AI Paper Atlas

Research map / Optimization / Optimizers

Learning Rate Free Sampling in Constrained Domains

Louis Sharrock, Lester Mackey, Christopher Nemeth

NeurIPS 2023 · Optimization › Optimizers · approach: Stochastic gradient MCMC · 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 Coin MSVGD instead of learning-rate-dependent MSVGDConstrained sampling on simplex targets · Sparse Dirichlet simplex targetenergy distanceImproved
Use Coin MSVGD instead of learning-rate-dependent MSVGDConstrained sampling on simplex targets · Quadratic simplex targetenergy distanceMixed
Use Coin MSVGD instead of MSVGD with a sub-optimal learning rateConstrained sampling · Simplex targetsenergy distanceImproved
Use a mirrored method instead of a projected methodConstrained sampling · Simplex targetsenergy distanceImproved
Use Coin MSVGD instead of MSVGDPost-selection inference sampling · Two-dimensional selective distributionenergy distanceImproved
Use Coin MSVGD instead of norejection MCMCPost-selection confidence intervals · Post-selection inferenceconfidence interval coverageImproved
Use Coin MSVGD instead of MSVGD or SVMD with a well-chosen learning ratePost-selection confidence intervals · HIV-1 drug resistance datasetconfidence interval agreement with standard approachNo clear effect
Use Coin MSVGD instead of MSVGD or SVMD with a sub-optimal learning ratePost-selection confidence intervals · HIV-1 drug resistance datasetconfidence interval agreement with standard approachImproved
Use Coin MIED instead of MIEDFairness Bayesian neural network · Adult Incometest accuracy and Calder-Verwer score Pareto frontImproved
Use Coin MIED instead of MIEDFairness Bayesian neural network · Adult IncomeconstraintImproved

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