MétaCan
Menu
Back to cohort
Record W7039154034

Limitations of information : theoretic generalization bounds for gradient descent methods in stochastic convex optimization

2023· article· en· W7039154034 on OpenAlexfundno aff

Bibliographic record

VenueKTH Publication Database DiVA (KTH Royal Institute of Technology) · 2023
Typearticle
Languageen
FieldComputer Science
TopicStochastic Gradient Optimization Techniques
Canadian institutionsnot available
FundersNatural Sciences and Engineering Research Council of CanadaVetenskapsrådetUniversity of Toronto
KeywordsMinimaxGeneralizationStochastic gradient descentGradient descentMutual informationRegular polygonConvex optimizationConvex function
DOInot available

Abstract

fetched live from OpenAlex

To date, no “information-theoretic” frameworks for reasoning about generalization error have been shown to establish minimax rates for gradient descent in the setting of stochastic convex optimization. In this work, we consider the prospect of establishing such rates via several existing information-theoretic frameworks: input-output mutual information bounds, conditional mutual information bounds and variants, PAC-Bayes bounds, and recent conditional variants thereof. We prove that none of these bounds are able to establish minimax rates. We then consider a common tactic employed in studying gradient methods, whereby the final iterate is corrupted by Gaussian noise, producing a noisy “surrogate” algorithm. We prove that minimax rates cannot be established via the analysis of such surrogates. Our results suggest that new ideas are required to analyze gradient descent using information-theoretic techniques.

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)0.055
metaresearch head score (Gemma)0.219
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 score0.055
Threshold uncertainty score0.289

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0550.219
Meta-epidemiology (narrow)0.0030.002
Meta-epidemiology (broad)0.0040.003
Bibliometrics0.0030.003
Science and technology studies0.0020.012
Scholarly communication0.0070.022
Open science0.0070.009
Research integrity0.0050.018
Insufficient payload (model declined to judge)0.0050.002

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 head0.062
GPT teacher head0.318
Teacher spread0.256 · 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

Citations0
Published2023
Admission routes1
Has abstractyes

Explore more

Same venueKTH Publication Database DiVA (KTH Royal Institute of Technology)Same topicStochastic Gradient Optimization TechniquesFrench-language works237,207