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.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

3 results for “OMWU”

Linear Last-iterate Convergence in Constrained Saddle-point Optimizationcs.LG

Improved convergence rates for saddle-point optimization algorithms.

problem Understanding last-iterate convergence rates for saddle-point optimization algorithms in constrained settings.

method Expanding the understanding of last-iterate convergence for Optimistic Gradient Descent Ascent (OGDA) and Optimistic Multiplicative Weights Update (OMWU) in the constrained setting.

result Linear last-iterate convergence achieved with a universal constant learning rate for OMWU in bilinear games over the simplex.

saddle-point optimization last-iterate convergence OGDA OMWU bilinear games

2020-06-16abs ↗pdf ↗

Last-Iterate Convergence: Zero-Sum Games and Constrained Min-Max Optimizationmath.OC

Motivated by applications in Game Theory, Optimization, and Generative Adversarial Networks, recent work of Daskalakis et al \cite{DISZ17} and follow-up work of Liang and Stokes \cite{LiangS18} have established that a variant of the widely used Gradient Descent/Ascent procedure, called "Optimistic Gradient Descent/Asce…

2018-07-11abs ↗pdf ↗

Last iterate convergence in no-regret learning: constrained min-max optimization for convex-concave landscapescs.LG

In a recent series of papers it has been established that variants of Gradient Descent/Ascent and Mirror Descent exhibit last iterate convergence in convex-concave zero-sum games. Specifically, \cite{DISZ17, LiangS18} show last iterate convergence of the so called "Optimistic Gradient Descent/Ascent" for the case of \t…

2020-02-17abs ↗pdf ↗