MétaCan
Menu
Back to cohort
Record W3211820441

Best-case lower bounds in online learning

2021· article· en· W3211820441 on OpenAlexafffund
Cristóbal Guzmán, Nishant A. Mehta, Ali Mortazavi

Bibliographic record

VenueUniversity of Twente Research Information · 2021
Typearticle
Languageen
FieldDecision Sciences
TopicAdvanced Bandit Algorithms Research
Canadian institutionsUniversity of Victoria
FundersAgencia Nacional de Investigación y DesarrolloNatural Sciences and Engineering Research Council of CanadaInstitut national de recherche en informatique et en automatique (INRIA)
KeywordsSublinear functionRegretUpper and lower boundsHindsight biasOnline learningComputer scienceContrast (vision)Online algorithmMathematical optimizationMathematicsArtificial intelligenceAlgorithmMachine learningDiscrete mathematics
DOInot available

Abstract

fetched live from OpenAlex

Much of the work in online learning focuses on the study of sublinear upper bounds on the regret. In this work, we initiate the study of best-case lower bounds in online convex optimization, wherein we bound the largest improvement an algorithm can obtain relative to the single best action in hindsight. This problem is motivated by the goal of better understanding the adaptivity of a learning algorithm. Another motivation comes from fairness: it is known that best-case lower bounds are instrumental in obtaining algorithms for decision-theoretic online learning (DTOL) that satisfy a notion of group fairness. Our contributions are a general method to provide best-case lower bounds in Follow the Regularized Leader (FTRL) algorithms with time-varying regularizers, which we use to show that best-case lower bounds are of the same order as existing upper regret bounds: this includes situations with a fixed learning rate, decreasing learning rates, timeless methods, and adaptive gradient methods. In stark contrast, we show that the linearized version of FTRL can attain negative linear regret. Finally, in DTOL with two experts and binary losses, we fully characterize the best-case sequences, which provides a finer understanding of the best-case lower bounds.

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)0.024
metaresearch head score (Gemma)0.129
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: Empirical · Consensus signal: none
Teacher disagreement score0.024
Threshold uncertainty score0.129

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0240.129
Meta-epidemiology (narrow)0.0050.002
Meta-epidemiology (broad)0.0040.003
Bibliometrics0.0030.004
Science and technology studies0.0030.007
Scholarly communication0.0090.017
Open science0.0060.007
Research integrity0.0050.015
Insufficient payload (model declined to judge)0.0120.004

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 head0.181
GPT teacher head0.452
Teacher spread0.271 · 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
GenreEmpirical

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
Published2021
Admission routes2
Has abstractyes

Explore more

Same venueUniversity of Twente Research InformationSame topicAdvanced Bandit Algorithms ResearchFrench-language works237,207