mlsanityData to 7 Oct 2026

Neural Fixed-Point Acceleration for Convex Optimization

arXiv 2107.10254 ↗First posted 21 Jul 2021cs.LG cs.AI math.OCcited by 10

Not on the map. Why?

Abstract (arXiv)

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

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 31 of its 56 references that are in the map. First posted on arXiv 21 Jul 2021.

Builds on

31 of 56 references.

References · 31

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  4. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  5. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,806
  6. 2016CVXPY: A Python-Embedded Modeling Language for Convex Optimizationcited by 633
  7. 2016Learning to learn by gradient descent by gradient descentcited by 616
  8. 2018Machine Learning for Combinatorial Optimization: a Methodological Tour d'Horizoncited by 612
  9. 2019Deep Equilibrium Modelscited by 603
  10. 2017OptNet: Differentiable Optimization as a Layer in Neural Networkscited by 588
  11. 2017Learning Combinatorial Optimization Algorithms over Graphscited by 557
  12. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
19 more
  1. 2021Machine learning accelerated computational fluid dynamicscited by 461
  2. 2019Differentiable Convex Optimization Layerscited by 458
  3. 2016Learning to Optimizecited by 195
  4. 2021DC3: A learning method for optimization with hard constraintscited by 181
  5. 2018Differentiable MPC for End-to-end Planning and Controlcited by 178
  6. 2020Solving Mixed Integer Programs Using Neural Networkscited by 178
  7. 2018Learning Latent Permutations with Gumbel-Sinkhorn Networkscited by 172
  8. 2020Multiscale Deep Equilibrium Modelscited by 149
  9. 2017Learned Optimizers that Scale and Generalizecited by 109
  10. 2016On Differentiating Parameterized Argmin and Argmax Problems with Application to Bi-level Optimizationcited by 108
  11. 2015The Fast Bilateral Solvercited by 86
  12. 2020Hypersolvers: Toward Fast Continuous-Depth Modelscited by 33
  13. 2018Globally Convergent Type-I Anderson Acceleration for Non-Smooth Fixed-Point Iterationscited by 24
  14. 2018Solution Refinement at Regular Points of Conic Problemscited by 21
  15. 2021Training Learned Optimizers with Randomly Initialized Learned Optimizerscited by 13
  16. 2019Using learned optimizers to make models robust to input noisecited by 10
  17. 2020A Learning-boosted Quasi-Newton Method for AC Optimal Power Flowcited by 8
  18. 2017A Semismooth Newton Method for Fast, Generic Convex Programmingcited by 5
  19. 2021OpReg-Boost: Learning to Accelerate Online Algorithms with Operator Regressioncited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 2; 2024: 2; 2025: 0; 2026: 2.

10 papers.

  1. 2022Tutorial on amortized optimizationcited by 83
  2. 2023Learning to Warm-Start Fixed-Point Optimization Algorithmscited by 32
  3. 2023Machine Learning for Large-Scale Optimization in 6G Wireless Networkscited by 18
  4. 2022Graph-based Neural Acceleration for Nonnegative Matrix Factorizationcited by 9
  5. 2022A Recursively Recurrent Neural Network (R2N2) Architecture for Learning Iterative Algorithmscited by 8
  6. 2022Principled Acceleration of Iterative Numerical Methods Using Machine Learningcited by 6
  7. 2024Data-Driven Performance Guarantees for Classical and Learned Optimizerscited by 5
  8. 2024Accelerating Legacy Numerical Solvers by Non-intrusive Gradient-based Meta-solvingcited by 2
  9. 2026Memory-Computation Tradeoffs in Semi Amortized Parametric Optimizationcited by 0
  10. 2026Reinforcement Learning to Accelerate Primal-Dual Hybrid Gradient for Linear Programmingcited by 0