paper-with-me

Papers

Efficient Meta Subspace Optimization

2021-10-28 · Yoni Choukroun, Michael Katz

Subspace optimization methods have the attractive property of reducing large-scale optimization problems to a sequence of low-dimensional subspace optimization problems. However, existing subspace optimization frameworks adopt a fixed update policy of the subspace and therefore appear to be sub-optimal. In this paper, we propose a new \emph{Meta Subspace Optimization} (MSO) framework for large-scale optimization problems, which allows to determine the subspace matrix at each optimization iteration. In order to remain invariant to the optimization problem's dimension, we design an \emph{efficient} meta optimizer based on very low-dimensional subspace optimization coefficients, inducing a rule-based method that can significantly improve performance. Finally, we design and analyze a reinforcement learning (RL) procedure based on the subspace optimization dynamics whose learnt policies outperform existing subspace optimization methods.

📄 PDF Abstract BibTeX arXiv:2110.14920

Code (1)

yoniLc/Meta-Subspace-Optimization 공식 구현 pytorch

Tasks

Reinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Large-Scale Riemannian Meta-Optimization via Subspace Adaptation

2025-01-25 · Peilin Yu, Yuwei Wu, Zhi Gao, Xiaomeng Fan 외

Riemannian meta-optimization provides a promising approach to solving non-linear constrained optimization problems, which trains neural networks as optimizers to perform optimization on Riemannian manifolds. However, exi…

Bi-Level Meta-Learning for Few-Shot Domain Generalization

2023-01-01 · CVPR 2023 1 · Xiaorong Qin, Xinhang Song, Shuqiang Jiang

The goal of few-shot learning is to learn the generalizability from seen to unseen data with only a few samples. Most previous few-shot learning focus on learning generalizability within particular domains. However, …

Domain GeneralizationFew-Shot LearningMeta-Learning

A Sample Complexity Separation between Non-Convex and Convex Meta-Learning

2020-02-25 · ICML 2020 1 · Nikunj Saunshi, Yi Zhang, Mikhail Khodak, Sanjeev Arora

One popular trend in meta-learning is to learn from many training tasks a common initialization for a gradient-based method that can be used to solve a new task with few samples. The theory of meta-learning is still in i…

Meta-LearningRepresentation Learning

Black-box Prompt Tuning with Subspace Learning

2023-05-04 · Yuanhang Zheng, Zhixing Tan, Peng Li, Yang Liu

Black-box prompt tuning employs derivative-free optimization algorithms to learn prompts within low-dimensional subspaces rather than back-propagating through the network of Large Language Models (LLMs). Recent studies r…

Meta-Learning

Multi-Subspace Structured Meta-Learning

2021-09-29 · Weisen Jiang, James Kwok, Yu Zhang

Meta-learning aims to extract meta-knowledge from historical tasks to accelerate learning on new tasks. A critical challenge in meta-learning is to handle task heterogeneity, i.e., tasks lie in different distributions. U…

Meta-Learning