paper-with-me

Papers

Online Control for Meta-optimization

2023-09-21 · NeurIPS 2023 11

Choosing the optimal hyperparameters, including learning rate and momentum, for specific optimization instances is a significant yet non-convex challenge. This makes conventional iterative techniques such as hypergradient descent \cite{baydin2017online} insufficient in obtaining global optimality guarantees. We consider the more general task of meta-optimization -- online learning of the best optimization algorithm given problem instances, and introduce a novel approach based on control theory. We show how meta-optimization can be formulated as an optimal control problem, departing from existing literature that use stability-based methods to study optimization. Our approach leverages convex relaxation techniques in the recently-proposed nonstochastic control framework to overcome the challenge of nonconvexity, and obtains regret guarantees vs. the best offline solution. This guarantees that in meta-optimization, we can learn a method that attains convergence comparable to that of the best optimization method in hindsight from a class of methods.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

A Nonstochastic Control Approach to Optimization

2023-01-19 · Xinyi Chen, Elad Hazan

Selecting the best hyperparameters for a particular optimization instance, such as the learning rate and momentum, is an important but nonconvex problem. As a result, iterative optimization methods such as hypergradient …

MPC of Uncertain Nonlinear Systems with Meta-Learning for Fast Adaptation of Neural Predictive Models

2024-04-18 · Jiaqi Yan, Ankush Chakrabarty, Alisa Rupenyan, John Lygeros

In this paper, we consider the problem of reference tracking in uncertain nonlinear systems. A neural State-Space Model (NSSM) is used to approximate the nonlinear system, where a deep encoder network learns the nonlinea…

Meta-LearningModel Predictive Control

Online Learning of a Memory for Learning Rates

2017-09-20 · Franziska Meier, Daniel Kappler, Stefan Schaal

The promise of learning to learn for robotics rests on the hope that by extracting some information about the learning process itself we can speed up subsequent similar learning tasks. Here, we introduce a computationall…

Meta-Learning

Towards a modeling, optimization and predictive control framework for fed-batch metabolic cybergenetics

2023-02-04 · Sebastián Espinel-Ríos, Bruno Morabito, Johannes Pohlodek, Katja Bettenbrock 외

Biotechnology offers many opportunities for the sustainable manufacturing of valuable products. The toolbox to optimize bioprocesses includes \textit{extracellular} process elements such as the bioreactor design and mode…

Cultural Vocal Bursts Intensity PredictionModel Predictive Control

LaGO: Latent Action Guidance for Online Reinforcement Learning

2026-06-23 · Kuan-Yen Liu, Ren-Jyun Huang, Ti-Rong Wu arxiv

Large language models (LLMs) have shown strong potential for planning and sequential decision-making, but prior work often relies on using them as direct controllers, which requires precise action generation and can be u…

Reinforcement Learning