{"total":111,"rows":[{"id":"2110.11216","title":"User-friendly introduction to PAC-Bayes bounds","created":"2021-10-21","cited_by_count":239,"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":"2210.06422","title":"A New Family of Generalization Bounds Using Samplewise Evaluated CMI","created":"2022-10-12","cited_by_count":28,"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":"2203.02474","title":"Rate-Distortion Theoretic Generalization Bounds for Stochastic Learning Algorithms","created":"2022-03-04","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":"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":"2206.14800","title":"Understanding Generalization via Leave-One-Out Conditional Mutual Information","created":"2022-06-29","cited_by_count":16,"area":null},{"id":"2102.02976","title":"Generalization Bounds for Noisy Iterative Algorithms Using Properties of Additive Noise Channels","created":"2021-02-05","cited_by_count":15,"area":null},{"id":"2210.00706","title":"Information-Theoretic Analysis of Unsupervised Domain Adaptation","created":"2022-10-03","cited_by_count":15,"area":null},{"id":"2105.01747","title":"Information Complexity and Generalization Bounds","created":"2021-05-04","cited_by_count":14,"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":"2206.02604","title":"Rate-Distortion Theoretic Bounds on Generalization Error for Distributed Learning","created":"2022-06-06","cited_by_count":14,"area":null},{"id":"2206.03299","title":"Generalization Error Bounds for Deep Neural Networks Trained by SGD","created":"2022-06-07","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":"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":"2311.01046","title":"Time-Independent Information-Theoretic Generalization Bounds for SGLD","created":"2023-11-02","cited_by_count":12,"area":null},{"id":"2110.00926","title":"Information-Theoretic Characterization of the Generalization Error for Iterative Semi-Supervised Learning","created":"2021-10-03","cited_by_count":11,"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":"2207.05377","title":"On the Generalization for Transfer Learning: An Information-Theoretic Analysis","created":"2022-07-12","cited_by_count":11,"area":null},{"id":"2210.06511","title":"Evaluated CMI Bounds for Meta Learning: Tightness and Expressiveness","created":"2022-10-12","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":"2402.03254","title":"Minimum Description Length and Generalization Guarantees for Representation Learning","created":"2024-02-05","cited_by_count":11,"area":null},{"id":"2101.08390","title":"An Information-Theoretic Analysis of the Impact of Task Similarity on Meta-Learning","created":"2021-01-21","cited_by_count":10,"area":null},{"id":"2106.00252","title":"Information-Theoretic Analysis of Epistemic Uncertainty in Bayesian Meta-learning","created":"2021-06-01","cited_by_count":10,"area":null},{"id":"2203.00977","title":"Chained Generalisation Bounds","created":"2022-03-02","cited_by_count":10,"area":null},{"id":"2304.12216","title":"More Communication Does Not Result in Smaller Generalization Error in Federated Learning","created":"2023-04-24","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":"2208.03848","title":"Information bottleneck theory of high-dimensional regression: relevancy, efficiency and optimality","created":"2022-08-08","cited_by_count":9,"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":"2201.03064","title":"Stability Based Generalization Bounds for Exponential Family Langevin Dynamics","created":"2022-01-09","cited_by_count":8,"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":"2207.00581","title":"On Leave-One-Out Conditional Mutual Information For Generalization","created":"2022-07-01","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":"2210.04742","title":"Over-the-Air Split Machine Learning in Wireless MIMO Networks","created":"2022-10-07","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":"2402.13285","title":"Leveraging PAC-Bayes Theory and Gibbs Distributions for Generalization Bounds with Complexity Measures","created":"2024-02-19","cited_by_count":7,"area":null},{"id":"2202.03956","title":"From Generalisation Error to Transportation-cost Inequalities and Back","created":"2022-02-08","cited_by_count":6,"area":null},{"id":"2205.03131","title":"Fast Rate Generalization Error Bounds: Variations on a Theme","created":"2022-05-06","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":"2305.11042","title":"A unified framework for information-theoretic generalization bounds","created":"2023-05-18","cited_by_count":6,"area":null},{"id":"2310.20102","title":"Sample-Conditioned Hypothesis Stability Sharpens Information-Theoretic Generalization Bounds","created":"2023-10-31","cited_by_count":6,"area":null},{"id":"2407.09324","title":"Provable Privacy Advantages of Decentralized Federated Learning via Distributed Optimization","created":"2024-07-12","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":"2201.04545","title":"On generalization bounds for deep networks based on loss surface implicit regularization","created":"2022-01-12","cited_by_count":5,"area":null},{"id":"2202.07537","title":"Information-Theoretic Analysis of Minimax Excess Risk","created":"2022-02-15","cited_by_count":5,"area":null},{"id":"2205.13799","title":"Generalization Bounds for Gradient Methods via Discrete and Continuous Prior","created":"2022-05-27","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":"2303.14658","title":"Fast Rate Information-theoretic Bounds on Generalization Errors","created":"2023-03-26","cited_by_count":5,"area":null},{"id":"2304.14618","title":"Recognizable Information Bottleneck","created":"2023-04-28","cited_by_count":5,"area":null},{"id":"2310.10534","title":"Comparing Comparators in Generalization Bounds","created":"2023-10-16","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":"2502.04242","title":"A High-Dimensional Statistical Method for Optimizing Transfer Quantities in Multi-Source Transfer Learning","created":"2025-02-06","cited_by_count":5,"area":null},{"id":"2510.03313","title":"Scaling Laws Revisited: Modeling the Role of Data Quality in Language Model Pretraining","created":"2025-09-30","cited_by_count":5,"area":null},{"id":"2305.00876","title":"Exactly Tight Information-Theoretic Generalization Error Bound for the Quadratic Gaussian Problem","created":"2023-05-01","cited_by_count":4,"area":null},{"id":"2305.10540","title":"Generalization Bounds for Neural Belief Propagation Decoders","created":"2023-05-17","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":"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":"2205.06915","title":"Formal limitations of sample-wise information-theoretic generalization bounds","created":"2022-05-13","cited_by_count":3,"area":null},{"id":"2206.05454","title":"A General framework for PAC-Bayes Bounds for Meta-Learning","created":"2022-06-11","cited_by_count":3,"area":null},{"id":"2403.19895","title":"An Information-Theoretic Framework for Out-of-Distribution Generalization with Applications to Stochastic Gradient Langevin Dynamics","created":"2024-03-29","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":"2506.07861","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","created":"2025-06-09","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":"2301.11542","title":"Feasibility and Transferability of Transfer Learning: A Mathematical Framework","created":"2023-01-27","cited_by_count":2,"area":null},{"id":"2302.14518","title":"Generalization Error Bounds for Noisy, Iterative Algorithms via Maximal Leakage","created":"2023-02-28","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":"2305.12985","title":"Feasibility of Transfer Learning: A Mathematical Framework","created":"2023-05-22","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":"2401.02904","title":"Class-wise Generalization Error: an Information-Theoretic Analysis","created":"2024-01-05","cited_by_count":2,"area":null},{"id":"2407.08571","title":"Multi-Group Proportional Representation in Retrieval","created":"2024-07-11","cited_by_count":2,"area":null},{"id":"2502.01458","title":"The Capabilities and Limitations of Weak-to-Strong Generalization: Generalization and Calibration","created":"2025-02-03","cited_by_count":2,"area":null},{"id":"2502.07584","title":"Generalization Bounds for Markov Algorithms through Entropy Flow Computations","created":"2025-02-11","cited_by_count":2,"area":null},{"id":"2502.15540","title":"Generalization Guarantees for Representation Learning via Data-Dependent Gaussian Mixture Priors","created":"2025-02-21","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":"2506.21036","title":"An Information-Theoretic Analysis for Federated Learning under Concept Drift","created":"2025-06-26","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":"2601.01465","title":"Leveraging Flatness to Improve Information-Theoretic Generalization Bounds for SGD","created":"2026-01-04","cited_by_count":2,"area":null},{"id":"2602.00906","title":"Hallucination is a Consequence of Space-Optimality: A Rate-Distortion Theorem for Membership Testing","created":"2026-01-31","cited_by_count":2,"area":null},{"id":"2112.08439","title":"Generalization Bounds for Stochastic Gradient Langevin Dynamics: A Unified View via Information Leakage Analysis","created":"2021-12-14","cited_by_count":1,"area":null},{"id":"2202.06880","title":"Black-Box Generalization: Stability of Zeroth-Order Learning","created":"2022-02-14","cited_by_count":1,"area":null},{"id":"2504.18455","title":"Multiview Representation Learning via Distributed Joint Latent Space Structuring","created":"2025-04-25","cited_by_count":1,"area":null},{"id":"2505.11025","title":"Generalization Bounds for Quantum Learning via R\\'enyi Divergences","created":"2025-05-16","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":"2601.10779","title":"Unified Optimization of Source Weights and Transfer Quantities in Multi-Source Transfer Learning: An Asymptotic Framework","created":"2026-01-15","cited_by_count":1,"area":null},{"id":"2605.22940","title":"Human-Centered Learning Mechanics: A Dynamical Framework for Entropy-Regulated Representation Learning","created":"2026-05-21","cited_by_count":1,"area":null}],"next_cursor":"100"}