{"total":65,"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":"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":"2407.08039","title":"Knowledge Overshadowing Causes Amalgamated Hallucination in Large Language Models","created":"2024-07-10","cited_by_count":25,"area":null},{"id":"2106.04881","title":"Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms","created":"2021-06-09","cited_by_count":23,"area":null},{"id":"2302.02432","title":"Tighter Information-Theoretic Generalization Bounds from Supersamples","created":"2023-02-05","cited_by_count":22,"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":"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":"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":"2206.03299","title":"Generalization Error Bounds for Deep Neural Networks Trained by SGD","created":"2022-06-07","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":"2202.12150","title":"Tighter Expected Generalization Error Bounds via Convexity of Information Measures","created":"2022-02-24","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":"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":"2211.10929","title":"Towards Generalizable Graph Contrastive Learning: An Information Theory Perspective","created":"2022-11-20","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":"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":"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":"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":"2303.14658","title":"Fast Rate Information-theoretic Bounds on Generalization Errors","created":"2023-03-26","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":"2205.07050","title":"DECONET: an Unfolding Network for Analysis-based Compressed Sensing with Generalization Error Bounds","created":"2022-05-14","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":"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":"2511.08552","title":"FMMI: Flow Matching Mutual Information Estimation","created":"2025-11-11","cited_by_count":4,"area":"diffusion"},{"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":"2603.21541","title":"Sharper Generalization Bounds for Transformer","created":"2026-03-23","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":"2311.04561","title":"Information-Theoretic Generalization Bounds for Transductive Learning and its Applications","created":"2023-11-08","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":"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":"2211.00416","title":"Higher-order mutual information reveals synergistic sub-networks for multi-neuron importance","created":"2022-11-01","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},{"id":"2602.08894","title":"Discrete Bridges for Mutual Information Estimation","created":"2026-02-09","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":"2211.12685","title":"Mutual Information Learned Regressor: an Information-theoretic Viewpoint of Training Regression Systems","created":"2022-11-23","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":"2510.23448","title":"An Information-Theoretic Analysis of OOD Generalization in Meta-Reinforcement Learning","created":"2025-10-27","cited_by_count":0,"area":"deeprl"},{"id":"2601.13191","title":"Empirical Risk Minimization with $f$-Divergence Regularization","created":"2026-01-19","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":"2602.12605","title":"Block-Sample MAC-Bayes Generalization Bounds","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2602.14423","title":"The geometry of invariant learning: an information-theoretic analysis of data augmentation and generalization","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2604.10727","title":"Tail-Aware Information-Theoretic Bounds for LLM Alignment under Heavy-Tailed Rewards","created":"2026-04-12","cited_by_count":0,"area":"alignment"},{"id":"2605.25612","title":"Towards the Connection between Activation Sparsity and Flat Minima","created":"2026-05-25","cited_by_count":0,"area":null}],"next_cursor":null}