Papers › Training a Two Layer ReLU Network Analytically

Training a Two Layer ReLU Network Analytically

6 Apr 2023arXiv:2304.02972archive 2025-07-28

Adrian Barbu

Neural networks are usually trained with different variants of gradient descent based optimization algorithms such as stochastic gradient descent or the Adam optimizer. Recent theoretical work states that the critical points (where the gradient of the loss is zero) of two-layer ReLU networks with the square loss are not all local minima. However, in this work we will explore an algorithm for training two-layer neural networks with ReLU-like activation and the square loss that alternatively finds the critical points of the loss function analytically for one layer while keeping the other layer and the neuron activation pattern fixed. Experiments indicate that this simple algorithm can find deeper optima than Stochastic Gradient Descent or the Adam optimizer, obtaining significantly smaller training loss values on four out of the five real datasets evaluated. Moreover, the method is faster than the gradient descent methods and has virtually no tuning parameters.

PaperPDFCode

Code

barbua/anmin officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Vocal Bursts Valence Prediction

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Adam

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections