paper-with-me

홈 › Papers

Meta-strategy for Learning Tuning Parameters with Guarantees

2021-02-04 · Dimitri Meunier, Pierre Alquier

Online learning methods, like the online gradient algorithm (OGA) and exponentially weighted aggregation (EWA), often depend on tuning parameters that are difficult to set in practice. We consider an online meta-learning scenario, and we propose a meta-strategy to learn these parameters from past tasks. Our strategy is based on the minimization of a regret bound. It allows to learn the initialization and the step size in OGA with guarantees. It also allows to learn the prior or the learning rate in EWA. We provide a regret analysis of the strategy. It allows to identify settings where meta-learning indeed improves on learning each task in isolation.

📄 PDF Abstract BibTeX arXiv:2102.02504

Code (0)

등록된 구현이 없습니다.

Tasks

Meta-Learning

Similar Papers 제목 키워드 기반

Guarantees for Tuning the Step Size using a Learning-to-Learn Approach

2020-06-30 · Xiang Wang, Shuai Yuan, Chenwei Wu, Rong Ge

Choosing the right parameters for optimization algorithms is often the key to their success in practice. Solving this problem using a learning-to-learn approach -- using meta-gradient descent on a meta-objective based on…

Generalization Guarantees on Data-Driven Tuning of Gradient Descent with Langevin Updates

2026-04-13 · Saumya Goyal, Rohith Rongali, Ritabrata Ray, Barnabás Póczos arxiv

We study learning to learn for regression problems through the lens of hyperparameter tuning. We propose the Langevin Gradient Descent Algorithm (LGD), which approximates the mean of the posterior distribution defined by…

Few-Shot Learning

Multi-Teacher Multi-Objective Meta-Learning for Zero-Shot Hyperspectral Band Selection

2024-06-12 · Jie Feng, Xiaojian Zhong, Di Li, Weisheng Dong 외

Band selection plays a crucial role in hyperspectral image classification by removing redundant and noisy bands and retaining discriminative ones. However, most existing deep learning-based methods are aimed at dealing w…

Hyperspectral Image Classificationimage-classificationImage ClassificationMeta-Learning

Bilevel ZOFO: Bridging Parameter-Efficient and Zeroth-Order Techniques for Efficient LLM Fine-Tuning and Meta-Training

2025-02-05 · Reza Shirkavand, Qi He, Peiran Yu, Heng Huang

Fine-tuning pre-trained Large Language Models (LLMs) for downstream tasks using First-Order (FO) optimizers presents significant computational challenges. Parameter-Efficient Fine-Tuning(PEFT) methods have been proposed …

Bilevel Optimizationparameter-efficient fine-tuning

Fine-Tuning Language Models to Know What They Know

2026-02-02 · Sangjun Park, Elliot Meyerson, Xin Qiu, Risto Miikkulainen arxiv

Evaluating true metacognition in Large Language Models (LLMs) is difficult due to biases and heuristics. This paper presents a framework to measure and enhance LLM metacognition while controlling for these biases. A meas…