{"total":86,"rows":[{"id":"2102.00931","title":"Information-Theoretic Generalization Bounds for Stochastic Gradient Descent","created":"2021-02-01","cited_by_count":84,"area":null},{"id":"2505.24832","title":"How much do language models memorize?","created":"2025-05-30","cited_by_count":61,"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":"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":"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":"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":"2302.13091","title":"Explaining Generalization Power of a DNN Using Interactive Concepts","created":"2023-02-25","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":"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":"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":"2206.03299","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":"2211.06617","title":"Empirical Risk Minimization with Relative Entropy Regularization","created":"2022-11-12","cited_by_count":13,"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":"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":"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":"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":"2201.09209","title":"Weight Expansion: A New Perspective on Dropout and Generalization","created":"2022-01-23","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":"2210.06143","title":"On the Importance of Gradient Norm in PAC-Bayesian Bounds","created":"2022-10-12","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":"2106.06153","title":"Towards Understanding Generalization via Decomposing Excess Risk Dynamics","created":"2021-06-11","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":"2304.12579","title":"Learning Trajectories are Generalization Indicators","created":"2023-04-25","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":"2206.07199","title":"Benefits of Additive Noise in Composing Classes with Bounded Capacity","created":"2022-06-14","cited_by_count":4,"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":"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":"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":"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":"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":"2502.10162","title":"Revisiting Generalization Power of a DNN in Terms of Symbolic Interactions","created":"2025-02-14","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":"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":"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":"2309.05077","title":"Generalization error bounds for iterative learning algorithms with bounded updates","created":"2023-09-10","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":"2506.20094","title":"MEL: Multi-level Ensemble Learning for Resource-Constrained Environments","created":"2025-06-25","cited_by_count":1,"area":null},{"id":"2110.13750","title":"Optimizing Information-theoretical Generalization Bounds via Anisotropic Noise in SGLD","created":"2021-10-26","cited_by_count":0,"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":"2406.04567","title":"Error Bounds of Supervised Classification from Information-Theoretic Perspective","created":"2024-06-07","cited_by_count":0,"area":null},{"id":"2502.12353","title":"Stability-based Generalization Bounds for Variational Inference","created":"2025-02-17","cited_by_count":0,"area":null},{"id":"2510.10902","title":"Auditing Information Disclosure During Large-Scale Gradient-Based Training via Gradient Uniqueness","created":"2025-10-13","cited_by_count":0,"area":null},{"id":"2510.15422","title":"Information Theory in Open-world Machine Learning Foundations, Frameworks, and Future Direction","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2602.07999","title":"Tighter Information-Theoretic Generalization Bounds via a Novel Class of Change of Measure Inequalities","created":"2026-02-08","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":"2605.12190","title":"Information-Theoretic Generalization Bounds for Sequential Decision Making","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.15340","title":"Bounded-Rationality, Hedging, and Generalization","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2608.11690","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","created":"2026-08-12","cited_by_count":0,"area":null}],"next_cursor":null}