A Simple Guard for Learned Optimizers

• URL: http://arxiv.org/abs/2201.12426v1
• Date: Fri, 28 Jan 2022 21:32:28 GMT
• Title: A Simple Guard for Learned Optimizers
• Authors: Isabeau Pr\'emont-Schwarz, Jaroslav V\'itk\r{u}, Jan Feyereisl
• Abstract summary: We propose a new class of Safeguarded L2O, called Loss-Guarded L2O (LGL2O) Safeguarded L2O can take a learned algorithm and safeguard it with a generic learning algorithm so that by conditionally switching between the two, the resulting algorithm is provably convergent. We show theoretical proof of LGL2O's convergence guarantee and empirical results comparing to GL2O.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: If the trend of learned components eventually outperforming their hand-crafted version continues, learned optimizers will eventually outperform hand-crafted optimizers like SGD or Adam. Even if learned optimizers (L2Os) eventually outpace hand-crafted ones in practice however, they are still not provably convergent and might fail out of distribution. These are the questions addressed here. Currently, learned optimizers frequently outperform generic hand-crafted optimizers (such as gradient descent) at the beginning of learning but they generally plateau after some time while the generic algorithms continue to make progress and often overtake the learned algorithm as Aesop's tortoise which overtakes the hare and are not. L2Os also still have a difficult time generalizing out of distribution. (Heaton et al., 2020) proposed Safeguarded L2O (GL2O) which can take a learned optimizer and safeguard it with a generic learning algorithm so that by conditionally switching between the two, the resulting algorithm is provably convergent. We propose a new class of Safeguarded L2O, called Loss-Guarded L2O (LGL2O), which is both conceptually simpler and computationally less expensive. The guarding mechanism decides solely based on the expected future loss value of both optimizers. Furthermore, we show theoretical proof of LGL2O's convergence guarantee and empirical results comparing to GL2O and other baselines showing that it combines the best of both L2O and SGD and and in practice converges much better than GL2O.

Related papers

• M-L2O: Towards Generalizable Learning-to-Optimize by Test-Time Fast Self-Adaptation [145.7321032755538]
  Learning to Optimize (L2O) has drawn increasing attention as it often remarkably accelerates the optimization procedure of complex tasks. This paper investigates a potential solution to this open challenge by meta-training an L2O that can perform fast test-time self-adaptation to an out-of-distribution task.
  arXiv  Detail & Related papers  (2023-02-28T19:23:20Z)
• Learning to Generalize Provably in Learning to Optimize [185.71326306329678]
  Learning to optimize (L2O) has gained increasing popularity, which automates the design of optimizees by data-driven approaches. Current L2O methods often suffer from poor generalization performance in at least two folds. We propose to incorporate these two metrics as flatness-aware regularizers into the L2O framework.
  arXiv  Detail & Related papers  (2023-02-22T01:17:31Z)
• Symbolic Learning to Optimize: Towards Interpretability and Scalability [113.23813868412954]
  Recent studies on Learning to Optimize (L2O) suggest a promising path to automating and accelerating the optimization procedure for complicated tasks. Existing L2O models parameterize optimization rules by neural networks, and learn those numerical rules via meta-training. In this paper, we establish a holistic symbolic representation and analysis framework for L2O. We propose a lightweight L2O model that can be meta-trained on large-scale problems and outperformed human-designed and tuneds.
  arXiv  Detail & Related papers  (2022-03-13T06:04:25Z)
• Learning to Optimize: A Primer and A Benchmark [94.29436694770953]
  Learning to optimize (L2O) is an emerging approach that leverages machine learning to develop optimization methods. This article is poised to be the first comprehensive survey and benchmark of L2O for continuous optimization.
  arXiv  Detail & Related papers  (2021-03-23T20:46:20Z)
• Training Stronger Baselines for Learning to Optimize [119.35557905664832]
  We show that even the simplest L2O model could have been trained much better. We leverage off-policy imitation learning to guide the L2O learning, by taking reference to the behavior of analyticals. Our improved training techniques are plugged into a variety of state-of-the-art L2O models, and immediately boost their performance.
  arXiv  Detail & Related papers  (2020-10-18T20:05:48Z)
• Safeguarded Learned Convex Optimization [106.81731132086851]
  Analytic optimization algorithms can be hand-designed to provably solve problems in an iterative fashion. Data-driven algorithms can "learn to optimize" (L2O) with much fewer iterations and similar cost per iteration as general-purpose optimization algorithms. We present a Safe-L2O framework to fuse the advantages of these approaches.
  arXiv  Detail & Related papers  (2020-03-04T04:01:15Z)

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.