{"total":71,"rows":[{"id":"2005.13239","title":"MOPO: Model-based Offline Policy Optimization","created":"2020-05-27","cited_by_count":636,"area":"offlinerl"},{"id":"2107.13163","title":"Statistically Meaningful Approximation: a Case Study on Approximating Turing Machines with Transformers","created":"2021-07-28","cited_by_count":102,"area":null},{"id":"2210.14199","title":"Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models","created":"2022-10-25","cited_by_count":84,"area":null},{"id":"2111.04578","title":"Improved Regularization and Robustness for Fine-tuning in Neural Networks","created":"2021-11-08","cited_by_count":45,"area":null},{"id":"2102.04877","title":"Noisy Recurrent Neural Networks","created":"2021-02-09","cited_by_count":42,"area":null},{"id":"2211.14699","title":"A Theoretical Study of Inductive Biases in Contrastive Learning","created":"2022-11-27","cited_by_count":40,"area":null},{"id":"2302.04451","title":"Generalization in Graph Neural Networks: Improved PAC-Bayesian Bounds on Graph Diffusion","created":"2023-02-09","cited_by_count":40,"area":null},{"id":"2307.11007","title":"Sharpness Minimization Algorithms Do Not Only Minimize Sharpness To Achieve Better Generalization","created":"2023-07-20","cited_by_count":39,"area":null},{"id":"2104.05641","title":"Generalization bounds via distillation","created":"2021-04-12","cited_by_count":34,"area":null},{"id":"2110.02180","title":"Noisy Feature Mixup","created":"2021-10-05","cited_by_count":27,"area":null},{"id":"2407.08039","title":"Knowledge Overshadowing Causes Amalgamated Hallucination in Large Language Models","created":"2024-07-10","cited_by_count":25,"area":null},{"id":"2311.11871","title":"Training robust and generalizable quantum models","created":"2023-11-20","cited_by_count":21,"area":null},{"id":"2207.00614","title":"Integral Probability Metrics PAC-Bayes Bounds","created":"2022-07-01","cited_by_count":19,"area":null},{"id":"2303.01052","title":"Demystifying Causal Features on Adversarial Examples and Causal Inoculation for Robust Network by Adversarial Instrumental Variable Regression","created":"2023-03-02","cited_by_count":18,"area":null},{"id":"2202.13216","title":"Adversarial robustness of sparse local Lipschitz predictors","created":"2022-02-26","cited_by_count":11,"area":null},{"id":"2301.12309","title":"On the Lipschitz Constant of Deep Networks and Double Descent","created":"2023-01-28","cited_by_count":11,"area":null},{"id":"2406.00588","title":"Generalization Bound and New Algorithm for Clean-Label Backdoor Attack","created":"2024-06-02","cited_by_count":11,"area":null},{"id":"2202.08070","title":"On Measuring Excess Capacity in Neural Networks","created":"2022-02-16","cited_by_count":9,"area":null},{"id":"2209.12611","title":"MaxMatch: Semi-Supervised Learning with Worst-Case Consistency","created":"2022-09-26","cited_by_count":9,"area":null},{"id":"2302.05825","title":"Koopman-based generalization bound: New aspect for full-rank weights","created":"2023-02-12","cited_by_count":9,"area":null},{"id":"2305.00608","title":"Differentiable Neural Networks with RePU Activation: with Applications to Score Estimation and Isotonic Regression","created":"2023-05-01","cited_by_count":9,"area":null},{"id":"2307.00426","title":"Sparsity-aware generalization theory for deep neural networks","created":"2023-07-01","cited_by_count":8,"area":null},{"id":"2103.13598","title":"Recent Advances in Large Margin Learning","created":"2021-03-25","cited_by_count":7,"area":null},{"id":"2301.12033","title":"Norm-based Generalization Bounds for Compositionally Sparse Neural Networks","created":"2023-01-28","cited_by_count":7,"area":null},{"id":"2305.14683","title":"On progressive sharpening, flat minima and generalisation","created":"2023-05-24","cited_by_count":7,"area":null},{"id":"2307.11030","title":"Cluster-aware Semi-supervised Learning: Relational Knowledge Distillation Provably Learns Clustering","created":"2023-07-20","cited_by_count":7,"area":"distill"},{"id":"2203.00246","title":"An Information-Theoretic Framework for Supervised Learning","created":"2022-03-01","cited_by_count":6,"area":null},{"id":"2206.07892","title":"Max-Margin Works while Large Margin Fails: Generalization without Uniform Convergence","created":"2022-06-16","cited_by_count":6,"area":null},{"id":"2210.06143","title":"On the Importance of Gradient Norm in PAC-Bayesian Bounds","created":"2022-10-12","cited_by_count":6,"area":null},{"id":"2306.01992","title":"On Size-Independent Sample Complexity of ReLU Networks","created":"2023-06-03","cited_by_count":6,"area":null},{"id":"2306.13239","title":"The Inductive Bias of Flatness Regularization for Deep Matrix Factorization","created":"2023-06-22","cited_by_count":6,"area":null},{"id":"2407.05664","title":"How DNNs break the Curse of Dimensionality: Compositionality and Symmetry Learning","created":"2024-07-08","cited_by_count":6,"area":null},{"id":"2502.01473","title":"Generalization Error Analysis for Selective State-Space Models Through the Lens of Attention","created":"2025-02-03","cited_by_count":5,"area":"ssm"},{"id":"2511.20888","title":"Deep Learning as a Convex Paradigm of Computation: Minimizing Circuit Size with ResNets","created":"2025-11-25","cited_by_count":5,"area":null},{"id":"2206.05749","title":"Regularization Penalty Optimization for Addressing Data Quality Variance in OoD Algorithms","created":"2022-06-12","cited_by_count":4,"area":null},{"id":"2206.07277","title":"A Gift from Label Smoothing: Robust Training with Adaptive Label Smoothing via Auxiliary Classifier under Label Noise","created":"2022-06-15","cited_by_count":4,"area":null},{"id":"2312.09793","title":"PAC-Bayes Generalisation Bounds for Dynamical Systems Including Stable RNNs","created":"2023-12-15","cited_by_count":4,"area":null},{"id":"2410.11985","title":"The Fair Language Model Paradox","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2410.16401","title":"Simplicity Bias via Global Convergence of Sharpness Minimization","created":"2024-10-21","cited_by_count":4,"area":null},{"id":"2412.06381","title":"Gentle Local Robustness implies Generalization","created":"2024-12-09","cited_by_count":4,"area":null},{"id":"2505.04937","title":"Generalization Analysis for Supervised Contrastive Representation Learning under Non-IID Settings","created":"2025-05-08","cited_by_count":4,"area":null},{"id":"2511.03548","title":"Flat Minima and Generalization: Insights from Stochastic Convex Optimization","created":"2025-11-05","cited_by_count":4,"area":null},{"id":"2106.05332","title":"Reinforcement Learning for Industrial Control Network Cyber Security Orchestration","created":"2021-06-09","cited_by_count":3,"area":null},{"id":"2110.00199","title":"Perturbated Gradients Updating within Unit Space for Deep Learning","created":"2021-10-01","cited_by_count":3,"area":null},{"id":"2102.08093","title":"A Law of Robustness for Weight-bounded Neural Networks","created":"2021-02-16","cited_by_count":2,"area":null},{"id":"2405.20278","title":"Length independent generalization bounds for deep SSM architectures via Rademacher contraction and stability constraints","created":"2024-05-30","cited_by_count":2,"area":null},{"id":"2111.02445","title":"Autonomous Attack Mitigation for Industrial Control Systems","created":"2021-11-03","cited_by_count":1,"area":null},{"id":"2203.10571","title":"Distributionally robust risk evaluation with a causality constraint and structural information","created":"2022-03-20","cited_by_count":1,"area":null},{"id":"2208.13080","title":"Information FOMO: The unhealthy fear of missing out on information. A method for removing misleading data for healthier models","created":"2022-08-27","cited_by_count":1,"area":null},{"id":"2211.03570","title":"Do highly over-parameterized neural networks generalize since bad solutions are rare?","created":"2022-11-07","cited_by_count":1,"area":null},{"id":"2212.14838","title":"PAC-Bayesian-Like Error Bound for a Class of Linear Time-Invariant Stochastic State-Space Models","created":"2022-12-30","cited_by_count":1,"area":null},{"id":"2505.23013","title":"Scalable Complexity Control Facilitates Reasoning Ability of LLMs","created":"2025-05-29","cited_by_count":1,"area":"lr"},{"id":"2509.21895","title":"Why High-rank Neural Networks Generalize?: An Algebraic Framework with RKHSs","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2510.07758","title":"R\\'enyi Sharpness: A Novel Sharpness that Strongly Correlates with Generalization","created":"2025-10-09","cited_by_count":1,"area":null},{"id":"2512.19199","title":"On the Koopman-Based Generalization Bounds for Multi-Task Deep Learning","created":"2025-12-22","cited_by_count":1,"area":null},{"id":"2608.15982","title":"Operator-Theoretic Generalization Bounds for Multitask Deep Learning","created":"2026-08-17","cited_by_count":1,"area":null},{"id":"2101.06061","title":"Heating up decision boundaries: isocapacitory saturation, adversarial scenarios and generalization bounds","created":"2021-01-15","cited_by_count":0,"area":null},{"id":"2106.07989","title":"Compression Implies Generalization","created":"2021-06-15","cited_by_count":0,"area":null},{"id":"2202.05510","title":"Support Vectors and Gradient Dynamics of Single-Neuron ReLU Networks","created":"2022-02-11","cited_by_count":0,"area":null},{"id":"2405.10054","title":"A finite-sample generalization bound for stable LPV systems","created":"2024-05-16","cited_by_count":0,"area":null},{"id":"2410.16868","title":"Rethinking generalization of classifiers in separable classes scenarios and over-parameterized regimes","created":"2024-10-22","cited_by_count":0,"area":null},{"id":"2501.02010","title":"Explainable Neural Networks with Guarantees: A Sparse Estimation Approach","created":"2025-01-02","cited_by_count":0,"area":null},{"id":"2503.04111","title":"Generalizability of Neural Networks Minimizing Empirical Risk Based on Expressive Ability","created":"2025-03-06","cited_by_count":0,"area":null},{"id":"2506.00182","title":"Overfitting has a limitation: a model-independent generalization gap bound based on R\\'enyi entropy","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2510.22667","title":"Block Coordinate Descent for Neural Networks Provably Finds Global Minima","created":"2025-10-26","cited_by_count":0,"area":null},{"id":"2511.21787","title":"Dynamical Implicit Neural Representations","created":"2025-11-26","cited_by_count":0,"area":null},{"id":"2602.20178","title":"Data-Driven Deep MIMO Detection:Network Architectures and Generalization Analysis","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2602.23219","title":"Takeuchi's Information Criteria as Generalization Measures for DNNs Close to NTK Regime","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2603.09024","title":"When to Retrain after Drift: A Data-Only Test of Post-Drift Data Size Sufficiency","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2603.09742","title":"Upper Generalization Bounds for Neural Oscillators","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2605.13260","title":"Unified generalization analysis for physics informed neural networks","created":"2026-05-13","cited_by_count":0,"area":null}],"next_cursor":null}