
Jul 21, 2026Haram ChoiNatural Language Inference Monotonicity
University of Bremen
Value-Monotonicity Matters: A Concordance Loss for Deep Survival Prediction
Jul 18, 2026Meixu Chen, Kai Wang, Jing WangSurvival Predictions Monotonicity
Department of Radiation Oncology, University of Colorado School of Medicine, Aurora, CO, USA · Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, TX, USA
Win by Silence: Deletion Non-Monotonicity, Autonomous Exploitation, and Typed-State Gating in LLM Plan Evaluation
Jul 14, 2026Aleh ManchuliantsauLarge Language Model Planning Destination-Only Scoring
Independent Researcher
Non-Convex Sparse Reinforcement Learning via Non-Monotone Inclusions
Jul 6, 2026Kyohei Suzuki, Konstantinos SlavakisEntropy Regularized Reinforcement Learning Lipschitz Continuity
Department of Information and Communications Engineering, Institute of Science Tokyo, Yokohama, 226-8501, Japan
Securing Multi-Tool AI Agent Chains With Dynamic, Real-Time Compositional Policies
Jul 3, 2026Chris Schneider, Kriti Faujdar, Philipp Schoenegger +1Monotonicity
1Microsoft AI · 2Microsoft
Unveiling the Non-Monotonic Effect of Privacy on Generalization under Byzantine Robustness
Jul 1, 2026Thomas Boudou, Batiste Le Bars, Nirupam Gupta +1Generalization Bounds Byzantine Attacks
Inria, Université de Montpellier, INSERM · Montpellier, France · Inria, Université de Lille +3
Deep Multitask Learning for Mixed-Type Outcomes with Shared Sparsity
Jul 1, 2026Huichao Li, Tong Wang, Sanguo Zhang +1Multi--Task Learning Sparsity
School of Mathematical Sciences, University of Chinese Academy of Sciences · School of Statistics and Data Science, Southeast University, Nanjing, Jiangsu, China · School of Mathematical Sciences, University of Chinese Academy of Sciences, Beijing, China +2
Dangerous Liaisons of Convex Learning and Non-Affine Aggregation
Jun 26, 2026Thomas Boudou, Batiste Le Bars, Nirupam Gupta +1Convergence Monotonicity
PreMeDICaL team, Inria, Idesp, Inserm, Universit´e de Montpellier, Montpellier, France · Univ. Lille, Inria, CNRS, Centrale Lille, UMR 9189, CRIStAL, F-59000 Lille, France · Department of Computer Science, University of Copenhagen, Copenhagen, Danemark
Beyond Monotonic Progress: Retry-Supervised Value Learning for Robot Imitation
Jun 23, 2026Xinyao Qin, Junjie Lu, Kaixin Wang +7Imitation Value Functions
Tsinghua University · Work done at Microsoft Research Asia · University of Technology Sydney +3
On the QUEST for Uncertainty Quantification via Highest Density Regions
Jun 17, 2026Sam Goring, Tom Kuipers, Nicola Paoletti +1Uncertainty Quantification Uncertainty
King’s College London · Northeastern University London
LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling
Jun 16, 2026Jian Yang, Shawn Guo, Wei Zhang +16Code Optimization Loop
1Beihang University · 2IQuest Research · 4Renming University of China +1
Monotonic Kolmogorov-Arnold Networks: A Theoretical and Empirical Study of Monotonicity as an Inductive Bias
Jun 16, 2026Mikhail Krasnov, Blaž Bertalanič, Carolina FortunaKolmogorov-Arnold Networks Monotonicity
Jozef Stefan Institute
Transfer Learning Across Policy Regimes in Adaptive Multi-Agent Systems
Jun 15, 2026Roberto GarroneTransfer Learning Regulation
Open University of Cyprus
Polynomial-Time Mistake-Bounded Language Generation
Jun 15, 2026Héctor Jimenez, Alexander Kozachinskiy, Vicente OpazoPolynomials Context-Free Grammars
University of Chile · CENIA
Fitting scattered data with optional monotonicity constraints on GPU: LipFit package
Jun 3, 2026Gleb BeliakovLipschitz Continuity Interpolation
School of Information Technology, Deakin University, Burwood 3125, Australia
Towards Non-Monotonic Entailment in Propositional Defeasible Standpoint Logic
Jun 2, 2026Nicholas Leisegang, Thomas Meyer, Ivan VarzniczakLogic Entailment
University of Cape Town and CAIR, South Africa · 2Université Sorbonne Paris Nord, Inserm, Sorbonne Université, Limics, 93017 Bobigny, France · 3ISTI-CNR, Pisa, Italy
A Nonmonotone Gradient-Based Algorithm for Symmetric Nonnegative Matrix Factorization and Graph Clustering
Jun 1, 2026Ryan Swart, Johannes BrustNonnegative Matrix Factorization Community Detection
School of Mathematical and Statistical Sciences, Arizona State University, Tempe, AZ
Model Monotonicity in Autobidding Auctions: When Do Better Predictions Lead to Better Outcomes?
May 29, 2026Ashwinkumar BadanidiyuruFirst-Price Auctions Bidding
Uber Technologies, Inc., San Francisco, CA, USA.
Hedging on the Frontier: Learning New Tasks with Few Samples
May 29, 2026Tobias Wegel, Federico Di Gennaro, Geelon So +1Learnability Monotonicity
Department of Computer Science, ETH Zurich · Department of Computer Science and Engineering, UC San Diego
Preference-Shaped Expected Hypervolume and R2 Improvement: Exact Computation and Monotonicity
May 27, 2026Michael T. M. EmmerichMulti-Objective Optimization Monotonicity
Faculty of Information Technology, University of Jyväskylä, Finland
Relevant Is Not Warranted: Evidence-Force Calibration for Cited RAG
May 27, 2026Pin Qian, Su Wang, Xiaoyuan Wang +7Citations Stress Testing
Carnegie Mellon University · Georgia Institute of Technology · Dartmouth College +3
Privately Estimating Monotone Statistics in Polynomial Time
May 27, 2026Gavin Brown, Ephraim Linder, Mahbod Majid +1Optimal Sample Complexity Statistical Inference
University of Wisconsin–Madison · Boston University · MIT Mathematics +1
Probabilistic Smoothing with Ratio-Monotone Transforms for Global Optimization
May 26, 2026Kukyoung Jang, Taehyun Cho, Junrui Zhang +2Smoothing Kernel Method
Department of Statistics, Seoul, Korea University · Department of Electrical and Computer Engineering, Seoul, Seoul National University · Shandong University at Weihai, Weihai, China.
It's Not the Capability: Harness Sensitivity Is Non-Monotone Across LLM Agent Tiers
May 26, 2026Yong-eun ChoFrontier Large Language Model Agents Agent Harness
KailosLab · Seoul, Republic of Korea
ChainCaps: Composition-Safe Tool-Using Agents via Monotonic Capability Attenuation
May 26, 2026Xiaochong Jiang, Shiqi Yang, Ziwei Li +3Bottlenecks Token Budget Allocation
Independent Researcher, Seattle, WA, USA · Independent Researcher, New York City, NY, USA · King Abdullah University of Science and Technology, Saudi Arabia
Learning Nonlinear Factor Models with Unknown Monotone Links from Incomplete and Noisy Data
May 25, 2026Yutong Chao, Resat Gökhan, Jalal Etesami +1Exploratory Factor Analysis Nonlinearity
School of Computation, Information and Technology, Technical University of Munich, Germany · Munich Institute of Robotics and Machine Intelligence · Department of Economics, Virginia Tech, USA
Evidential Information Fusion on Possibilistic Structure
May 16, 2026Qianli Zhou, Ye Cui, Zhen Li +2Evidence Fusion Evidential Uncertainty
School of Electronics and Information, Northwestern Polytechnical University, Xi’an 710072, China · Department of Electrical and Computer Engineering, University of Alberta, Edmonton, AB T6G 1H9, Canada · China Mobile Information Technology Center, Beijing, 100029, China +4
A Non-Monotone Preconditioned Trust-Region Method for Neural Network Training
May 14, 2026Andrea Angino, Bindi Çapriqi, Shega Likaj +2Spectral Preconditioning Trust Region
UniDistance Suisse · King Abdullah University of Science and Technology · Universit`a della Svizzera italiana
On Strong Equivalence Notions in Logic Programming and Abstract Argumentation
May 14, 2026Giovanni Buraglio, Wolfgang Dvorak, Stefan WoltranLogic Equivalence
TU Wien, Austria
Online Conformal Prediction: Enforcing monotonicity via Online Optimization
May 12, 2026Eduardo Ochoa Rivera, Ambuj TewariOnline Conformal Prediction Multi-Quantile Regression
University of Michigan · Ann Arbor, USA
Is Monotonic Sampling Necessary in Diffusion Models?
May 12, 2026Muhammad Haris KhanDiffusion Sampling Diffusion Models
Department of Computer Science, University of Copenhagen, Denmark
Trust Region Inverse Reinforcement Learning: Explicit Dual Ascent using Local Policy Updates
May 10, 2026Anish Diwan, Davide Tateo, Christopher E. Mower +3Offline Reinforcement Learning Reward Functions
Technical University of Darmstadt · Robotics Institute Germany (RIG) · Lund University +3
Curvature Beyond Positivity: Greedy Guarantees for Arbitrary Submodular Functions
May 8, 2026Yixin Chen, Alan KuhnleSubmodular Functions Local Curvature
Department of Computer Science & Engineering, Texas A&M University
Quotient Semivalues for False-Name-Resistant Data Attribution
May 8, 2026Florian A. D. Burnat, Brittany I. DavidsonFalsehood Monotonicity
School of Management, University of Bath, UK.
Counterfactual identifiability beyond global monotonicity: non-monotone triangular structural causal models
May 6, 2026Pengcheng Tan, Jiang Chen, Dehui DuMonotonicity
Shanghai Key Laboratory of Trustworthy Computing, East China Normal University
MoRFI: Monotonic Sparse Autoencoder Feature Identification
Apr 29, 2026Dimitris Dimakopoulos, Shay B. Cohen, Ioannis KonstasLarge Language Model Hallucination Model Fine-Tuning
University of Edinburgh, UK · Heriot-Watt University, UK
State-Dependent Lyapunov Analysis of Rank-1 Matrix Factorization
Apr 28, 2026Jaehong MoonLyapunov Function Step Accuracy
Industrial & Enterprise Systems Engineering University of Illinois at Urbana-Champaign Urbana, IL 61801
CoGReV: A Confidence-Gated Post-Hoc Non-Monotonic Belief Revision Framework for Phishing Website Classification
Apr 28, 2026Mainak Sen, Kumar Sankar Ray, Amlan ChakrabartiPhishing Contextual Reasoning
Techno India University, West Bengal, India · A. K. Choudhury School of Information Technology, University of Calcutta, Kolkata, India · Electronics and Communication Sciences Unit (ECSU), Indian Statistical Institute, Kolkata, India +1

Oct 4, 2026, cs.LGJ/K move · Enter open · S save

Measuring Learned Monotone Temporal Aggregation at Matched Admissibility

Yew Lee Tan

This work was conducted in a personal capacity; the views expressed are the author’s own.

Monotonicity

Open paper AskPDF arXiv

Risk regulation imposes directional constraints on scores; we adopt their strict per-input form -- the score monotone non-decreasing in every exposure input -- as a normative commitment. Deployed pipelines -- monotone hand-crafted aggregates feeding sign-constrained gradient boosting -- already satisfy it by composition, so constrained-versus-unconstrained comparisons price a guarantee the incumbent has for free. We instead hold admissibility fixed on both sides and measure what learning the aggregation is worth. Our instrument is a recurrent network whose state is classical risk statistics (an exponentially weighted moving average and a high-water mark with learned transforms), monotone by construction in every input and per MC-dropout sample. The central finding, by functional regression, is a subsumption boundary: a learned monotone channel reproduces the geometrically weighted separable family of hand-crafted statistics, one channel per member, to Spearman

ρ\ge 0.996

, approximates window statistics with measurable ceilings, and fails at consecutivity (

ρ= 0.924

) and time localization (0.628), both structural, and at the exposure floor (0.829), a learnability boundary. One explicit admissible basis repairs each failure (rank correlation 1.000). In or near the separable family, learned and engineered aggregation are substitutes, and the learned channel is never statistically behind at full sample size and specified capacity. Its advantages are incumbent-specific: a committed grid pays up to 0.019 AUC in decay regions it leaves uncovered (the learned channel stays within 0.004 of the strongest engineered consumer at every swept point); the highest-dimensional comparator degrades fastest with scarce data; and beyond the training support, grid-fed tree-ensemble scores go flat while a strictly increasing head keeps ranking. No single incumbent is dominated on all three axes.

Momentum

Related topics

Latest papers 71