REVIEW 2 cited by
On a Unified and Simplified Proof for the Ergodic Convergence Rates of PPM, PDHG and ADMM
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
Signed reviews
abstract
We present a unified viewpoint of proximal point method (PPM), primal-dual hybrid gradient (PDHG) and alternating direction method of multipliers (ADMM) for solving convex-concave primal-dual problems. This viewpoint shows the equivalence of these three algorithms upto a norm change, and it leads to a four-line simple proof of their $\mathcal O(1/k)$ ergodic rates. The simple proof technique is not limited to these three algorithms, but can also be utilized to analyze related algorithms, such as gradient descent, linearized PDHG, inexact algorithms, just to name a few.
Forward citations
Cited by 2 Pith papers
-
On the Relationship Between CoCoA and ADMM for Distributed Empirical Risk Minimization
Ridge-regularized CoCoA is shown to be a special case of proximal ADMM, and consensus ADMM is shown to be equivalent to proximal ADMM under a parameter mapping and sign reversal of the saddle objective.
-
An Overview of GPU-based First-Order Methods for Linear Programming and Extensions
A survey of GPU-based first-order LP solvers focusing on cuPDLP, its PDHG core, theory, benchmarks, and extensions to QP, SDP, and conic programming.
Discussion (0). Continue with ORCID to comment.