SGD as Free Energy Minimization: A Thermodynamic View on Neural Network Training

Documenti analoghi

• Can Stationary Distributions of Scale-Invariant Neural Networks Be Described by the Thermodynamics of an Ideal Gas?
  di: Sadrtdinov, Ildus, et al.
  Pubblicazione: (2025)
• To Stay or Not to Stay in the Pre-train Basin: Insights on Ensembling in Transfer Learning
  di: Sadrtdinov, Ildus, et al.
  Pubblicazione: (2023)
• Where Do Large Learning Rates Lead Us?
  di: Sadrtdinov, Ildus, et al.
  Pubblicazione: (2024)
• Why Gaussian Diffusion Models Fail on Discrete Data and How to Prevent It?
  di: Shabalin, Alexander, et al.
  Pubblicazione: (2026)
• SDE Matching: Scalable and Simulation-Free Training of Latent Stochastic Differential Equations
  di: Bartosh, Grigory, et al.
  Pubblicazione: (2025)