Bridging Lifelong and Multi-Task Representation Learning via Algorithm and Complexity Measure
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914132943437824 |
|---|---|
| author | Wang, Zhi Zhang, Chicheng Vinayak, Ramya Korlakai |
| author_facet | Wang, Zhi Zhang, Chicheng Vinayak, Ramya Korlakai |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_01847 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Bridging Lifelong and Multi-Task Representation Learning via Algorithm and Complexity Measure Wang, Zhi Zhang, Chicheng Vinayak, Ramya Korlakai Machine Learning 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. |
| title | Bridging Lifelong and Multi-Task Representation Learning via Algorithm and Complexity Measure |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2511.01847 |