paper-with-me

홈 › Papers

Learning to Optimize

2016-06-06 · 2016 2016 6 · Ke Li, Jitendra Malik

Algorithm design is a laborious process and often requires many iterations of ideation and validation. In this paper, we explore automating algorithm design and present a method to learn an optimization algorithm, which we believe to be the first method that can automatically discover a better algorithm. We approach this problem from a reinforcement learning perspective and represent any particular optimization algorithm as a policy. We learn an optimization algorithm using guided policy search and demonstrate that the resulting algorithm outperforms existing hand-engineered algorithms in terms of convergence speed and/or the final objective value.

📄 PDF Abstract BibTeX arXiv:1606.01885

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Learning to Generalize Provably in Learning to Optimize

2023-02-22 · Junjie Yang, Tianlong Chen, Mingkang Zhu, Fengxiang He 외

Learning to optimize (L2O) has gained increasing popularity, which automates the design of optimizers by data-driven approaches. However, current L2O methods often suffer from poor generalization performance in at least …

metaTextGrad: Automatically optimizing language model optimizers

2025-05-24 · Guowei Xu, Mert Yuksekgonul, Carlos Guestrin, James Zou

Large language models (LLMs) are increasingly used in learning algorithms, evaluations, and optimization tasks. Recent studies have shown that using LLM-based optimizers to automatically optimize model prompts, demonstra…

Language ModelingLanguage Modellingmodel

Training Learned Optimizers with Randomly Initialized Learned Optimizers

2021-01-14 · Luke Metz, C. Daniel Freeman, Niru Maheswaranathan, Jascha Sohl-Dickstein

Learned optimizers are increasingly effective, with performance exceeding that of hand designed optimizers such as Adam~\citep{kingma2014adam} on specific tasks \citep{metz2019understanding}. Despite the potential gains …

Judging Adam: Studying the Performance of Optimization Methods on ML4SE Tasks

2023-03-06 · Dmitry Pasechnyuk, Anton Prazdnichnykh, Mikhail Evtikhiev, Timofey Bryksin

Solving a problem with a deep learning model requires researchers to optimize the loss function with a certain optimization method. The research community has developed more than a hundred different optimizers, yet there…

Deep Learning

Optimizer Amalgamation

2022-03-12 · ICLR 2022 4 · Tianshu Huang, Tianlong Chen, Sijia Liu, Shiyu Chang 외

Selecting an appropriate optimizer for a given problem is of major interest for researchers and practitioners. Many analytical optimizers have been proposed using a variety of theoretical and empirical approaches; howeve…