MLDIS-NNLGFeb 12, 2024

Stochastic Gradient Flow Dynamics of Test Risk and its Exact Solution for Weak Features

arXiv:2402.07626v23 citationsh-index: 2ICML
Originality Incremental advance
AI Analysis

This work provides incremental theoretical insights into stochastic gradient dynamics for researchers in machine learning theory, specifically analyzing test risk in a controlled setting.

The paper tackles the test risk dynamics of stochastic gradient flow in learning theory, deriving a general formula for the difference between pure and stochastic gradient flows in the small learning rate regime and applying it to a weak features model to compute explicit corrections, with analytical results showing good agreement with simulations.

We investigate the test risk of continuous-time stochastic gradient flow dynamics in learning theory. Using a path integral formulation we provide, in the regime of a small learning rate, a general formula for computing the difference between test risk curves of pure gradient and stochastic gradient flows. We apply the general theory to a simple model of weak features, which displays the double descent phenomenon, and explicitly compute the corrections brought about by the added stochastic term in the dynamics, as a function of time and model parameters. The analytical results are compared to simulations of discrete-time stochastic gradient descent and show good agreement.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes