AI Paper Atlas

Research map / Optimization / Optimizers

Generalizing Stochastic Smoothing for Differentiation and Gradient Estimation

Felix Petersen, Christian Borgelt, Aashwin Ananda Mishra, Stefano Ermon

ICML 2026 · Optimization › Optimizers · approach: Differentiating through embedded optimization · 0 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
use Cauchy distribution with 32,768 samples instead of 256 samples (best cv) (ablation)generalized stochastic smoothing · 4-digit MNIST sorting (n=5)exact match accuracy: 55.6 -> 85.1Improved
use best sampling strategy chosen by cross-validation instead of vanilla MC (Gaussian, 256 samples) (ablation)generalized stochastic smoothing · 4-digit MNIST sorting (n=5), 256 samplesexact match accuracy: 82.3 -> 83.1Improved
use best sampling strategy by cv instead of vanilla for Gumbel at 1k samples (ablation)generalized stochastic smoothing · 4-digit MNIST sorting (n=5), 1k samplesexact match accuracy: 82.0 -> 84.2Improved
use best sampling strategy by cv instead of vanilla for Cauchy at 256 samples (ablation)generalized stochastic smoothing · 4-digit MNIST sorting (n=5), 256 samplesexact match accuracy: 68.1 -> 55.6Hurt
add antithetic sampling on top of QMC/RQMC strategies (ablation)generalized stochastic smoothing · gradient variance (sorting, shortest paths)L2 error of gradientHurt
add antithetic sampling to vanilla MC without LOO covariate (ablation)vanilla Monte Carlo · gradient variance (sorting, shortest paths)L2 error of gradientImproved
use Cartesian RQMC instead of MC (ablation)generalized stochastic smoothing · gradient variance (sorting, shortest paths)L2 error of gradientImproved
add leave-one-out covariate instead of none (ablation)generalized stochastic smoothing · gradient variance (sorting, shortest paths)L2 error of gradientImproved
use f(x) covariate instead of none or LOO (ablation)generalized stochastic smoothing · 4-digit MNIST sorting (n=5)exact match accuracyNo clear effect
smooth the algorithm instead of the loss (ablation)generalized stochastic smoothing · Warcraft shortest-pathexact match accuracyImproved
smooth the algorithm instead of the loss (ablation)generalized stochastic smoothing · Utah teapot camera pose optimizationfraction of poses recoveredImproved
use logistic distribution (ablation)generalized stochastic smoothing · Warcraft shortest-pathexact match accuracyImproved

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