Multi-task and Lifelong Learning of Kernels

2016-02-21 · Anastasia Pentina, Shai Ben-David

We consider a problem of learning kernels for use in SVM classification in the multi-task and lifelong scenarios and provide generalization bounds on the error of a large margin classifier. Our results show that, under mild conditions on the family of kernels used for learning, solving several related tasks simultaneously is beneficial over single task learning. In particular, as the number of observed tasks grows, assuming that in the considered family of kernels there exists one that yields low approximation error on all tasks, the overhead associated with learning such a kernel vanishes and the complexity converges to that of learning when this good kernel is given to the learner.

📄 PDF Abstract BibTeX arXiv:1602.06531

Code (0)

등록된 구현이 없습니다.

Tasks

General ClassificationGeneralization BoundsLifelong learning

Methods 이 논문이 사용한 방법론

SVM A Support Vector Machine, or SVM, is a non-parametric supervised learning model. For non-linear classification and regression, they utilise the kernel trick to map inputs…

Lifelong Learning with Output Kernels

2018-01-01 · ICLR 2018 1 · Keerthiram Murugesan, Jaime Carbonell

Lifelong learning poses considerable challenges in terms of effectiveness (minimizing prediction errors for all tasks) and overall computational tractability for real-time performance. This paper addresses continuous li…

Lifelong learning

Incremental learning for audio classification with Hebbian Deep Neural Networks

2026-04-20 · Riccardo Casciotti, Francesco De Santis, Alberto Antonietti, Annamaria Mesaros arxiv

The ability of humans for lifelong learning is an inspiration for deep learning methods and in particular for continual learning. In this work, we apply Hebbian learning, a biologically inspired learning process, to soun…

Incremental Learning Audio Classification Continual Learning

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 learning Multi-Armed Bandits

Regularize, Expand and Compress: Multi-task based Lifelong Learning via NonExpansive AutoML

2019-03-20 · Jie Zhang, Junting Zhang, Shalini Ghosh, Dawei Li 외

Lifelong learning, the problem of continual learning where tasks arrive in sequence, has been lately attracting more attention in the computer vision community. The aim of lifelong learning is to develop a system that ca…

AutoML Continual Learning Lifelong learning

Sharing Lifelong Reinforcement Learning Knowledge via Modulating Masks

2023-05-18 · Saptarshi Nath, Christos Peridis, Eseoghene Ben-Iwhiwhu, Xinran Liu 외

Lifelong learning agents aim to learn multiple tasks sequentially over a lifetime. This involves the ability to exploit previous knowledge when learning new tasks and to avoid forgetting. Modulating masks, a specific typ…

Lifelong learning reinforcement-learning Reinforcement Learning