AWhat changed
Allowed concurrent sparse shared-memory stochastic updates without global locks, with convergence analysis for a specified asynchronous sampling model and empirical parallel implementations.
Scientific scope
Allowed concurrent sparse shared-memory stochastic updates without global locks, with convergence analysis for a specified asynchronous sampling model and empirical parallel implementations. Pinned 2011 v1 front orders Feng Niu / Benjamin Recht / Christopher Ré / Stephen J. Wright. Theory assumes convex separable terms, smooth strongly convex objective, bounded gradients/delay, atomic component additions and sparse overlap. Analyzed with-replacement single-coordinate model differs from practical without-replacement full-edge updates. Not convergence for arbitrary dense/nonconvex/asynchronous programs or hardware data-race safety.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Pinned 2011 v1 front orders Feng Niu / Benjamin Recht / Christopher Ré / Stephen J. Wright. Theory assumes convex separable terms, smooth strongly convex objective, bounded gradients/delay, atomic component additions and sparse overlap. Analyzed with-replacement single-coordinate model differs from practical without-replacement full-edge updates. Not convergence for arbitrary dense/nonconvex/asynchronous programs or hardware data-race safety.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction