MétaCan
Menu
Back to cohort
Record W2965944281

Tight analyses for non-smooth stochastic gradient descent

2019· article· en· W2965944281 on OpenAlexaff
Nicholas J. A. Harvey, Christopher Liaw, Yaniv Plan, Sikander Randhawa

Bibliographic record

VenueConference on Learning Theory · 2019
Typearticle
Languageen
FieldComputer Science
TopicStochastic Gradient Optimization Techniques
Canadian institutionsUniversity of British Columbia
Fundersnot available
KeywordsMathematicsLipschitz continuityStochastic gradient descentDifferentiable functionCombinatoricsConvex functionGradient descentUpper and lower boundsRegular polygonDiscrete mathematicsApplied mathematicsMathematical analysisComputer science
DOInot available

Abstract

fetched live from OpenAlex

Consider the problem of minimizing functions that are Lipschitz and strongly convex, but not necessarily differentiable. We prove that after $T$ steps of stochastic gradient descent, the error of the final iterate is $O(\log(T)/T)$ with high probability. We also construct a function from this class for which the error of the final iterate of deterministic gradient descent is $\Omega(\log(T)/T)$. This shows that the upper bound is tight and that, in this setting, the last iterate of stochastic gradient descent has the same general error rate (with high probability) as deterministic gradient descent. This resolves both open questions posed by Shamir (2012). An intermediate step of our analysis proves that the suffix averaging method achieves error $O(1/T)$ with high probability, which is optimal (for any first-order optimization method). This improves results of Rakhlin (2012) and Hazan and Kale (2014), both of which achieved error $O(1/T)$, but only in expectation, and achieved a high probability error bound of $O(\log \log(T)/T)$, which is suboptimal. We prove analogous results for functions that are Lipschitz and convex, but not necessarily strongly convex or differentiable. After $T$ steps of stochastic gradient descent, the error of the final iterate is $O(\log(T)/\sqrt{T})$ with high probability, and there exists a function for which the error of the final iterate of deterministic gradient descent is $\Omega(\log(T)/\sqrt{T})$.

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)0.027
metaresearch head score (Gemma)0.131
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: Theoretical or conceptual
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.027
Threshold uncertainty score0.142

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0270.131
Meta-epidemiology (narrow)0.0050.003
Meta-epidemiology (broad)0.0060.005
Bibliometrics0.0040.003
Science and technology studies0.0030.008
Scholarly communication0.0050.012
Open science0.0070.011
Research integrity0.0050.014
Insufficient payload (model declined to judge)0.0120.002

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 head0.047
GPT teacher head0.310
Teacher spread0.263 · 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 designTheoretical or conceptual
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

Citations41
Published2019
Admission routes1
Has abstractyes

Explore more

Same venueConference on Learning TheorySame topicStochastic Gradient Optimization TechniquesFrench-language works237,207