Overview

Generalization bounds estimate how well a model trained on finite data will perform on new examples, helping explain when learning is reliable. Common tools include VC and Rademacher complexity, covering numbers, PAC-Bayes and information-theoretic bounds, and algorithmic stability. For deep networks and modern settings, analyses increasingly use learned feature geometry, optimization dynamics, and structure in data, while extending guarantees to distribution shift, generative models, and dependent or distributed samples. A central tension is that broad worst-case guarantees can be too loose to be useful, whereas tighter, non-vacuous bounds often rely on assumptions about the algorithm, data geometry, or shift between training and test distributions.

Latest papers

CardsList

172 papers12 papers in the last four weeks, down 50% on the four weeks before. 0.1% of all new papers.

  1. Unveiling the Non-Monotonic Effect of Privacy on Generalization under Byzantine Robustness

    Jul 1, 2026Thomas Boudou, Batiste Le Bars, Nirupam Gupta +1Differential PrivacyDistributed Training

  2. A Generalization Theory for JEPA-Based World Models

    Jun 25, 2026Jingyi Cui, Qi Zhang, Hongwei Wen +1World Model LearningJoint-Embedding Predictive Architecture

  3. Non-asymptotic estimates of the minimal risk in statistical learning

    Jun 22, 2026Liming Wu, Sen YangStatistical Learning TheoryEmpirical Risk Minimization

  4. Formalizing and Estimating Task-Space Complexity for Zero-shot Generalization

    Jun 18, 2026Jung-Hoon Cho, Heling Zhang, Siqi Du +2Zero-Shot LearningGeneralization Bounds

  5. On Local Population-Risk Certificates

    Jun 17, 2026Mingzhi SongCross-FittingStatistical Learning Theory

  6. From Sparse Features to Trustworthy Proxies: Certifying SAE-Based Interpretability

    Jun 16, 2026Dibyanayan Bandyopadhyay, Asif EkbalLLM InterpretabilitySparse Autoencoders

  7. Generalization Guarantees for Multi-Input Neural Operator Learning in Sobolev Spaces

    Jun 16, 2026Yahong Yang, Zecheng Zhang, Wei Zhu +2Neural Network Approximation TheoryOperator Learning

  8. Upper Bounds on the Generalization Error of Deep Learning Models via Local Robustness and Stability

    Jun 15, 2026Abdul-Rauf Nuhu, Parham M. Kebria, Vahid Hemmati +3Neural Network GeneralizationNeural Network Robustness

  9. Brownian Kernel Ladders

    Jun 14, 2026Mahdi Mohammadigohari, Giuseppe Di Fatta, Giuseppe Nicosia +1Hierarchical Representation LearningReproducing Kernel Hilbert Spaces

  10. The Data Manifold under the Microscope

    Jun 14, 2026Marios Koulakis, Constantin SeiboldIntrinsic DimensionalitySynthetic Benchmark Generation

  11. Beyond LoRA: Is Sparsity-Induced Adaptation Better?

    Jun 11, 2026Elijah Cadenhead, Cristian McGee, Xin Li +2Low-Rank AdaptationParameter-Efficient Fine-Tuning

  12. Bidirectional Random Projections

    Jun 9, 2026Chao Lan, Luyuan YangRandomized SketchingLinear Regression

  13. Generalization in Nonlinear Least Squares via Learned Feature Geometry

    Jun 7, 2026Ayub Kharel, Ilja Kuzborskij, Patrick Rebeschini +1Neural Representation GeometryAlgorithmic Stability

  14. A Joint Finite-Sample Certificate for Adaptive Selective Conformal Risk Control

    Jun 7, 2026Xiaoli Yu, Jiamiao LiuSelective PredictionConformal Risk Control

  15. Uniform Stability and Generalization Error of GD and SGD on Fixed-Point Parameters

    Jun 5, 2026Jonghyun Shin, Sejun ParkAlgorithmic StabilityGradient Descent

  16. Stability beyond Bounded Differences: Sharp Generalization Bounds under Finite LpL_p Moments

    Jun 5, 2026Qianqian Lei, Soham Bonnerjee, Yuefeng Han +1Algorithmic StabilityGeneralization Bounds

  17. Generalization in Deep Neural Networks: Minimax Rates for Gradient Methods

    Jun 4, 2026Junyu Zhou, Puyu Wang, Yunwen Lei +2Neural Network GeneralizationGradient Descent Dynamics

  18. Measurement-Budget Allocation in Quantum Learning with Finite-Shot Generalization Guarantees

    Jun 1, 2026Ferhat Ozgur CatakQuantum Machine LearningGeneralization Bounds

  19. A Note on Stability for Orthogonalized Matrix Momentum with Client Sampling

    Jun 1, 2026Da Chang, Qiankun Shi, Lvgang Zhang +2Algorithmic StabilityDistributed Optimization

  20. A Practical Upper Bound on Selection Bias Effects in Medical Prediction Models

    May 30, 2026Kara Liu, Maggie Wang, Russ B. AltmanOOD GeneralizationSelection Bias

  21. Stochastic Gradient Descent with Momentum is Algorithmically Stable

    May 27, 2026Yunwen Lei, Zimeng Wang, Xiaoming YuanMomentum MethodsAlgorithmic Stability

  22. Learning Theory of the SVRG: Generalization and Convergence Analysis

    May 27, 2026Yunwen Lei, Zimeng Wang, Xiaoming YuanStochastic Optimization ConvergenceVariance Reduction

  23. A PAC-Bayesian View of Generalisation for Physics-Informed Machine Learning

    May 25, 2026Thien V. Nguyen, Amaury Habrard, Benjamin GuedjPAC-Bayesian Generalization BoundsPhysics-Informed ML

  24. On the Regularity and Generalization of One-Step Wasserstein-guided Generative Models for PDE-Induced Measures

    May 20, 2026Likun Lin, Zhongjian Wang, Jack Xin +1One-Step Generative ModelingOptimal Transport

  25. A Measure-Theoretic Analysis of Reasoning in Transformers: Structural Generalization and Approximation Limits

    May 19, 2026Yuyang Zhang, Yifu Zhang, Xuehai Zhou +1Transformer ExpressivityOOD Generalization

  26. Pointwise Generalization in Deep Neural Networks

    May 18, 2026Shaojie Li, Yunbei XuNeural Network GeneralizationRepresentation Learning

  27. Shallow ReLUs^s Networks in LpL^p-Type and Sobolev Spaces: Approximation and Path-Norm Controlled Generalization

    May 18, 2026Weizhao Li, Fanghui Liu, Lei ShiShallow Neural NetworksNonparametric Regression