Papers › Diagonal Rescaling For Neural Networks

Diagonal Rescaling For Neural Networks

25 May 2017arXiv:1705.09319archive 2025-07-28

Jean Lafond, Nicolas Vasilache, Léon Bottou

We define a second-order neural network stochastic gradient training algorithm whose block-diagonal structure effectively amounts to normalizing the unit activations. Investigating why this algorithm lacks in robustness then reveals two interesting insights. The first insight suggests a new way to scale the stepsizes, clarifying popular algorithms such as RMSProp as well as old neural network tricks such as fanin stepsize scaling. The second insight stresses the practical importance of dealing with fast changes of the curvature of the cost.

PaperPDFCode

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

Thrandis/EKFAC-pytorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Optimizing Neural Networks with Kronecker-factored Approximate Curvature (arXiv:1503.05671; that paper's own run record: 48 ran (of which 20 constructed an object rather than computing a result; 36 with no instrument failure: 5 honoured, 1 violated, 30 with no contract checked; 12 where Syntology's instrument failed) · 34 unverified), Fast Approximate Natural Gradient Descent in a Kronecker-factored Eigenbasis (arXiv:1806.03884; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified) and Dynamic Game Theoretic Neural Optimizer (arXiv:2105.03788; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 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

RMSProp

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