Decentralized optimization with non-identical sampling in presence of\n stragglers
Bibliographic record
Abstract
We consider decentralized consensus optimization when workers sample data\nfrom non-identical distributions and perform variable amounts of work due to\nslow nodes known as stragglers. The problem of non-identical distributions and\nthe problem of variable amount of work have been previously studied separately.\nIn our work we analyze them together under a unified system model. We study the\nconvergence of the optimization algorithm when combining worker outputs under\ntwo heuristic methods: (1) weighting equally, and (2) weighting by the amount\nof work completed by each. We prove convergence of the two methods under\nperfect consensus, assuming straggler statistics are independent and identical\nacross all workers for all iterations. Our numerical results show that under\napproximate consensus the second method outperforms the first method for both\nconvex and non-convex objective functions. We make use of the theory on minimum\nvariance unbiased estimator (MVUE) to evaluate the existence of an optimal\nmethod for combining worker outputs. While we conclude that neither of the two\nheuristic methods are optimal, we also show that an optimal method does not\nexist.\n
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.010 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".