paper-with-me

홈 › Papers

Bridging Lifelong and Multi-Task Representation Learning via Algorithm and Complexity Measure

2025-11-03 · Zhi Wang, Chicheng Zhang, Ramya Korlakai Vinayak arxiv

In lifelong learning, a learner faces a sequence of tasks with shared structure and aims to identify and leverage it to accelerate learning. We study the setting where such structure is captured by a common representation of data. Unlike multi-task learning or learning-to-learn, where tasks are available upfront to learn the representation, lifelong learning requires the learner to make use of its existing knowledge while continually gathering partial information in an online fashion. In this paper, we consider a generalized framework of lifelong representation learning. We propose a simple algorithm that uses multi-task empirical risk minimization as a subroutine and establish a sample complexity bound based on a new notion we introduce--the task-eluder dimension. Our result applies to a wide range of learning problems involving general function classes. As concrete examples, we instantiate our result on classification and regression tasks under noise.

📄 PDF Abstract BibTeX arXiv:2511.01847

Code (0)

등록된 구현이 없습니다.

Tasks

Representation LearningMulti-Task Learning

Similar Papers 제목 키워드 기반

Bridging Graph Network to Lifelong Learning with Feature Interaction

2021-01-01 · Chen Wang, Yuheng Qiu, Sebastian Scherer

Graph neural networks (GNN) are powerful models for many graph-structured tasks. In this paper, we aim to bridge GNN to lifelong learning, which is to overcome the effect of ``catastrophic forgetting" for continuously le…

Graph ClassificationLifelong learningNode Classification

Provable Lifelong Learning of Representations

2021-10-27 · Xinyuan Cao, Weiyang Liu, Santosh S. Vempala

In lifelong learning, tasks (or classes) to be learned arrive sequentially over time in arbitrary order. During training, knowledge from previous tasks can be captured and transferred to subsequent ones to improve sample…

Continual LearningLifelong learning

Nearly Minimax Algorithms for Linear Bandits with Shared Representation

2022-03-29 · Jiaqi Yang, Qi Lei, Jason D. Lee, Simon S. Du

We give novel algorithms for multi-task and lifelong linear bandits with shared representation. Specifically, we consider the setting where we play $M$ linear bandits with dimension $d$, each for $T$ rounds, and these $M…

PAC-Bayesian Lifelong Learning For Multi-Armed Bandits

2022-03-07 · Hamish Flynn, David Reeb, Melih Kandemir, Jan Peters

We present a PAC-Bayesian analysis of lifelong learning. In the lifelong learning problem, a sequence of learning tasks is observed one-at-a-time, and the goal is to transfer information acquired from previous tasks to n…

Lifelong learningMulti-Armed Bandits

Guidance Graph Optimization for Lifelong Multi-Agent Path Finding

2024-02-02 · Yulun Zhang, He Jiang, Varun Bhatt, Stefanos Nikolaidis 외

We study how to use guidance to improve the throughput of lifelong Multi-Agent Path Finding (MAPF). Previous studies have demonstrated that, while incorporating guidance, such as highways, can accelerate MAPF algorithms,…

Multi-Agent Path Finding