Pith. sign in

REVIEW 1 cited by

Practical Gauss-Newton Optimisation for Deep Learning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1706.03662 v2 pith:V4SCL3IT submitted 2017-06-12 stat.ML

classification stat.ML
keywords optimisationfunctionsgauss-newtonmethodsperformancetransferworkalgorithm
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We present an efficient block-diagonal ap- proximation to the Gauss-Newton matrix for feedforward neural networks. Our result- ing algorithm is competitive against state- of-the-art first order optimisation methods, with sometimes significant improvement in optimisation performance. Unlike first-order methods, for which hyperparameter tuning of the optimisation parameters is often a labo- rious process, our approach can provide good performance even when used with default set- tings. A side result of our work is that for piecewise linear transfer functions, the net- work objective function can have no differ- entiable local maxima, which may partially explain why such transfer functions facilitate effective optimisation.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Parameter identification for predator-prey system with sparse data

    stat.ME 2026-08 conditional novelty 5.0 of 10

    A parameter-estimation framework for Lotka-Volterra models with sparse data, combining Natural Gradient Ascent, non-dimensionalization, and an adaptive ODE solver, claims fewer iterations and more stability than stand...

Pith tools