Proceedings of the 30th International Conference on Machine Learning, PMLR 28(1):507-515, 2013.
Abstract
The problem of learning multiple consecutive tasks, known as lifelong learning, is of great importance to the creation of intelligent, general-purpose, and flexible machines. In this paper, we develop a method for online multi-task learning in the lifelong learning setting. The proposed Efficient Lifelong Learning Algorithm (ELLA) maintains a sparsely shared basis for all task models, transfers knowledge from the basis to learn each new task, and refines the basis over time to maximize performance across all tasks. We show that ELLA has strong connections to both online dictionary learning for sparse coding and state-of-the-art batch multi-task learning methods, and provide robust theoretical performance guarantees. We show empirically that ELLA yields nearly identical performance to batch multi-task learning while learning tasks sequentially in three orders of magnitude (over 1,000x) less time.
@InProceedings{pmlr-v28-ruvolo13,
title = {{ELLA}: An Efficient Lifelong Learning Algorithm},
author = {Paul Ruvolo and Eric Eaton},
booktitle = {Proceedings of the 30th International Conference on Machine Learning},
pages = {507--515},
year = {2013},
editor = {Sanjoy Dasgupta and David McAllester},
volume = {28},
number = {1},
series = {Proceedings of Machine Learning Research},
address = {Atlanta, Georgia, USA},
month = {17--19 Jun},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v28/ruvolo13.pdf},
url = {http://proceedings.mlr.press/v28/ruvolo13.html},
abstract = {The problem of learning multiple consecutive tasks, known as lifelong learning, is of great importance to the creation of intelligent, general-purpose, and flexible machines. In this paper, we develop a method for online multi-task learning in the lifelong learning setting. The proposed Efficient Lifelong Learning Algorithm (ELLA) maintains a sparsely shared basis for all task models, transfers knowledge from the basis to learn each new task, and refines the basis over time to maximize performance across all tasks. We show that ELLA has strong connections to both online dictionary learning for sparse coding and state-of-the-art batch multi-task learning methods, and provide robust theoretical performance guarantees. We show empirically that ELLA yields nearly identical performance to batch multi-task learning while learning tasks sequentially in three orders of magnitude (over 1,000x) less time.}
}
%0 Conference Paper
%T ELLA: An Efficient Lifelong Learning Algorithm
%A Paul Ruvolo
%A Eric Eaton
%B Proceedings of the 30th International Conference on Machine Learning
%C Proceedings of Machine Learning Research
%D 2013
%E Sanjoy Dasgupta
%E David McAllester
%F pmlr-v28-ruvolo13
%I PMLR
%J Proceedings of Machine Learning Research
%P 507--515
%U http://proceedings.mlr.press
%V 28
%N 1
%W PMLR
%X The problem of learning multiple consecutive tasks, known as lifelong learning, is of great importance to the creation of intelligent, general-purpose, and flexible machines. In this paper, we develop a method for online multi-task learning in the lifelong learning setting. The proposed Efficient Lifelong Learning Algorithm (ELLA) maintains a sparsely shared basis for all task models, transfers knowledge from the basis to learn each new task, and refines the basis over time to maximize performance across all tasks. We show that ELLA has strong connections to both online dictionary learning for sparse coding and state-of-the-art batch multi-task learning methods, and provide robust theoretical performance guarantees. We show empirically that ELLA yields nearly identical performance to batch multi-task learning while learning tasks sequentially in three orders of magnitude (over 1,000x) less time.
TY - CPAPER
TI - ELLA: An Efficient Lifelong Learning Algorithm
AU - Paul Ruvolo
AU - Eric Eaton
BT - Proceedings of the 30th International Conference on Machine Learning
PY - 2013/02/13
DA - 2013/02/13
ED - Sanjoy Dasgupta
ED - David McAllester
ID - pmlr-v28-ruvolo13
PB - PMLR
SP - 507
DP - PMLR
EP - 515
L1 - http://proceedings.mlr.press/v28/ruvolo13.pdf
UR - http://proceedings.mlr.press/v28/ruvolo13.html
AB - The problem of learning multiple consecutive tasks, known as lifelong learning, is of great importance to the creation of intelligent, general-purpose, and flexible machines. In this paper, we develop a method for online multi-task learning in the lifelong learning setting. The proposed Efficient Lifelong Learning Algorithm (ELLA) maintains a sparsely shared basis for all task models, transfers knowledge from the basis to learn each new task, and refines the basis over time to maximize performance across all tasks. We show that ELLA has strong connections to both online dictionary learning for sparse coding and state-of-the-art batch multi-task learning methods, and provide robust theoretical performance guarantees. We show empirically that ELLA yields nearly identical performance to batch multi-task learning while learning tasks sequentially in three orders of magnitude (over 1,000x) less time.
ER -
Ruvolo, P. & Eaton, E.. (2013). ELLA: An Efficient Lifelong Learning Algorithm. Proceedings of the 30th International Conference on Machine Learning, in PMLR 28(1):507-515
This site last compiled Tue, 14 Nov 2017 21:10:07 +0000