REVIEW 3 cited by
Neural Fixed-Point Acceleration for Convex Optimization
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
read the original abstract
Fixed-point iterations are at the heart of numerical computing and are often a computational bottleneck in real-time applications that typically need a fast solution of moderate accuracy. We present neural fixed-point acceleration which combines ideas from meta-learning and classical acceleration methods to automatically learn to accelerate fixed-point problems that are drawn from a distribution. We apply our framework to SCS, the state-of-the-art solver for convex cone programming, and design models and loss functions to overcome the challenges of learning over unrolled optimization and acceleration instabilities. Our work brings neural acceleration into any optimization problem expressible with CVXPY. The source code behind this paper is available at https://github.com/facebookresearch/neural-scs
Forward citations
Cited by 3 Pith papers
-
Memory-Computation Tradeoffs in Semi Amortized Parametric Optimization
For smooth strongly convex problems, the required memory scales as (ρ^K/ε)^{dΘ} up to a square-root gap in ε; for convex problems with β-growth (β>2) the scaling is polynomial in ε^{-1} with a K-phase transition beyon...
-
Learning Algorithm Hyperparameters for Fast Parametric Convex Optimization
A machine-learning framework that learns a shared hyperparameter sequence for first-order optimization solvers, achieving order-of-magnitude speedups with only 10 training instances.
-
Neural Network Acceleration of Iterative Methods for Nonlinear Schr\"odinger Eigenvalue Problems
A U-Net trained on solver trajectories accelerates the energy-adaptive Riemannian conjugate gradient method for rotating Gross-Pitaevskii ground states, saving about 22% of iterations and 14.5% of wall time on average.
Discussion (0). Continue with ORCID to comment.