MétaCan
Menu
Back to cohort
Record W3157664688 · doi:10.1145/3453935

Robustness meets algorithms

2021· article· en· W3157664688 on OpenAlexaff
Ilias Diakonikolas, Gautam Kamath, Daniel M. Kane, Jerry Li, Ankur Moitra, Alistair Stewart

Bibliographic record

VenueCommunications of the ACM · 2021
Typearticle
Languageen
FieldMathematics
TopicAdvanced Statistical Methods and Models
Canadian institutionsUniversity of Waterloo
FundersOffice of Naval ResearchAlfred P. Sloan FoundationGoogleDavid and Lucile Packard FoundationNational Science Foundation
KeywordsRobustness (evolution)EstimatorComputer scienceAlgorithmFraction (chemistry)Exponential functionGaussianDimension (graph theory)Mathematical optimizationInverseMathematicsApplied mathematicsStatisticsCombinatorics

Abstract

fetched live from OpenAlex

In every corner of machine learning and statistics, there is a need for estimators that work not just in an idealized model, but even when their assumptions are violated. Unfortunately, in high dimensions, being provably robust and being efficiently computable are often at odds with each other. We give the first efficient algorithm for estimating the parameters of a high-dimensional Gaussian that is able to tolerate a constant fraction of corruptions that is independent of the dimension. Prior to our work, all known estimators either needed time exponential in the dimension to compute or could tolerate only an inverse-polynomial fraction of corruptions. Not only does our algorithm bridge the gap between robustness and algorithms, but also it turns out to be highly practical in a variety of settings.

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)0.014
metaresearch head score (Gemma)0.108
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 score0.014
Threshold uncertainty score0.075

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0140.108
Meta-epidemiology (narrow)0.0030.002
Meta-epidemiology (broad)0.0040.003
Bibliometrics0.0030.003
Science and technology studies0.0020.008
Scholarly communication0.0080.015
Open science0.0040.010
Research integrity0.0070.012
Insufficient payload (model declined to judge)0.0120.006

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 head0.311
GPT teacher head0.481
Teacher spread0.170 · 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

Citations6
Published2021
Admission routes1
Has abstractyes

Explore more

Same venueCommunications of the ACMSame topicAdvanced Statistical Methods and ModelsFrench-language works237,207