MétaCan
Menu
Back to cohort
Record W3171665446

PAGE: A Simple and Optimal Probabilistic Gradient Estimator for Nonconvex Optimization

2021· article· en· W3171665446 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueKing Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology) · 2021
Typearticle
Languageen
FieldComputer Science
TopicStochastic Gradient Optimization Techniques
Canadian institutionsKootenay Association for Science & Technology
Fundersnot available
KeywordsCombinatoricsOmegaUpper and lower boundsEstimatorMathematicsSimple (philosophy)Convergence (economics)Matching (statistics)Rate of convergenceDiscrete mathematicsAlgorithmComputer sciencePhysicsMathematical analysisStatistics
DOInot available

Abstract

fetched live from OpenAlex

In this paper, we propose a novel stochastic gradient estimator-ProbAbilistic Gradient Estimator (PAGE)-for nonconvex optimization. PAGE is easy to implement as it is designed via a small adjustment to vanilla SGD: in each iteration, PAGE uses the vanilla minibatch SGD update with probability p t or reuses the previous gradient with a small adjustment, at a much lower computational cost, with probability 1 - p(t). We give a simple formula for the optimal choice of p(t). Moreover, we prove the first tight lower bound Omega (n + root n/epsilon(2)), for non-convex finite-sum problems, which also leads to a tight lower bound Omega (b + root b/epsilon(2)) for non- convex online problems, where b := min{sigma(2)/epsilon(2), n} . Then, we show that PAGE obtains the optimal convergence results O(n + root n/epsilon(2)) (finite-sum) and O(b + root b/is an element of(2)) (online) matching our lower bounds for both nonconvex finite-sum and online problems. Besides, we also show that for nonconvex functions satisfying the Polyak-Lojasiewicz (PL) condition, PAGE can automatically switch to a faster linear convergence rate O(. log 1/epsilon). Finally, we conduct several deep learning experiments (e.g., LeNet, VGG, ResNet) on real datasets in PyTorch showing that PAGE not only converges much faster than SGD in training but also achieves the higher test accuracy, validating the optimal theoretical results and confirming the practical superiority of PAGE.

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.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Science and technology studies
Consensus categoriesScience and technology studies
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.841
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0020.006
Science and technology studies0.0030.020
Scholarly communication0.0000.001
Open science0.0020.002
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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 head0.007
GPT teacher head0.196
Teacher spread0.189 · 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