{"total":277,"rows":[{"id":"2110.11216","title":"User-friendly introduction to PAC-Bayes bounds","created":"2021-10-21","cited_by_count":239,"area":null},{"id":"2305.18887","title":"How Does Information Bottleneck Help Deep Learning?","created":"2023-05-30","cited_by_count":93,"area":null},{"id":"2402.16842","title":"Asymmetry in Low-Rank Adapters of Foundation Models","created":"2024-02-26","cited_by_count":86,"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":"2205.10053","title":"What's Behind the Mask: Understanding Masked Graph Modeling for Graph Autoencoders","created":"2022-05-20","cited_by_count":82,"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":"2303.12921","title":"Stability is Stable: Connections between Replicability, Privacy, and Adaptive Generalization","created":"2023-03-22","cited_by_count":42,"area":null},{"id":"2112.13547","title":"PRIME: A few primitives can boost robustness to common corruptions","created":"2021-12-27","cited_by_count":40,"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":"2604.21691","title":"There Will Be a Scientific Theory of Deep Learning","created":"2026-04-23","cited_by_count":29,"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":"2202.08311","title":"Single Trajectory Nonparametric Learning of Nonlinear Dynamics","created":"2022-02-16","cited_by_count":26,"area":null},{"id":"2206.07082","title":"Stability and Generalization of Stochastic Optimization with Nonconvex and Nonsmooth Problems","created":"2022-06-14","cited_by_count":25,"area":null},{"id":"2303.00633","title":"An Information-Theoretic Perspective on Variance-Invariance-Covariance Regularization","created":"2023-03-01","cited_by_count":25,"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":"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":"2403.02187","title":"Mutual Information Estimation via Normalizing Flows","created":"2024-03-04","cited_by_count":22,"area":null},{"id":"2405.01964","title":"Position: Understanding LLMs Requires More Than Statistical Generalization","created":"2024-05-03","cited_by_count":21,"area":null},{"id":"2105.00303","title":"RATT: Leveraging Unlabeled Data to Guarantee Generalization","created":"2021-05-01","cited_by_count":20,"area":null},{"id":"2202.13361","title":"Benign Underfitting of Stochastic Gradient Descent","created":"2022-02-27","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":"2305.08013","title":"Information Bottleneck Analysis of Deep Neural Networks via Lossy Compression","created":"2023-05-13","cited_by_count":19,"area":null},{"id":"2309.13658","title":"Fantastic Generalization Measures are Nowhere to be Found","created":"2023-09-24","cited_by_count":19,"area":null},{"id":"2107.01131","title":"Tight Mutual Information Estimation With Contrastive Fenchel-Legendre Optimization","created":"2021-07-02","cited_by_count":18,"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":"2208.04284","title":"On Rademacher Complexity-based Generalization Bounds for Deep Learning","created":"2022-08-08","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":"2207.10081","title":"What Do We Maximize in Self-Supervised Learning?","created":"2022-07-20","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":"2301.11885","title":"Algorithmic Stability of Heavy-Tailed SGD with General Loss Functions","created":"2023-01-27","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":"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":"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":"2310.18428","title":"The Bayesian Stability Zoo","created":"2023-10-27","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":"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":"2304.03398","title":"Quantum Conformal Prediction for Reliable Uncertainty Quantification in Quantum Machine Learning","created":"2023-04-06","cited_by_count":11,"area":null},{"id":"2312.00194","title":"Robust Concept Erasure via Kernelized Rate-Distortion Maximization","created":"2023-11-30","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":"2105.04180","title":"Rate-Distortion Analysis of Minimum Excess Risk in Bayesian Learning","created":"2021-05-10","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":"2306.02939","title":"Improved Stability and Generalization Guarantees of the Decentralized SGD Algorithm","created":"2023-06-05","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":"2405.15709","title":"Information-theoretic Generalization Analysis for Expected Calibration Error","created":"2024-05-24","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":"2201.11059","title":"Generalization Error Bounds on Deep Learning with Markov Datasets","created":"2021-12-23","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":"2401.01148","title":"PAC-Bayes-Chernoff bounds for unbounded losses","created":"2024-01-02","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":"2410.02247","title":"Theoretical Insights into Fine-Tuning Attention Mechanism: Generalization and Optimization","created":"2024-10-03","cited_by_count":9,"area":null},{"id":"2510.12066","title":"AI Agents as Universal Task Solvers","created":"2025-10-14","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":"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":"2207.00581","title":"On Leave-One-Out Conditional Mutual Information For Generalization","created":"2022-07-01","cited_by_count":8,"area":null},{"id":"2211.08597","title":"SketchySGD: Reliable Stochastic Optimization via Randomized Curvature Estimates","created":"2022-11-16","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":"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":"2111.03505","title":"Visualizing the Emergence of Intermediate Visual Patterns in DNNs","created":"2021-11-05","cited_by_count":7,"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":"2207.06687","title":"Breaking Correlation Shift via Conditional Invariant Regularizer","created":"2022-07-14","cited_by_count":7,"area":null},{"id":"2208.01134","title":"Improving the Trainability of Deep Neural Networks through Layerwise Batch-Entropy Regularization","created":"2022-08-01","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":"2305.04712","title":"High-Dimensional Smoothed Entropy Estimation via Dimensionality Reduction","created":"2023-05-08","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":"2410.06851","title":"Understanding Model Ensemble in Transferable Adversarial Attack","created":"2024-10-09","cited_by_count":7,"area":null}],"next_cursor":"100"}