Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

count% of corpus
0111 · Mar 201919922001200920172026
2 results for “cocoercivity”
Finite-Time Last-Iterate Convergence for Multi-Agent Learning in Gamesmath.OC

Paper analyzes convergence rates for multi-agent learning in games.

problem Convergence rates for multi-agent learning in games.
method Characterizes finite-time convergence rates for joint OGD learning on λλ-cocoercive games and develops adaptive algorithms.
result Adaptive algorithms achieve same convergence rates as non-adaptive counterparts.
multi-agent learningconvergence ratescocoercive gamesonline gradient descentfully adaptive algorithms
2020-02-23abs ↗pdf ↗
Cocoercivity, Smoothness and Bias in Variance-Reduced Stochastic Gradient Methodsmath.OC

SVAG method examines biased updates in variance-reduced stochastic gradient methods.

problem Examining biased updates in variance-reduced stochastic gradient methods.
method Introduces SVAG, a SAG/SAGA-like method with adjustable bias, analyzed in a cocoercive root-finding setting.
result SVAG's step-size requirements for gradients are less restrictive compared to non-gradient cases, highlighting the need for careful analysis.
SVAGbiased updatesvariance-reducedstochastic gradientcocoercivity
2019-03-21abs ↗pdf ↗