MétaCan
Menu
Back to cohort
Record W2965199817

Pure entropic regularization for metrical task systems

2019· article· en· W2965199817 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

VenueOxford University Research Archive (ORA) (University of Oxford) · 2019
Typearticle
Languageen
FieldComputer Science
TopicOptimization and Search Problems
Canadian institutionsMcGill University
Fundersnot available
KeywordsCompetitive analysisRandomized algorithmOnline algorithmBinary logarithmMetric spaceComputer scienceDeterministic algorithmMathematicsConditional entropyEntropy (arrow of time)EmbeddingRegularization (linguistics)ExploitAlgorithmMathematical optimizationCombinatoricsDiscrete mathematicsUpper and lower boundsArtificial intelligencePrinciple of maximum entropy
DOInot available

Abstract

fetched live from OpenAlex

<p>We show that on every <i>n</i>-point HST metric, there is a randomized online algorithm for metrical task systems (MTS) that is 1-competitive for service costs and <i>O</i>(log <i>n</i>)-competitive for movement costs. In general, these refined guarantees are optimal up to the implicit constant. While an <i>O</i>(log <i>n</i>)-competitive algorithm for MTS on HST metrics was developed by Bubeck et al. (SODA'19), that approach could only establish an <i>O</i>((log <i>n</i>)<sup>2</sup>)-competitive ratio when the service costs are required to be <i>O</i>(1)-competitive. Our algorithm can be viewed as an instantiation of online mirror descent with the regularizer derived from a multiscale conditional entropy.</p><br>\n\n<p>In fact, our algorithm satisfies a set of even more refined guarantees; we are able to exploit this property to combine it with known random embedding theorems and obtain, for <i>any</i> <i>n</i>-point metric space, a randomized algorithm that is 1-competitive for service costs and <i>O</i>((log <i>n</i>)<sup>2</sup>)-competitive for movement costs.</p>

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)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.953
Threshold uncertainty score0.977

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0020.002
Science and technology studies0.0010.000
Scholarly communication0.0000.001
Open science0.0030.001
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 head0.025
GPT teacher head0.248
Teacher spread0.223 · 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