Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Ziqiao, Mao, Yongyi
Format:	Preprint
Published:	2022
Subjects:	Machine Learning Information Theory
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Generalization Bounds via Conditional $f$-Information
by: Wang, Ziqiao, et al.
Published: (2024)

Generalization in Federated Learning: A Conditional Mutual Information Framework
by: Wang, Ziqiao, et al.
Published: (2025)

Theoretically Grounded Framework for LLM Watermarking: A Distribution-Adaptive Approach
by: He, Haiyun, et al.
Published: (2024)

On the Hardness of Unsupervised Domain Adaptation: Optimal Learners and Information-Theoretic Perspective
by: Dong, Zhiyi, et al.
Published: (2025)

Distributional Information Embedding: A Framework for Multi-bit Watermarking
by: He, Haiyun, et al.
Published: (2025)

Tighter Information-Theoretic Generalization Bounds via a Novel Class of Change of Measure Inequalities
by: Liu, Yanxiao, et al.
Published: (2026)

On the Generalization for Transfer Learning: An Information-Theoretic Analysis
by: Wu, Xuetong, et al.
Published: (2022)

On the Generalization of Knowledge Distillation: An Information-Theoretic View
by: Li, Bingying, et al.
Published: (2026)

Machine Unlearning via Information Theoretic Regularization
by: Xu, Shizhou, et al.
Published: (2025)

Information-Theoretic Generalization Bounds for Deep Neural Networks
by: He, Haiyun, et al.
Published: (2024)

Improved Information Theoretic Generalization Bounds for Distributed and Federated Learning
by: Barnes, L. P., et al.
Published: (2022)

An Information-Theoretic Framework for Out-of-Distribution Generalization with Applications to Stochastic Gradient Langevin Dynamics
by: Liu, Wenliang, et al.
Published: (2024)

Cryptanalysis via Machine Learning Based Information Theoretic Metrics
by: Kim, Benjamin D., et al.
Published: (2025)

Information-Theoretic Generative Clustering of Documents
by: Du, Xin, et al.
Published: (2024)

Information-Theoretic Policy Pre-Training with Empowerment
by: Schneider, Moritz, et al.
Published: (2025)

Information-Theoretic Discrete Diffusion
by: Jeon, Moongyu, et al.
Published: (2025)

Information-Theoretic State Variable Selection for Reinforcement Learning
by: Westphal, Charles, et al.
Published: (2024)

Efficient Generalization via Multimodal Co-Training under Data Scarcity and Distribution Shift
by: Pan, Tianyu Bell, et al.
Published: (2025)

On $f$-Divergence Principled Domain Adaptation: An Improved Framework
by: Wang, Ziqiao, et al.
Published: (2024)

Rethinking KV Cache Eviction via a Unified Information-Theoretic Objective
by: Yang, Jiaming, et al.
Published: (2026)

Information-Theoretic Proofs for Diffusion Sampling
by: Reeves, Galen, et al.
Published: (2025)

Information Theoretic Perspective on Representation Learning
by: Pereg, Deborah, et al.
Published: (2026)

An Information Theoretic Perspective on Conformal Prediction
by: Correia, Alvaro H. C., et al.
Published: (2024)

An Information-Theoretic Analysis of Temporal GNNs
by: Farzaneh, Amirmohammad
Published: (2024)

An Information-Theoretic Analysis of In-Context Learning
by: Jeon, Hong Jun, et al.
Published: (2024)

Bounds on the Excess Minimum Risk via Generalized Information Divergence Measures
by: Omanwar, Ananya, et al.
Published: (2025)

Directed Information $γ$-covering: An Information-Theoretic Framework for Context Engineering
by: Huang, Hai
Published: (2025)

Information-Theoretic Framework for Understanding Modern Machine-Learning
by: Feder, Meir, et al.
Published: (2025)

Information Theoretic Learning for Diffusion Models with Warm Start
by: Shen, Yirong, et al.
Published: (2025)

Information-Theoretic Measures on Lattices for High-Order Interactions
by: Liu, Zhaolu, et al.
Published: (2024)

Unifying Information-Theoretic and Pair-Counting Clustering Similarity
by: Gates, Alexander J.
Published: (2025)

Information-Theoretic Limits of Quantum Learning via Data Compression
by: Angrisani, Armando, et al.
Published: (2021)

Neural Networks Learn Generic Multi-Index Models Near Information-Theoretic Limit
by: Zhang, Bohan, et al.
Published: (2025)

Information Theoretic Guarantees For Policy Alignment In Large Language Models
by: Mroueh, Youssef
Published: (2024)

A Theoretical Framework for Statistical Evaluability of Generative Models
by: Aiyer, Shashaank, et al.
Published: (2026)

Information-Theoretic Thresholds for the Alignments of Partially Correlated Graphs
by: Huang, Dong, et al.
Published: (2024)

Structure Learning via Mutual Information
by: Nixon, Jeremy
Published: (2024)

Forecastability as an Information-Theoretic Limit on Prediction
by: Catt, Peter Maurice
Published: (2026)

Laplace Sample Information: Data Informativeness Through a Bayesian Lens
by: Kaiser, Johannes, et al.
Published: (2025)

An Effective Information Theoretic Framework for Channel Pruning
by: Chen, Yihao, et al.
Published: (2024)