atlas

Research map / Optimization / Nonconvex and smooth optimization

Faster Convex Optimization: Simulated Annealing with an Efficient Universal Barrier

ICML 2016 · Optimization › Nonconvex and smooth optimization · approach: Nonconvex minimax and constrained methods · 12 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 the entropic-barrier parameter ν to set the simulated-annealing temperature scheduleSimulated annealing for general convex optimization · General convex optimization (membership oracle)running time: \tilde{O}(n^{4.5}) -> \tilde{O}(\sqrt{\nu} n^{4})Helped
Apply the entropic-barrier schedule to the PSD cone, where the paper gives ν = nSimulated annealing · PSD conerunning time improvement factor: an improvement of n compared to the state-of-the-artHelped
Use the entropic universal barrier, computable implicitly through sampling, instead of requiring a supplied barrierInterior point methods · Arbitrary convex sets described by a membership oracleapplicabilityHelped
Identify the heat path with the central path for the entropic barrierSimulated annealing and interior point methods · Any convex setequivalence of optimization pathsHelped

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