Saved in:
Bibliographic Details
Main Authors: Afanah, Assem, Rosenow, Bernd
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.20010
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917354837901312
author Afanah, Assem
Rosenow, Bernd
author_facet Afanah, Assem
Rosenow, Bernd
contents We analyze the soft committee machine with Rectified Linear Unit (ReLU) activation by means of the replica method. In a realizable teacher--student setting, we compute the quenched free energy within a replica-symmetric ansatz and obtain the typical generalization behavior from the saddle-point equations for the macroscopic order parameters. The system exhibits a transition from an unspecialized symmetric phase to a specialized phase in which the permutation symmetry among hidden units is broken. We determine the critical training-set size as a function of the inverse training temperature and derive analytic expressions both near the transition and in the asymptotic large-sample regime. Unlike the corresponding model with sigmoidal activations, which undergoes a first-order transition, the ReLU soft committee machine shows a continuous specialization transition. These results show that the activation function plays a decisive role in the phase structure and generalization behavior of multilayer networks.
format Preprint
id arxiv_https___arxiv_org_abs_2603_20010
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Continuous Specialization Transition in the Soft Committee Machine with ReLU Activation
Afanah, Assem
Rosenow, Bernd
Disordered Systems and Neural Networks
We analyze the soft committee machine with Rectified Linear Unit (ReLU) activation by means of the replica method. In a realizable teacher--student setting, we compute the quenched free energy within a replica-symmetric ansatz and obtain the typical generalization behavior from the saddle-point equations for the macroscopic order parameters. The system exhibits a transition from an unspecialized symmetric phase to a specialized phase in which the permutation symmetry among hidden units is broken. We determine the critical training-set size as a function of the inverse training temperature and derive analytic expressions both near the transition and in the asymptotic large-sample regime. Unlike the corresponding model with sigmoidal activations, which undergoes a first-order transition, the ReLU soft committee machine shows a continuous specialization transition. These results show that the activation function plays a decisive role in the phase structure and generalization behavior of multilayer networks.
title Continuous Specialization Transition in the Soft Committee Machine with ReLU Activation
topic Disordered Systems and Neural Networks
url https://arxiv.org/abs/2603.20010