Neural Fixed-Point Acceleration for Convex Optimization
arXiv:2107.10254
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
AutoML@ICML2021
References in corpus (7)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- The NumPy array: a structure for efficient numerical computation
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
- Differentiable Convex Optimization Layers
- On Differentiating Parameterized Argmin and Argmax Problems with Application to Bi-level Optimization
- Using learned optimizers to make models robust to input noise
- Training Learned Optimizers with Randomly Initialized Learned Optimizers