AI Paper Atlas

Research map / Optimization / Optimizers

Non-Parametric Optimization for Scalable Learning in Stochastic Decision Problems

Mohsen Amidzadeh, Lauri Viitasaari, Mario Di Francesco

ICML 2026 · Optimization › Optimizers · approach: Stochastic gradient MCMC

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
omit the Malliavin-based optimality term from the loss (ablation)SPF · Scalar TV-SO (Exp1), t=1learning performanceHurt
use SPF (non-parametric) instead of PDMSPF · Scalar TV-SO (Exp1)runtime per update step: 9 -> < 1Improved
use SPF instead of PDMSPF · Constrained TV-SO (Exp2)runtime per update step: 41 -> < 1Improved
use SPF instead of PDM and PSGSPF · Least-squares recovery (n=10, d=5)optimality distance and suboptimalityImproved
use SPF instead of PDMSPF · Logistic regressionobjective suboptimalityNo clear effect
use SPF instead of PSGSPF · Logistic regressionobjective suboptimalityImproved
increase NN parameterization dimension (ablation)SPF · Least-squares recoveryruntimeNo clear effect
increase NN parameterization dimension (ablation)PDM · Least-squares recoveryruntimeHurt
use SPF instead of PSG in high dimensionSPF · Least-squares recovery (n=100, d=50)performanceImproved

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