MétaCan
Menu
Back to cohort
Record W2964309400

Revisiting Natural Gradient for Deep Networks

2014· article· en· W2964309400 on OpenAlexaff
Razvan Pascanu, Yoshua Bengio

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicNeural Networks and Applications
Canadian institutionsUniversité de Montréal
Fundersnot available
KeywordsHessian matrixStochastic gradient descentGradient descentRobustness (evolution)DiagonalGeneralizationComputer scienceMetric (unit)Deep learningSubspace topologyAlgorithmArtificial intelligenceMathematicsMathematical optimizationApplied mathematicsArtificial neural network
DOInot available

Abstract

fetched live from OpenAlex

We evaluate natural gradient, an algorithm originally proposed in Amari (1997), for learning deep models. The contributions of this paper are as follows. We show the connection between natural gradient and three other recently proposed meth-ods: Hessian-Free (Martens, 2010), Krylov Subspace Descent (Vinyals and Povey, 2012) and TONGA (Le Roux et al., 2008). We empirically evaluate the robust-ness of natural gradient to the ordering of the training set compared to stochastic gradient descent and show how unlabeled data can be used to improve generaliza-tion error. Another contribution is to extend natural gradient to incorporate second error information alongside the manifold information. Lastly we benchmark this new algorithm as well as natural gradient, where both are implemented using a truncated Newton approach for inverting the metric matrix instead of using a di-agonal approximation of it. 1

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.006
metaresearch head score (Gemma)0.025
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.007
Threshold uncertainty score0.033

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0060.025
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0010.002
Scholarly communication0.0020.005
Open science0.0020.003
Research integrity0.0020.003
Insufficient payload (model declined to judge)0.0040.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.010
GPT teacher head0.237
Teacher spread0.227 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations139
Published2014
Admission routes1
Has abstractyes

Explore more

Same topicNeural Networks and ApplicationsFrench-language works237,207