AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Approaching Quartic Convergence Rates for Quasi-Stochastic Approximation with Application to Gradient-Free Optimization

Caio Kalil Lauand, Sean P. Meyn

NeurIPS 2022 · Optimization › Nonconvex and smooth optimization · approach: Stochastic gradient last-iterate analysis · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace divergence-minimizing and bilevel regularized baselines with Implicit Flow Network layer (hard conservation plus learned nonlinear constitutive relationship)flow estimation · AC power networks (IEEE-57/118/145/300, ACTIVSg200/500)RMSE on unlabeled edges (MW)Improved
replace divergence-minimizing and bilevel regularized baselines with Implicit Flow Network layerflow estimation · Water distribution (Fairfield, Bellingham, Harrisburg)RMSE on unlabeled edges (m3/s)Improved
increase the fraction of labeled edges toward 90%baselines (Div, Bil-MLP, Bil-GCN, Bil-True) · power and water networksRMSEImproved
use only 10% labeled edges instead of moreIFN · power and water networksRMSENo clear effect
large labeled fraction (above 80% power, 60% water) as opposed to smallIFN versus baselines · power and water networksRMSEMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy