{"total":119,"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":"2210.01513","title":"The Dynamics of Sharpness-Aware Minimization: Bouncing Across Ravines and Drifting Towards Wide Minima","created":"2022-10-04","cited_by_count":51,"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":"2106.09683","title":"PAC-Bayes, MAC-Bayes and Conditional Mutual Information: Fast rate bounds that handle general VC classes","created":"2021-06-17","cited_by_count":31,"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":"2109.14509","title":"PAC-Bayes Information Bottleneck","created":"2021-09-29","cited_by_count":28,"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":"2303.10653","title":"Randomized Adversarial Training via Taylor Expansion","created":"2023-03-19","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":"2111.12876","title":"Time-independent Generalization Bounds for SGLD in Non-convex Settings","created":"2021-11-25","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":"2407.08039","title":"Knowledge Overshadowing Causes Amalgamated Hallucination in Large Language Models","created":"2024-07-10","cited_by_count":25,"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":"2204.12446","title":"Beyond Lipschitz: Sharp Generalization and Excess Risk Bounds for Full-Batch GD","created":"2022-04-26","cited_by_count":19,"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":"2302.04925","title":"Information Theoretic Lower Bounds for Information Theoretic Upper Bounds","created":"2023-02-09","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":"2302.02766","title":"Generalization Bounds with Data-dependent Fractal Dimensions","created":"2023-02-06","cited_by_count":15,"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":"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":"2402.08508","title":"A PAC-Bayesian Link Between Generalisation and Flat Minima","created":"2024-02-13","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":"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":"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":"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":"2107.06665","title":"Disparity Between Batches as a Signal for Early Stopping","created":"2021-07-14","cited_by_count":9,"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":"2209.02525","title":"Generalisation under gradient descent via deterministic PAC-Bayes","created":"2022-09-06","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":"2404.17442","title":"Uniform Generalization Bounds on Data-Dependent Hypothesis Sets via PAC-Bayesian Theory on Random Sets","created":"2024-04-26","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":"2207.00581","title":"On Leave-One-Out Conditional Mutual Information For Generalization","created":"2022-07-01","cited_by_count":8,"area":null},{"id":"2305.01034","title":"Model-agnostic Measure of Generalization Difficulty","created":"2023-05-01","cited_by_count":7,"area":null},{"id":"2105.14416","title":"Communication efficient privacy-preserving distributed optimization using adaptive differential quantization","created":"2021-05-30","cited_by_count":6,"area":null},{"id":"2201.09209","title":"Weight Expansion: A New Perspective on Dropout and Generalization","created":"2022-01-23","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":"2310.20102","title":"Sample-Conditioned Hypothesis Stability Sharpens Information-Theoretic Generalization Bounds","created":"2023-10-31","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":"2211.03970","title":"On the Algorithmic Stability and Generalization of Adaptive Optimization Methods","created":"2022-11-08","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":"2304.12579","title":"Learning Trajectories are Generalization Indicators","created":"2023-04-25","cited_by_count":5,"area":null},{"id":"2304.13593","title":"Thompson Sampling Regret Bounds for Contextual Bandits with sub-Gaussian rewards","created":"2023-04-26","cited_by_count":5,"area":null},{"id":"2304.14618","title":"Recognizable Information Bottleneck","created":"2023-04-28","cited_by_count":5,"area":null},{"id":"2305.01143","title":"Understanding the Generalization Ability of Deep Learning Algorithms: A Kernelized Renyi's Entropy Perspective","created":"2023-05-02","cited_by_count":5,"area":null},{"id":"2305.02247","title":"Select without Fear: Almost All Mini-Batch Schedules Generalize Optimally","created":"2023-05-03","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":"2406.15941","title":"Towards Exact Computation of Inductive Bias","created":"2024-06-22","cited_by_count":5,"area":null},{"id":"2506.03849","title":"Algorithm- and Data-Dependent Generalization Bounds for Diffusion Models","created":"2025-06-04","cited_by_count":5,"area":"diffusion"},{"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":"2406.03768","title":"Enhancing In-Context Learning Performance with just SVD-Based Weight Pruning: A Theoretical Perspective","created":"2024-06-06","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":"2410.22887","title":"Generalization Bounds via Conditional $f$-Information","created":"2024-10-30","cited_by_count":4,"area":null},{"id":"2511.08552","title":"FMMI: Flow Matching Mutual Information Estimation","created":"2025-11-11","cited_by_count":4,"area":"diffusion"},{"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":"2210.09617","title":"Protecting Split Learning by Potential Energy Loss","created":"2022-10-18","cited_by_count":3,"area":null},{"id":"2311.00274","title":"Generalization Bounds for Label Noise Stochastic Gradient Descent","created":"2023-11-01","cited_by_count":3,"area":null},{"id":"2401.08909","title":"Leveraging Gradients for Unsupervised Accuracy Estimation under Distribution Shift","created":"2024-01-17","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":"2506.00849","title":"Generalization in VAE and Diffusion Models: A Unified Information-Theoretic Analysis","created":"2025-06-01","cited_by_count":3,"area":"diffusion"},{"id":"2510.08413","title":"Prompts Generalize with Low Data: Non-vacuous Generalization Bounds for Optimizing Prompts with More Informative Priors","created":"2025-10-09","cited_by_count":3,"area":null},{"id":"2110.11804","title":"Probabilistic fine-tuning of pruning masks and PAC-Bayes self-bounded learning","created":"2021-10-22","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":"2311.04561","title":"Information-Theoretic Generalization Bounds for Transductive Learning and its Applications","created":"2023-11-08","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":"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":"2601.01465","title":"Leveraging Flatness to Improve Information-Theoretic Generalization Bounds for SGD","created":"2026-01-04","cited_by_count":2,"area":null},{"id":"2103.00075","title":"Noisy Truncated SGD: Optimization and Generalization","created":"2021-02-26","cited_by_count":1,"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":"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":"2202.01958","title":"Demystify Optimization and Generalization of Over-parameterized PAC-Bayesian Learning","created":"2022-02-04","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":"2208.14092","title":"Super-model ecosystem: A domain-adaptation perspective","created":"2022-08-30","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":"2406.05628","title":"Domain Generalization Guided by Large-Scale Pre-Trained Priors","created":"2024-06-09","cited_by_count":1,"area":null},{"id":"2412.18539","title":"Convergence of Statistical Estimators via Mutual Information Bounds","created":"2024-12-24","cited_by_count":1,"area":null},{"id":"2504.02957","title":"Randomized Pairwise Learning with Adaptive Sampling: A PAC-Bayes Analysis","created":"2025-04-03","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":"2505.15303","title":"Laplace Sample Information: Data Informativeness Through a Bayesian Lens","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2506.04053","title":"Curse of Slicing: Why Sliced Mutual Information is a Deceptive Measure of Statistical Dependence","created":"2025-06-04","cited_by_count":1,"area":null}],"next_cursor":"100"}