MétaCan
Menu
Back to cohort

On Weighted Cross-Entropy for Label-Imbalanced Separable Data: An Algorithmic-Stability Study

2023· article· en· W4372260056 on OpenAlexaff
Puneesh Deora, Christos Thrampoulidis

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicDomain Adaptation and Few-Shot Learning
Canadian institutionsUniversity of British Columbia
Fundersnot available
KeywordsComputer scienceEarly stoppingGeneralization errorLogarithmCross entropyGradient descentConjectureMathematicsAlgorithmRegularization (linguistics)Applied mathematicsStability (learning theory)Artificial intelligenceMachine learningPattern recognition (psychology)Artificial neural networkDiscrete mathematics

Abstract

fetched live from OpenAlex

Implicit bias theory characterizes notions of simplicity in the weights learned by gradient descent when training without explicit regularization beyond zero training error, and has served as a cornerstone result for theoretically justifying good generalization of interpolating models. However, its asymptotic nature (in number of gradient steps) limits its practical relevance. This motivates developing finite-time generalization bounds. Specifically, recent works have proposed bounding the generalization error indirectly by controlling the corresponding test loss via the algorithmic-stability framework. Concretely, for cross-entropy (CE) training on separable balanced data, they show that the CE test loss decays as fast (up to logarithmic factors) as the test error. In this paper, we study generalization under label imbalances. Motivated by our empirical observation that weighted CE (wCE) can significantly outperform the max-margin classifier at early training phases, we ask whether the stability framework can prove this early-stopping result. To this end, we extend the analysis to the imbalanced setting and bound the test loss of wCE. For Gaussian mixtures, we show this bound is orderwise the same as the balanced error of the max-margin classifier, suggesting the test loss might not be a good proxy of balanced error for wCE under imbalances. We further support this conjecture with empirical results.

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)0.016
metaresearch head score (Gemma)0.075
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.016
Threshold uncertainty score0.087

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0160.075
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0020.001
Bibliometrics0.0030.001
Science and technology studies0.0010.006
Scholarly communication0.0030.008
Open science0.0020.005
Research integrity0.0020.005
Insufficient payload (model declined to judge)0.0020.001

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 head0.110
GPT teacher head0.386
Teacher spread0.276 · 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 designSimulation or modeling
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

Citations1
Published2023
Admission routes1
Has abstractyes

Explore more

Same topicDomain Adaptation and Few-Shot LearningFrench-language works237,207