Lifelong learning with weighted majority votes

A. Pentina, R. Urner, in:, Neural Information Processing Systems, 2016, pp. 3619–3627.

Download
OA 237.11 KB
OA IST-2017-775-v1+2_supplementary.pdf 185.82 KB
Conference Paper | Published | English
Author
Department
Series Title
Advances in Neural Information Processing Systems
Abstract
Better understanding of the potential benefits of information transfer and representation learning is an important step towards the goal of building intelligent systems that are able to persist in the world and learn over time. In this work, we consider a setting where the learner encounters a stream of tasks but is able to retain only limited information from each encountered task, such as a learned predictor. In contrast to most previous works analyzing this scenario, we do not make any distributional assumptions on the task generating process. Instead, we formulate a complexity measure that captures the diversity of the observed tasks. We provide a lifelong learning algorithm with error guarantees for every observed task (rather than on average). We show sample complexity reductions in comparison to solving every task in isolation in terms of our task complexity measure. Further, our algorithmic framework can naturally be viewed as learning a representation from encountered tasks with a neural network.
Publishing Year
Date Published
2016-12-01
Acknowledgement
This work was in parts funded by the European Research Council under the European Union’s Seventh Framework Programme (FP7/2007-2013)/ERC grant agreement no 308036.
Volume
29
Page
3619-3627
Conference
NIPS: Neural Information Processing Systems
Conference Location
Barcelona, Spain
Conference Date
2016-12-05 – 2016-12-10
IST-REx-ID

Cite this

Pentina A, Urner R. Lifelong learning with weighted majority votes. In: Vol 29. Neural Information Processing Systems; 2016:3619-3627.
Pentina, A., & Urner, R. (2016). Lifelong learning with weighted majority votes (Vol. 29, pp. 3619–3627). Presented at the NIPS: Neural Information Processing Systems, Barcelona, Spain: Neural Information Processing Systems.
Pentina, Anastasia, and Ruth Urner. “Lifelong Learning with Weighted Majority Votes,” 29:3619–27. Neural Information Processing Systems, 2016.
A. Pentina and R. Urner, “Lifelong learning with weighted majority votes,” presented at the NIPS: Neural Information Processing Systems, Barcelona, Spain, 2016, vol. 29, pp. 3619–3627.
Pentina A, Urner R. 2016. Lifelong learning with weighted majority votes. NIPS: Neural Information Processing Systems, Advances in Neural Information Processing Systems, vol. 29. 3619–3627.
Pentina, Anastasia, and Ruth Urner. Lifelong Learning with Weighted Majority Votes. Vol. 29, Neural Information Processing Systems, 2016, pp. 3619–27.
Main File(s)
File Name
Access Level
OA Open Access
Last Uploaded
2018-12-12T10:12:42Z
Access Level
OA Open Access
Last Uploaded
2018-12-12T10:12:43Z


Export

Marked Publications

Open Data IST Research Explorer

Search this title in

Google Scholar