MétaCan
Menu
Back to cohort
Record W4315489128 · doi:10.1109/cdc51059.2022.9992906

Bandit learning with regularized second-order mirror descent

2022· article· en· W4315489128 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

Venue2022 IEEE 61st Conference on Decision and Control (CDC) · 2022
Typearticle
Languageen
FieldDecision Sciences
TopicAdvanced Bandit Algorithms Research
Canadian institutionsUniversity of Toronto
FundersHuawei Technologies
KeywordsDescent (aeronautics)Computer scienceOrder (exchange)Gradient descentArtificial intelligenceMathematical optimizationApplied mathematicsMathematicsPhysicsArtificial neural network

Abstract

fetched live from OpenAlex

Many recent game-theoretic applications can benefit from relaxed assumptions on the players’ informational requirements as well as structural properties of the game. Bandit information represents one of the weakest possible environments for which convergence towards Nash equilibrium can be shown. Currently, most results on multi-agent bandit learning only consider games with strict monotonicity or strict variationally stable states. In this work, we propose a novel second-order variant of the bandit mirror descent algorithm and show that it can converge in games with mere VSS, which is a broader class of games compared to the ones studied in the existing literature. Aside from the incorporation of second-order learning, this convergence is also enabled through a Tikhonov regularization term. Furthermore, we show that our algorithm converges in representative games and the adjustment of the regularization term is consistent with our prediction.

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)0.004
metaresearch head score (Gemma)0.002
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Science and technology studies, Insufficient payload (model declined to judge)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.931
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0040.002
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0010.002
Science and technology studies0.0020.000
Scholarly communication0.0010.000
Open science0.0010.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0260.000

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 head0.072
GPT teacher head0.358
Teacher spread0.287 · 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