The sharp, the flat and the shallow: Can weakly interacting agents learn to escape bad minima?
arXiv:1905.04121
Abstract
An open problem in machine learning is whether flat minima generalize better and how to compute such minima efficiently. This is a very challenging problem. As a first step towards understanding this question we formalize it as an optimization problem with weakly interacting agents. We review appropriate background material from the theory of stochastic processes and provide insights that are relevant to practitioners. We propose an algorithmic framework for an extended stochastic gradient Langevin dynamics and illustrate its potential. The paper is written as a tutorial, and presents an alternative use of multi-agent learning. Our primary focus is on the design of algorithms for machine learning applications; however the underlying mathematical framework is suitable for the understanding of large scale systems of agent based models that are popular in the social sciences, economics and finance.
References in corpus (10)
- On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima
- Three Factors Influencing Minima in SGD
- A consensus-based model for global optimization and its mean-field limit
- Ensemble Kalman Inversion: A Derivative-Free Technique For Machine Learning Tasks
- Entropy-SGD: Biasing Gradient Descent Into Wide Valleys
- Mean-field theory of two-layers neural networks: dimension-free bounds and kernel limit
- On Graduated Optimization for Stochastic Non-Convex Problems
- Mean Field Limits for Interacting Diffusions in a Two-Scale Potential
- Stochastic Particle Gradient Descent for Infinite Ensembles
- Predict Globally, Correct Locally: Parallel-in-Time Optimal Control of Neural Networks