atlas

Research map / Optimization / Nonconvex and smooth optimization

ADMM without a Fixed Penalty Parameter: Faster Convergence with New Adaptive Penalization

NeurIPS 2017 · Optimization › Nonconvex and smooth optimization · approach: Coordinate and Adam convergence analysis

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
locally adaptive penalty (LA-SADMM) vs fixed-penalty SADMMstochastic ADMM for generalized lasso (SVM + GGLASSO) · w8a, gisetteobjective vs iterationsHelped
locally adaptive penalty (LA-ADMM) vs fixed penalty linearized ADMMrobust regression with low-rank regularizer · synthetic dataobjective vs iterationsNo clear effect
locally adaptive penalty (LA-ADMM) vs fixed penalty linearized ADMMlow-rank representation · shapeobjective vs iterationsNo clear effect
self-adaptive residual-based penalty (ADMM-AP) vs locally adaptive penaltylinearized ADMM baselines · RR+LR and LRRobjective vs iterationsHurt
theoretical complexity: adaptive penalty (deterministic) vs fixed penalty ADMMADMM for structured non-smooth problems · theory, local error bound exponent thetaiteration complexity: O(1/eps) to O(1/eps^(1-theta))Helped

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