AI Paper Atlas

Research map / Optimization / Optimizers

Sampling with Trusthworthy Constraints: A Variational Gradient Framework

Xingchao Liu, Xin Tong, qiang liu

NeurIPS 2021 · Optimization › Optimizers · approach: Stochastic gradient MCMC · 2 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 constraint-controlled gradient (Control) instead of primal-dual updates of the multiplierLangevin and SVGD constrained sampling · Loan Application logic constraintlogic loss (train and test)Improved
use SVGD instead of Langevin as the base samplerconstrained sampling methods · Loan Application logic constrainttest accuracyImproved
use constraint-controlled gradient instead of primal-dualconstrained sampling methods · COMPAS monotonic Bayesian neural networkmonotonic loss vs log-likelihood trade-offImproved
use constraint-controlled gradient instead of primal-dualconstrained sampling methods · Adult Income fair Bayesian neural networkconstraint enforcement speed and strictnessImproved
add the constraint to NCSN Langevin sampling using Control+LangevinNCSN on CIFAR10 · black square center constraint, epsilon 0.0001constraint satisfaction and sample diversityImproved

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