Papers › An Analytical Formula of Population Gradient for two-layered ReLU network and its...

An Analytical Formula of Population Gradient for two-layered ReLU network and its Applications in Convergence and Critical Point Analysis

2 Mar 2017ICML 2017 8arXiv:1703.00560archive 2025-07-28

Yuandong Tian

In this paper, we explore theoretical properties of training a two-layered ReLU network g(x; w) = ∑ⱼ₌₁ᴷ σ(wⱼᵀx) with centered d-dimensional spherical Gaussian input x (σ=ReLU). We train our network with gradient descent on w to mimic the output of a teacher network with the same architecture and fixed parameters w^*. We show that its population gradient has an analytical formula, leading to interesting theoretical analysis of critical points and convergence behaviors. First, we prove that critical points outside the hyperplane spanned by the teacher parameters ("out-of-plane") are not isolated and form manifolds, and characterize in-plane critical-point-free regions for two ReLU case. On the other hand, convergence to w^* for one ReLU node is guaranteed with at least (1-ϵ)/2 probability, if weights are initialized randomly with standard deviation upper-bounded by O(ϵ/√(d)), consistent with empirical practice. For network with many ReLU nodes, we prove that an infinitesimal perturbation of weight initialization results in convergence towards w^* (or its permutation), a phenomenon known as spontaneous symmetric-breaking (SSB) in physics. We assume no independence of ReLU activations. Simulation verifies our findings.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

yuandong-tian/ICML17_ReLU officialmentioned on GitHubSyntology: not harvested report
MindSpore-scientific/code-14 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data,... (arXiv:2306.01116; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

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

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ReLU

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