From Learning to Optimize to Learning Optimization Algorithms

• URL: http://arxiv.org/abs/2405.18222v1
• Date: Tue, 28 May 2024 14:30:07 GMT
• Title: From Learning to Optimize to Learning Optimization Algorithms
• Authors: Camille Castera, Peter Ochs,
• Abstract summary: We identify key principles that classical algorithms obey, but have up to now, not been used for Learning to Optimize (L2O) We provide a general design pipeline, taking into account data, architecture and learning strategy, and thereby enabling a synergy between classical optimization and L2O. We demonstrate the success of these novel principles by designing a new learning-enhanced BFGS algorithm and provide numerical experiments evidencing its adaptation to many settings at test time.
• Score: 4.066869900592636
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Towards designing learned optimization algorithms that are usable beyond their training setting, we identify key principles that classical algorithms obey, but have up to now, not been used for Learning to Optimize (L2O). Following these principles, we provide a general design pipeline, taking into account data, architecture and learning strategy, and thereby enabling a synergy between classical optimization and L2O, resulting in a philosophy of Learning Optimization Algorithms. As a consequence our learned algorithms perform well far beyond problems from the training distribution. We demonstrate the success of these novel principles by designing a new learning-enhanced BFGS algorithm and provide numerical experiments evidencing its adaptation to many settings at test time.

Related papers

• Bayesian Design Principles for Frequentist Sequential Learning [11.421942894219901]
  We develop a theory to optimize the frequentist regret for sequential learning problems. We propose a novel optimization approach to generate "algorithmic beliefs" at each round. We present a novel algorithm for multi-armed bandits that achieves the "best-of-all-worlds" empirical performance.
  arXiv  Detail & Related papers  (2023-10-01T22:17:37Z)
• PAC-Bayesian Learning of Optimization Algorithms [6.624726878647541]
  We apply the PAC-Bayes theory to the setting of learning-to-optimize. We learn optimization algorithms with provable generalization guarantees (PAC-bounds) and explicit trade-off between a high probability of convergence and a high convergence speed. Our results rely on PAC-Bayes bounds for general, unbounded loss-functions based on exponential families.
  arXiv  Detail & Related papers  (2022-10-20T09:16:36Z)
• Improved Algorithms for Neural Active Learning [74.89097665112621]
  We improve the theoretical and empirical performance of neural-network(NN)-based active learning algorithms for the non-parametric streaming setting. We introduce two regret metrics by minimizing the population loss that are more suitable in active learning than the one used in state-of-the-art (SOTA) related work.
  arXiv  Detail & Related papers  (2022-10-02T05:03:38Z)
• Tree-Based Adaptive Model Learning [62.997667081978825]
  We extend the Kearns-Vazirani learning algorithm to handle systems that change over time. We present a new learning algorithm that can reuse and update previously learned behavior, implement it in the LearnLib library, and evaluate it on large examples.
  arXiv  Detail & Related papers  (2022-08-31T21:24:22Z)
• On the Convergence of Distributed Stochastic Bilevel Optimization Algorithms over a Network [55.56019538079826]
  Bilevel optimization has been applied to a wide variety of machine learning models. Most existing algorithms restrict their single-machine setting so that they are incapable of handling distributed data. We develop novel decentralized bilevel optimization algorithms based on a gradient tracking communication mechanism and two different gradients.
  arXiv  Detail & Related papers  (2022-06-30T05:29:52Z)
• Neural Combinatorial Optimization: a New Player in the Field [69.23334811890919]
  This paper presents a critical analysis on the incorporation of algorithms based on neural networks into the classical optimization framework. A comprehensive study is carried out to analyse the fundamental aspects of such algorithms, including performance, transferability, computational cost and to larger-sized instances.
  arXiv  Detail & Related papers  (2022-05-03T07:54:56Z)
• Evolving Reinforcement Learning Algorithms [186.62294652057062]
  We propose a method for meta-learning reinforcement learning algorithms. The learned algorithms are domain-agnostic and can generalize to new environments not seen during training. We highlight two learned algorithms which obtain good generalization performance over other classical control tasks, gridworld type tasks, and Atari games.
  arXiv  Detail & Related papers  (2021-01-08T18:55:07Z)
• Reverse engineering learned optimizers reveals known and novel mechanisms [50.50540910474342]
  Learneds are algorithms that can themselves be trained to solve optimization problems. Our results help elucidate the previously murky understanding of how learneds work, and establish tools for interpreting future learneds.
  arXiv  Detail & Related papers  (2020-11-04T07:12:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.