LGOCApr 23, 2024

Regularized Gauss-Newton for Optimizing Overparameterized Neural Networks

arXiv:2404.14875v14 citationsh-index: 4Has Code
Originality Incremental advance
AI Analysis

This work addresses optimization challenges in deep learning for researchers, but it is incremental as it builds on existing Gauss-Newton methods with specific regularization.

The authors tackled the problem of optimizing overparameterized two-layer neural networks by introducing a regularized Gauss-Newton method with generalized self-concordant functions, resulting in improved generalization as shown in numerical experiments.

The generalized Gauss-Newton (GGN) optimization method incorporates curvature estimates into its solution steps, and provides a good approximation to the Newton method for large-scale optimization problems. GGN has been found particularly interesting for practical training of deep neural networks, not only for its impressive convergence speed, but also for its close relation with neural tangent kernel regression, which is central to recent studies that aim to understand the optimization and generalization properties of neural networks. This work studies a GGN method for optimizing a two-layer neural network with explicit regularization. In particular, we consider a class of generalized self-concordant (GSC) functions that provide smooth approximations to commonly-used penalty terms in the objective function of the optimization problem. This approach provides an adaptive learning rate selection technique that requires little to no tuning for optimal performance. We study the convergence of the two-layer neural network, considered to be overparameterized, in the optimization loop of the resulting GGN method for a given scaling of the network parameters. Our numerical experiments highlight specific aspects of GSC regularization that help to improve generalization of the optimized neural network. The code to reproduce the experimental results is available at https://github.com/adeyemiadeoye/ggn-score-nn.

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