An Information-Theoretic Framework for Out-of-Distribution Generalization with Applications to Stochastic Gradient Langevin Dynamics

Documenti analoghi

• A PAC-Bayesian Analysis of Channel-Induced Degradation in Edge Inference
  di: He, Yangshuo, et al.
  Pubblicazione: (2026)
• Improved Information Theoretic Generalization Bounds for Distributed and Federated Learning
  di: Barnes, L. P., et al.
  Pubblicazione: (2022)
• Robustness in Wireless Distributed Learning: An Information-Theoretic Analysis
  di: He, Yangshuo, et al.
  Pubblicazione: (2024)
• InfoDPCCA: Information-Theoretic Dynamic Probabilistic Canonical Correlation Analysis
  di: Tang, Shiqin, et al.
  Pubblicazione: (2025)
• Characterizing Dependence of Samples along the Langevin Dynamics and Algorithms via Contraction of $Φ$-Mutual Information
  di: Liang, Jiaming, et al.
  Pubblicazione: (2024)