{"total":67,"rows":[{"id":"2305.18887","title":"How Does Information Bottleneck Help Deep Learning?","created":"2023-05-30","cited_by_count":93,"area":null},{"id":"2304.05366","title":"The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning","created":"2023-04-11","cited_by_count":63,"area":null},{"id":"2503.02113","title":"Deep Learning is Not So Mysterious or Different","created":"2025-03-03","cited_by_count":56,"area":null},{"id":"2312.17173","title":"Non-Vacuous Generalization Bounds for Large Language Models","created":"2023-12-28","cited_by_count":53,"area":null},{"id":"2407.18158","title":"Unlocking Tokens as Data Points for Generalization Bounds on Larger Language Models","created":"2024-07-25","cited_by_count":25,"area":null},{"id":"2405.01964","title":"Position: Understanding LLMs Requires More Than Statistical Generalization","created":"2024-05-03","cited_by_count":21,"area":null},{"id":"2306.00788","title":"Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression","created":"2023-06-01","cited_by_count":20,"area":null},{"id":"2312.02517","title":"Simplifying Neural Network Training Under Class Imbalance","created":"2023-12-05","cited_by_count":18,"area":null},{"id":"2402.06323","title":"How Uniform Random Weights Induce Non-uniform Bias: Typical Interpolating Neural Networks Generalize with Narrow Teachers","created":"2024-02-09","cited_by_count":18,"area":null},{"id":"2306.12214","title":"More PAC-Bayes bounds: From bounded losses, to losses with general tail behaviors, to anytime validity","created":"2023-06-21","cited_by_count":17,"area":null},{"id":"2306.04375","title":"Learning via Wasserstein-Based High Probability Generalisation Bounds","created":"2023-06-07","cited_by_count":12,"area":null},{"id":"2402.03994","title":"Efficient Sketches for Training Data Attribution and Studying the Loss Landscape","created":"2024-02-06","cited_by_count":10,"area":null},{"id":"2506.03470","title":"Models of Heavy-Tailed Mechanistic Universality","created":"2025-06-04","cited_by_count":10,"area":null},{"id":"2303.05369","title":"Data-dependent Generalization Bounds via Variable-Size Compressibility","created":"2023-03-09","cited_by_count":9,"area":null},{"id":"2306.05862","title":"Lessons from Generalization Error Analysis of Federated Learning: You May Communicate Less Often!","created":"2023-06-09","cited_by_count":8,"area":null},{"id":"2401.17898","title":"Multitask methods for predicting molecular properties from heterogeneous data","created":"2024-01-31","cited_by_count":8,"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":"2312.04658","title":"PAC-Bayes Generalization Certificates for Learned Inductive Conformal Prediction","created":"2023-12-07","cited_by_count":6,"area":null},{"id":"2509.22445","title":"Bridging Kolmogorov Complexity and Deep Learning: Asymptotically Optimal Description Length Objectives for Transformers","created":"2025-09-26","cited_by_count":6,"area":null},{"id":"2310.10534","title":"Comparing Comparators in Generalization Bounds","created":"2023-10-16","cited_by_count":5,"area":null},{"id":"2311.07013","title":"A PAC-Bayesian Perspective on the Interpolating Information Criterion","created":"2023-11-13","cited_by_count":5,"area":null},{"id":"2501.19067","title":"From Low Intrinsic Dimensionality to Non-Vacuous Generalization Bounds in Deep Multi-Task Learning","created":"2025-01-31","cited_by_count":5,"area":null},{"id":"2504.15208","title":"Compute-Optimal LLMs Provably Generalize Better With Scale","created":"2025-04-21","cited_by_count":5,"area":null},{"id":"2303.00196","title":"Transformed Low-Rank Parameterization Can Help Robust Generalization for Tensor Neural Networks","created":"2023-03-01","cited_by_count":4,"area":null},{"id":"2308.15466","title":"Input margins can predict generalization too","created":"2023-08-29","cited_by_count":4,"area":null},{"id":"2312.09323","title":"Perspectives on the State and Future of Deep Learning - 2023","created":"2023-12-07","cited_by_count":4,"area":null},{"id":"2406.04047","title":"Slicing Mutual Information Generalization Bounds for Neural Networks","created":"2024-06-06","cited_by_count":4,"area":null},{"id":"2503.08231","title":"How good is PAC-Bayes at explaining generalisation?","created":"2025-03-11","cited_by_count":4,"area":null},{"id":"2510.10693","title":"High-Dimensional Learning Dynamics of Quantized Models with Straight-Through Estimator","created":"2025-10-12","cited_by_count":4,"area":null},{"id":"2601.08100","title":"Towards A Unified PAC-Bayesian Framework for Norm-based Generalization Bounds","created":"2026-01-13","cited_by_count":4,"area":null},{"id":"2309.05292","title":"The fine print on tempered posteriors","created":"2023-09-11","cited_by_count":3,"area":null},{"id":"2406.11463","title":"Just How Flexible are Neural Networks in Practice?","created":"2024-06-17","cited_by_count":3,"area":null},{"id":"2410.13577","title":"Generalization Bounds via Meta-Learned Model Representations: PAC-Bayes and Sample Compression Hypernetworks","created":"2024-10-17","cited_by_count":3,"area":null},{"id":"2605.08896","title":"FragileFlow: Spectral Control of Correct-but-Fragile Predictions for Foundation Model Robustness","created":"2026-05-09","cited_by_count":3,"area":null},{"id":"2311.04561","title":"Information-Theoretic Generalization Bounds for Transductive Learning and its Applications","created":"2023-11-08","cited_by_count":2,"area":null},{"id":"2503.07325","title":"Non-vacuous Generalization Bounds for Deep Neural Networks without any modification to the trained models","created":"2025-03-10","cited_by_count":2,"area":null},{"id":"2505.15496","title":"Fast Rate Bounds for Multi-Task and Meta-Learning with Different Sample Sizes","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2505.19087","title":"Temperature is All You Need for Generalization in Langevin Dynamics and other Markov Processes","created":"2025-05-25","cited_by_count":2,"area":null},{"id":"2509.25979","title":"Reconcile Certified Robustness and Accuracy for DNN-based Smoothed Majority Vote Classifier","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2601.01465","title":"Leveraging Flatness to Improve Information-Theoretic Generalization Bounds for SGD","created":"2026-01-04","cited_by_count":2,"area":null},{"id":"2602.23128","title":"Bound to Disagree: Generalization Bounds via Certifiable Surrogates","created":"2026-02-26","cited_by_count":2,"area":null},{"id":"2605.10878","title":"Neural Weight Norm = Kolmogorov Complexity","created":"2026-05-11","cited_by_count":2,"area":null},{"id":"2310.20053","title":"Estimating optimal PAC-Bayes bounds with Hamiltonian Monte Carlo","created":"2023-10-30","cited_by_count":1,"area":null},{"id":"2312.13259","title":"A note on regularised NTK dynamics with an application to PAC-Bayesian training","created":"2023-12-20","cited_by_count":1,"area":null},{"id":"2409.01498","title":"A practical generalization metric for deep networks benchmarking","created":"2024-09-02","cited_by_count":1,"area":null},{"id":"2505.21813","title":"Optimizing Data Augmentation through Bayesian Model Selection","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2601.22756","title":"Understanding Generalization from Embedding Dimension and Distributional Convergence","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2604.10553","title":"Topology-Aware PAC-Bayesian Generalization Analysis for Graph Neural Networks","created":"2026-04-12","cited_by_count":1,"area":null},{"id":"2606.08799","title":"Generalization in Nonlinear Least Squares via Learned Feature Geometry","created":"2026-06-07","cited_by_count":1,"area":null},{"id":"2303.15464","title":"Mathematical Challenges in Deep Learning","created":"2023-03-24","cited_by_count":0,"area":null},{"id":"2304.13479","title":"Fundamental Tradeoffs in Learning with Prior Information","created":"2023-04-26","cited_by_count":0,"area":null},{"id":"2307.09379","title":"Generalization within in silico screening","created":"2023-07-18","cited_by_count":0,"area":null},{"id":"2502.17305","title":"`Generalization is hallucination' through the lens of tensor completions","created":"2025-02-24","cited_by_count":0,"area":null},{"id":"2505.15064","title":"Why and When Deep is Better than Shallow: Implementation-Agnostic State-Transition Model of Deep Learning","created":"2025-05-21","cited_by_count":0,"area":null},{"id":"2505.15579","title":"Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensions","created":"2025-05-21","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":"2510.18934","title":"Position: Many generalization measures for deep learning are fragile","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2602.22936","title":"Generalization Bounds of Stochastic Gradient Descent in Homogeneous Neural Networks","created":"2026-02-26","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":"2604.17219","title":"PAC-Bayes Bounds for Gibbs Posteriors via Singular Learning Theory","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2605.26222","title":"From Privacy to Generalization: Linear Max-Information Bounds for Differentially Private Learning Algorithms","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.10196","title":"Fisher-Guided Progressive Parameter Selection for Adaptive Fine-Tuning","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2607.23454","title":"Generalization bounds and sample complexity for remaining useful life prediction from complete degradation trajectories","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2608.03386","title":"Benign interpolation and Occam's razor","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2609.31996","title":"Can Circuit Alignment Predict OOD Generalization?","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.32271","title":"Certification Frontiers for Gaussian LoRA: Independent Priors, Posterior Risk, and Prediction-Preserving Balancing","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.13123","title":"Why Heavy-Tailed Weight Spectra Predict Model Quality","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}