Entropy-SGD

swMATH41231MaRDI QIDQ1354032FDOQ1354032

Author name not available (Why is that?)

Source code repository: https://github.com/ucla-vision/entropy-sgd

Described by source

• Entropy-SGD: biasing gradient descent into wide valleys

Cited In (20)

• A spin glass model for the loss surfaces of generative adversarial networks
• Comparing dynamics: deep neural networks versus glassy systems
• Selection dynamics for deep neural networks
• Forward stability of ResNet and its variants
• Stochastic backward Euler: an implicit gradient descent algorithm for \(k\)-means clustering
• Title not available (Why is that?)
• Ensemble Kalman inversion: a derivative-free technique for machine learning tasks
• Deep relaxation: partial differential equations for optimizing deep neural networks
• Building a telescope to look into high-dimensional image spaces
• Chaos and complexity from quantum neural network. A study with diffusion metric in machine learning
• Entropic gradient descent algorithms and wide flat minima*
• Bias of homotopic gradient descent for the hinge loss
• Dynamics of stochastic gradient descent for two-layer neural networks in the teacher–student setup*
• On Bayesian posterior mean estimators in imaging sciences and Hamilton-Jacobi partial differential equations
• Interpretable machine learning: fundamental principles and 10 grand challenges
• The committee machine: computational to statistical gaps in learning a two-layers neural network
• Global Minima of Overparameterized Neural Networks
• Wasserstein-Based Projections with Applications to Inverse Problems
• Optimization for deep learning: an overview
• Run-and-inspect method for nonconvex optimization and global optimality bounds for R-local minimizers

This page was built for software: Entropy-SGD