MétaCan
Menu
Back to cohort
Record W4389923777 · doi:10.1109/tit.2023.3344141

Order Optimal Bounds for One-Shot Federated Learning Over Non-Convex Loss Functions

2023· article· en· W4389923777 on OpenAlexaff
Arsalan Sharifnassab, Saber Salehkaleybar, S. Jamaloddin Golestani

Bibliographic record

VenueIEEE Transactions on Information Theory · 2023
Typearticle
Languageen
FieldComputer Science
TopicPrivacy-Preserving Technologies in Data
Canadian institutionsUniversity of Alberta
Fundersnot available
KeywordsRegular polygonComputer scienceOrder (exchange)Convex functionConvex optimizationMathematical optimizationMathematicsEconomics

Abstract

fetched live from OpenAlex

We consider the problem of federated learning in a one-shot setting in which there are$m$machines, each observing$n$sample functions from an unknown distribution on non-convex loss functions. Let$F:[-1,1]^{d}\to {\mathbb {R}} $be the expected loss function with respect to this unknown distribution. The goal is to find an estimate of the minimizer of$F$. Based on its observations, each machine generates a signal of bounded length$B$and sends it to a server. The server collects signals of all machines and outputs an estimate of the minimizer of$F$. We show that the expected loss of any algorithm is lower bounded by$\max \big (1/(\sqrt {n}(mB)^{1/d}), 1/\sqrt {mn}\big)$, up to a logarithmic factor. We then prove that this lower bound is order optimal in$m$and$n$by presenting a distributed learning algorithm, called Multi-Resolution Estimator for Non-Convex loss function (MRE-NC), whose expected loss matches the lower bound for large$mn$up to polylogarithmic factors.

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)0.056
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: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.014
Threshold uncertainty score0.075

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0140.056
Meta-epidemiology (narrow)0.0060.002
Meta-epidemiology (broad)0.0070.002
Bibliometrics0.0030.003
Science and technology studies0.0020.004
Scholarly communication0.0060.012
Open science0.0080.007
Research integrity0.0070.010
Insufficient payload (model declined to judge)0.0130.004

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 head0.032
GPT teacher head0.278
Teacher spread0.246 · 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

Citations2
Published2023
Admission routes1
Has abstractyes

Explore more

Same venueIEEE Transactions on Information TheorySame topicPrivacy-Preserving Technologies in DataFrench-language works237,207