Two Facets of SDE Under an Information-Theoretic Lens: Generalization of SGD via Training Trajectories and via Terminal States

19 November 2022

Papers citing "Two Facets of SDE Under an Information-Theoretic Lens: Generalization of SGD via Training Trajectories and via Terminal States"

14 / 14 papers shown

Title
Towards Auto-Regressive Next-Token Prediction: In-Context Learning Emerges from Generalization Zixuan Gong Xiaolin Hu Huayi Tang Yong Liu 33 0 0 24 Feb 2025
Generalization Bounds via Conditional $f$ -Information Ziqiao Wang Yongyi Mao FedML 40 1 0 30 Oct 2024
Theoretical Insights into Fine-Tuning Attention Mechanism: Generalization and Optimization Xinhao Yao Hongjin Qian Xiaolin Hu Gengze Xu Wei Liu Jian Luan B. Wang Y. Liu 48 0 0 03 Oct 2024
Enhancing Domain Adaptation through Prompt Gradient Alignment Hoang Phan Lam C. Tran Quyen Tran Trung Le 52 0 0 13 Jun 2024
Enhancing In-Context Learning Performance with just SVD-Based Weight Pruning: A Theoretical Perspective Xinhao Yao Xiaolin Hu Shenzhi Yang Yong Liu 39 2 0 06 Jun 2024
Sample-Conditioned Hypothesis Stability Sharpens Information-Theoretic Generalization Bounds Ziqiao Wang Yongyi Mao 22 5 0 31 Oct 2023
Tighter Information-Theoretic Generalization Bounds from Supersamples Ziqiao Wang Yongyi Mao 19 17 0 05 Feb 2023
Information-Theoretic Analysis of Unsupervised Domain Adaptation Ziqiao Wang Yongyi Mao 38 11 0 03 Oct 2022
Understanding Gradient Descent on Edge of Stability in Deep Learning Sanjeev Arora Zhiyuan Li A. Panigrahi MLT 75 89 0 19 May 2022
On the Generalization of Models Trained with SGD: Information-Theoretic Bounds and Implications Ziqiao Wang Yongyi Mao FedML MLT 32 22 0 07 Oct 2021
Stochastic Training is Not Necessary for Generalization Jonas Geiping Micah Goldblum Phillip E. Pope Michael Moeller Tom Goldstein 81 72 0 29 Sep 2021
Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization Stanislaw Jastrzebski Devansh Arpit Oliver Åstrand Giancarlo Kerg Huan Wang Caiming Xiong R. Socher Kyunghyun Cho Krzysztof J. Geras AI4CE 179 65 0 28 Dec 2020
Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates Jeffrey Negrea Mahdi Haghifam Gintare Karolina Dziugaite Ashish Khisti Daniel M. Roy FedML 105 146 0 06 Nov 2019
Pac-Bayesian Supervised Classification: The Thermodynamics of Statistical Learning O. Catoni 139 453 0 03 Dec 2007