Pith. sign in

REVIEW 1 cited by

Auto-conditioned primal-dual hybrid gradient method and alternating direction method of multipliers

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.01979 v1 pith:B2IDXOVP submitted 2024-10-02 math.OC cs.LGstat.ML

classification math.OCcs.LGstat.ML
keywords methodac-pdhgproblemsprimal-dualalternatingauto-conditionedbilineardirection
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Line search procedures are often employed in primal-dual methods for bilinear saddle point problems, especially when the norm of the linear operator is large or difficult to compute. In this paper, we demonstrate that line search is unnecessary by introducing a novel primal-dual method, the auto-conditioned primal-dual hybrid gradient (AC-PDHG) method, which achieves optimal complexity for solving bilinear saddle point problems. AC-PDHG is fully adaptive to the linear operator, using only past iterates to estimate its norm. We further tailor AC-PDHG to solve linearly constrained problems, providing convergence guarantees for both the optimality gap and constraint violation. Moreover, we explore an important class of linearly constrained problems where both the objective and constraints decompose into two parts. By incorporating the design principles of AC-PDHG into the preconditioned alternating direction method of multipliers (ADMM), we propose the auto-conditioned alternating direction method of multipliers (AC-ADMM), which guarantees convergence based solely on one part of the constraint matrix and fully adapts to it, eliminating the need for line search. Finally, we extend both AC-PDHG and AC-ADMM to solve bilinear problems with an additional smooth term. By integrating these methods with a novel acceleration scheme, we attain optimal iteration complexities under the single-oracle setting.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Optimal Parameter-Free First-Order Methods for Convex Optimization with Unknown Growth and Smoothness

    math.OC 2026-07 accept novelty 7.5 of 10

    Affine W-certificate bundle-level methods (BLW/A-BLW) attain optimal parameter-free rates under unknown Hölder smoothness and growth for convex first-order optimization.

Pith tools