REVIEW 4 cited by
A Primer on Coordinate Descent Algorithms
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
A Primer on Coordinate Descent Algorithms
read the original abstract
This monograph presents a class of algorithms called coordinate descent algorithms for mathematicians, statisticians, and engineers outside the field of optimization. This particular class of algorithms has recently gained popularity due to their effectiveness in solving large-scale optimization problems in machine learning, compressed sensing, image processing, and computational statistics. Coordinate descent algorithms solve optimization problems by successively minimizing along each coordinate or coordinate hyperplane, which is ideal for parallelized and distributed computing. Avoiding detailed technicalities and proofs, this monograph gives relevant theory and examples for practitioners to effectively apply coordinate descent to modern problems in data science and engineering.
Forward citations
Cited by 4 Pith papers
-
First-Order Methods for Solving Convex (Strongly) Concave Minimax Problems with Functional Constraints
PALM achieves Õ(ε^{-1}) first-order complexity for ε-KKT points in convex-strongly-concave minimax problems with functional constraints and Õ(ε^{-3/2}) for the dual in the convex-concave case.
-
bAdag: an adaptive block coordinate gradient method for smooth nonconvex functions
Introduces bAdag, an AdaGrad-based block coordinate gradient method with ergodic sublinear convergence proofs for smooth nonconvex objectives under block Lipschitz gradient assumptions, covering cyclic, uniform random...
-
Randomized Subsystem Descent for Fermion-to-Qubit Mapping
Randomized Subsystem Descent reduces weighted Pauli weight in fermion-to-qubit mappings for Hubbard models up to 16x16 sites and molecular Hamiltonians with 54 modes.
-
Stochastic block coordinate and function alternation for multi-objective optimization and learning
A new alternating stochastic optimization method for multi-objective problems that lowers computational cost per iteration by block and objective alternation while recovering classical convergence rates under convex, ...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.