Bridging Lifelong and Multi-Task Representation Learning via Algorithm and Complexity Measure
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Representation LearningMulti-Task LearningSimilar Papers 제목 키워드 기반
Bridging Graph Network to Lifelong Learning with Feature Interaction
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 ClassificationProvable Lifelong Learning of Representations
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 learningNearly Minimax Algorithms for Linear Bandits with Shared Representation
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
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 BanditsGuidance Graph Optimization for Lifelong Multi-Agent Path Finding
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