Pith. sign in

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

arxiv 2107.10254 v2 pith:WT6SF4OE submitted 2021-07-21 cs.LG cs.AImath.OC

classification cs.LGcs.AImath.OC
keywords accelerationfixed-pointneuraloptimizationconvexaccelerateaccuracyapplications
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
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

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

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

  1. Memory-Computation Tradeoffs in Semi Amortized Parametric Optimization

    cs.LG 2026-07 conditional novelty 7.0 of 10

    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...

  2. Learning Algorithm Hyperparameters for Fast Parametric Convex Optimization

    math.OC 2024-11 conditional novelty 7.0 of 10

    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.

  3. Neural Network Acceleration of Iterative Methods for Nonlinear Schr\"odinger Eigenvalue Problems

    math.NA 2025-07 conditional novelty 6.0 of 10

    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.

Pith tools