UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Probabilistic Active Meta-Learning

Kaddour, J; Sæmundsson, S; Deisenroth, MP; (2020) Probabilistic Active Meta-Learning. In: Larochelle, H and Ranzato, M and Hadsell, R and Balcan, M-F and Lin, H-T, (eds.) Advances in Neural Information Processing Systems 33 pre-proceedings (NeurIPS 2020). NeurIPS Proceedings: Virtual conference. (In press). Green open access

[thumbnail of NeurIPS-2020-probabilistic-active-meta-learning-Paper.pdf]
NeurIPS-2020-probabilistic-active-meta-learning-Paper.pdf - Published version

Download (3MB) | Preview


Data-efficient learning algorithms are essential in many practical applications where data collection is expensive, e.g., in robotics due to the wear and tear. To address this problem, meta-learning algorithms use prior experience about tasks to learn new, related tasks efficiently. Typically, a set of training tasks is assumed given or randomly chosen. However, this setting does not take into account the sequential nature that naturally arises when training a model from scratch in real-life: how do we collect a set of training tasks in a data-efficient manner? In this work, we introduce task selection based on prior experience into a meta-learning algorithm by conceptualizing the learner and the active meta-learning setting using a probabilistic latent variable model. We provide empirical evidence that our approach improves data-efficiency when compared to strong baselines on simulated robotic experiments.

Type: Proceedings paper
Title: Probabilistic Active Meta-Learning
Event: Neural Information Processing Systems 2020
Open access status: An open access version is available from UCL Discovery
Publisher version: https://proceedings.neurips.cc/paper/2020
Language: English
Additional information: This version is the version of record. For information on re-use, please refer to the publisher’s terms and conditions.
UCL classification: UCL
UCL > Provost and Vice Provost Offices
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10120832
Downloads since deposit
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item