{"total":88,"rows":[{"id":"2110.11216","title":"User-friendly introduction to PAC-Bayes bounds","created":"2021-10-21","cited_by_count":239,"area":null},{"id":"2102.00931","title":"Information-Theoretic Generalization Bounds for Stochastic Gradient Descent","created":"2021-02-01","cited_by_count":84,"area":null},{"id":"2304.09355","title":"To Compress or Not to Compress- Self-Supervised Learning and Information Theory: A Review","created":"2023-04-19","cited_by_count":72,"area":null},{"id":"2110.01584","title":"Information-theoretic generalization bounds for black-box learning algorithms","created":"2021-10-04","cited_by_count":49,"area":null},{"id":"2109.14595","title":"Generalization Bounds For Meta-Learning: An Information-Theoretic Analysis","created":"2021-09-29","cited_by_count":45,"area":null},{"id":"2101.09315","title":"Tighter expected generalization error bounds via Wasserstein distance","created":"2021-01-22","cited_by_count":43,"area":null},{"id":"2110.03128","title":"On the Generalization of Models Trained with SGD: Information-Theoretic Bounds and Implications","created":"2021-10-07","cited_by_count":31,"area":null},{"id":"2111.05275","title":"Towards a Unified Information-Theoretic Framework for Generalization","created":"2021-11-09","cited_by_count":30,"area":null},{"id":"2108.00781","title":"Generalization Bounds using Lower Tail Exponents in Stochastic Optimizers","created":"2021-08-02","cited_by_count":27,"area":null},{"id":"2202.04985","title":"Generalization Bounds via Convex Analysis","created":"2022-02-10","cited_by_count":27,"area":null},{"id":"2202.08311","title":"Single Trajectory Nonparametric Learning of Nonlinear Dynamics","created":"2022-02-16","cited_by_count":26,"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":"2507.20016","title":"FedSWA: Improving Generalization in Federated Learning with Highly Heterogeneous Data via Momentum-Based Stochastic Controlled Weight Averaging","created":"2025-07-26","cited_by_count":25,"area":null},{"id":"2211.01568","title":"Fine-Tuning Language Models via Epistemic Neural Networks","created":"2022-11-03","cited_by_count":22,"area":null},{"id":"2302.02432","title":"Tighter Information-Theoretic Generalization Bounds from Supersamples","created":"2023-02-05","cited_by_count":22,"area":null},{"id":"2212.13556","title":"Limitations of Information-Theoretic Generalization Bounds for Gradient Descent Methods in Stochastic Convex Optimization","created":"2022-12-27","cited_by_count":19,"area":null},{"id":"2202.12123","title":"An Information-theoretical Approach to Semi-supervised Learning under Covariate-shift","created":"2022-02-24","cited_by_count":18,"area":null},{"id":"2302.04925","title":"Information Theoretic Lower Bounds for Information Theoretic Upper Bounds","created":"2023-02-09","cited_by_count":17,"area":null},{"id":"2210.00706","title":"Information-Theoretic Analysis of Unsupervised Domain Adaptation","created":"2022-10-03","cited_by_count":15,"area":null},{"id":"2302.02766","title":"Generalization Bounds with Data-dependent Fractal Dimensions","created":"2023-02-06","cited_by_count":15,"area":null},{"id":"2111.01635","title":"Characterizing and Understanding the Generalization Error of Transfer Learning with Gibbs Algorithm","created":"2021-11-02","cited_by_count":14,"area":null},{"id":"2305.19674","title":"Online-to-PAC Conversions: Generalization Bounds via Regret Analysis","created":"2023-05-31","cited_by_count":14,"area":null},{"id":"2402.09327","title":"Information Complexity of Stochastic Convex Optimization: Applications to Generalization and Memorization","created":"2024-02-14","cited_by_count":14,"area":null},{"id":"2211.06617","title":"Empirical Risk Minimization with Relative Entropy Regularization","created":"2022-11-12","cited_by_count":13,"area":null},{"id":"2102.02016","title":"Information-Theoretic Bounds on the Moments of the Generalization Error of Learning Algorithms","created":"2021-02-03","cited_by_count":12,"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":"2202.12150","title":"Tighter Expected Generalization Error Bounds via Convexity of Information Measures","created":"2022-02-24","cited_by_count":11,"area":null},{"id":"2204.03230","title":"What You See is What You Get: Principled Deep Learning via Distributional Generalization","created":"2022-04-07","cited_by_count":11,"area":null},{"id":"2211.10691","title":"Two Facets of SDE Under an Information-Theoretic Lens: Generalization of SGD via Training Trajectories and via Terminal States","created":"2022-11-19","cited_by_count":11,"area":null},{"id":"2105.04180","title":"Rate-Distortion Analysis of Minimum Excess Risk in Bayesian Learning","created":"2021-05-10","cited_by_count":10,"area":null},{"id":"2203.00977","title":"Chained Generalisation Bounds","created":"2022-03-02","cited_by_count":10,"area":null},{"id":"2306.12380","title":"On the Validation of Gibbs Algorithms: Training Datasets, Test Datasets and their Aggregation","created":"2023-06-21","cited_by_count":10,"area":null},{"id":"2404.03176","title":"Information-Theoretic Generalization Bounds for Deep Neural Networks","created":"2024-04-04","cited_by_count":10,"area":null},{"id":"2201.08704","title":"Adaptive Data Analysis with Correlated Observations","created":"2022-01-21","cited_by_count":9,"area":null},{"id":"2209.02525","title":"Generalisation under gradient descent via deterministic PAC-Bayes","created":"2022-09-06","cited_by_count":9,"area":null},{"id":"2406.12600","title":"Generalization bounds for mixing processes via delayed online-to-PAC conversions","created":"2024-06-18","cited_by_count":9,"area":null},{"id":"2410.02247","title":"Theoretical Insights into Fine-Tuning Attention Mechanism: Generalization and Optimization","created":"2024-10-03","cited_by_count":9,"area":null},{"id":"2202.02423","title":"Improved Information Theoretic Generalization Bounds for Distributed and Federated Learning","created":"2022-02-04","cited_by_count":8,"area":null},{"id":"2202.04385","title":"Empirical Risk Minimization with Relative Entropy Regularization: Optimality and Sensitivity Analysis","created":"2022-02-09","cited_by_count":8,"area":null},{"id":"2202.09036","title":"Adaptive Experimentation in the Presence of Exogenous Nonstationary Variation","created":"2022-02-18","cited_by_count":8,"area":null},{"id":"2302.11709","title":"Bayes meets Bernstein at the Meta Level: an Analysis of Fast Rates in Meta-Learning with PAC-Bayes","created":"2023-02-23","cited_by_count":8,"area":null},{"id":"2402.01089","title":"No Free Prune: Information-Theoretic Barriers to Pruning at Initialization","created":"2024-02-02","cited_by_count":8,"area":null},{"id":"2206.11042","title":"f-divergences and their applications in lossy compression and bounding generalization error","created":"2022-06-21","cited_by_count":7,"area":null},{"id":"2206.13257","title":"Finite Littlestone Dimension Implies Finite Information Complexity","created":"2022-06-27","cited_by_count":7,"area":null},{"id":"2304.02064","title":"Algorithm-Dependent Bounds for Representation Learning of Multi-Source Domain Adaptation","created":"2023-04-04","cited_by_count":7,"area":null},{"id":"2312.12236","title":"Generalization Analysis of Machine Learning Algorithms via the Worst-Case Data-Generating Probability Measure","created":"2023-12-19","cited_by_count":7,"area":null},{"id":"2405.01304","title":"Misclassification bounds for PAC-Bayesian sparse deep learning","created":"2024-05-02","cited_by_count":7,"area":null},{"id":"2203.00246","title":"An Information-Theoretic Framework for Supervised Learning","created":"2022-03-01","cited_by_count":6,"area":null},{"id":"2210.00483","title":"Learning Algorithm Generalization Error Bounds via Auxiliary Distributions","created":"2022-10-02","cited_by_count":6,"area":null},{"id":"2306.00169","title":"Inconsistency, Instability, and Generalization Gap of Deep Neural Network Training","created":"2023-05-31","cited_by_count":6,"area":null},{"id":"2402.00501","title":"Equivalence of the Empirical Risk Minimization to Regularization on the Family of f-Divergences","created":"2024-02-01","cited_by_count":6,"area":null},{"id":"2410.02833","title":"Asymmetry of the Relative Entropy in the Regularization of Empirical Risk Minimization","created":"2024-10-02","cited_by_count":6,"area":null},{"id":"2506.01855","title":"Trade-offs in Data Memorization via Strong Data Processing Inequalities","created":"2025-06-02","cited_by_count":6,"area":null},{"id":"2202.07537","title":"Information-Theoretic Analysis of Minimax Excess Risk","created":"2022-02-15","cited_by_count":5,"area":null},{"id":"2210.08188","title":"How Does Pseudo-Labeling Affect the Generalization Error of the Semi-Supervised Gibbs Algorithm?","created":"2022-10-15","cited_by_count":5,"area":null},{"id":"2302.07263","title":"Interpolation Learning With Minimum Description Length","created":"2023-02-14","cited_by_count":5,"area":null},{"id":"2304.12579","title":"Learning Trajectories are Generalization Indicators","created":"2023-04-25","cited_by_count":5,"area":null},{"id":"2306.07123","title":"Analysis of the Relative Entropy Asymmetry in the Regularization of Empirical Risk Minimization","created":"2023-06-12","cited_by_count":5,"area":null},{"id":"2411.12030","title":"The Method of Gaps: Exact Expressions for the Generalization Error of Supervised Learning Algorithms","created":"2024-11-18","cited_by_count":5,"area":null},{"id":"2206.07199","title":"Benefits of Additive Noise in Composing Classes with Bounded Capacity","created":"2022-06-14","cited_by_count":4,"area":null},{"id":"2409.19431","title":"Generalization and Robustness of the Tilted Empirical Risk","created":"2024-09-28","cited_by_count":4,"area":null},{"id":"2410.22887","title":"Generalization Bounds via Conditional $f$-Information","created":"2024-10-30","cited_by_count":4,"area":null},{"id":"2107.13656","title":"Characterizing the Generalization Error of Gibbs Algorithm with Symmetrized KL information","created":"2021-07-28","cited_by_count":3,"area":null},{"id":"2210.09617","title":"Protecting Split Learning by Potential Energy Loss","created":"2022-10-18","cited_by_count":3,"area":null},{"id":"2406.09745","title":"How Does Distribution Matching Help Domain Generalization: An Information-theoretic Analysis","created":"2024-06-14","cited_by_count":3,"area":null},{"id":"2406.11569","title":"Pre-Training and Personalized Fine-Tuning via Over-the-Air Federated Meta-Learning: Convergence-Generalization Trade-Offs","created":"2024-06-17","cited_by_count":3,"area":null},{"id":"2502.17024","title":"Towards Auto-Regressive Next-Token Prediction: In-Context Learning Emerges from Generalization","created":"2025-02-24","cited_by_count":3,"area":null},{"id":"2212.14681","title":"An Entropy-Based Model for Hierarchical Learning","created":"2022-12-30","cited_by_count":2,"area":null},{"id":"2304.14332","title":"On the Generalization Error of Meta Learning for the Gibbs Algorithm","created":"2023-04-27","cited_by_count":2,"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":"2503.04091","title":"Generalization in Federated Learning: A Conditional Mutual Information Framework","created":"2025-03-06","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":"2507.12043","title":"Information-Theoretic Generalization Bounds of Replay-based Continual Learning","created":"2025-07-16","cited_by_count":2,"area":null},{"id":"2510.08095","title":"Beyond Real Data: Synthetic Data through the Lens of Regularization","created":"2025-10-09","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":"2106.10262","title":"A Probabilistic Representation of DNNs: Bridging Mutual Information and Generalization","created":"2021-06-18","cited_by_count":1,"area":null},{"id":"2304.13493","title":"Towards clinical AI fairness: A translational perspective","created":"2023-04-26","cited_by_count":1,"area":null},{"id":"2309.05077","title":"Generalization error bounds for iterative learning algorithms with bounded updates","created":"2023-09-10","cited_by_count":1,"area":null},{"id":"2310.07497","title":"Energy-Efficient and Real-Time Sensing for Federated Continual Learning via Sample-Driven Control","created":"2023-10-11","cited_by_count":1,"area":null},{"id":"2311.03955","title":"Elastic Information Bottleneck","created":"2023-11-07","cited_by_count":1,"area":null},{"id":"2508.03314","title":"A Dual Optimization View to Empirical Risk Minimization with f-Divergence Regularization","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2509.15932","title":"The Alignment Bottleneck","created":"2025-09-19","cited_by_count":1,"area":null},{"id":"2602.03690","title":"LLM-Inspired Pretrain-Then-Finetune for Small-Data, Large-Scale Optimization","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2602.09127","title":"Epistemic Throughput: Fundamental Limits of Attention-Constrained Inference","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2606.13767","title":"Beyond LoRA: Is Sparsity-Induced Adaptation Better?","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2608.13514","title":"Bagging Robustly Learns VC Classes with Linear Sample Complexity","created":"2026-08-13","cited_by_count":1,"area":null},{"id":"2305.18423","title":"On the Role of Noise in the Sample Complexity of Learning Recurrent Neural Networks: Exponential Gaps for Long Sequences","created":"2023-05-28","cited_by_count":0,"area":null},{"id":"2601.13191","title":"Empirical Risk Minimization with $f$-Divergence Regularization","created":"2026-01-19","cited_by_count":0,"area":null}],"next_cursor":null}