Portrait de Oleksiy Ostapenko

Oleksiy Ostapenko

ostapeno@mila.quebec
Collaborateur·rice alumni - UdeM
Superviseur⋅e principal⋅e
Laurent Charlin
Sujets de recherche
Apprentissage en ligne
Apprentissage profond
Traitement du langage naturel
Google Scholar

Publications

Sequoia: A Software Framework to Unify Continual Learning Research
Fabrice Normandin
Florian Golemo
Oleksiy Ostapenko
Pau Rodríguez
Matthew Riemer
J. Hurtado
Lucas Cecchi
Khimya Khetarpal
Dominic Zhao
Ryan Lindeborg
Timothee LESORT
David Vázquez
Laurent Charlin
Irina Rish
Massimo Caccia
The field of Continual Learning (CL) seeks to develop algorithms that accumulate knowledge and skills over time through interaction with non… (voir plus)-stationary environments. In practice, a plethora of evaluation procedures (settings) and algorithmic solutions (methods) exist, each with their own potentially disjoint set of assumptions. This variety makes measuring progress in CL difficult. We propose a taxonomy of settings, where each setting is described as a set of assumptions. A tree-shaped hierarchy emerges from this view, where more general settings become the parents of those with more restrictive assumptions. This makes it possible to use inheritance to share and reuse research, as developing a method for a given setting also makes it directly applicable onto any of its children. We instantiate this idea as a publicly available software framework called Sequoia, which features a wide variety of settings from both the Continual Supervised Learning (CSL) and Continual Reinforcement Learning (CRL) domains. Sequoia also includes a growing suite of methods which are easy to extend and customize, in addition to more specialized methods from external libraries. We hope that this new paradigm and its first implementation can help unify and accelerate research in CL. You can help us grow the tree by visiting www.github.com/lebrice/Sequoia.
2021-08-01
ArXiv (prépublication)
doi.org
openreview.net
Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning
Massimo Caccia
Pau Rodríguez
Oleksiy Ostapenko
Fabrice Normandin
Min Lin
Lucas Caccia
Issam Laradji
Irina Rish
Alexandre Lacoste
David Vázquez
Laurent Charlin
Continual learning studies agents that learn from streams of tasks without forgetting previous ones while adapting to new ones. Two recent c… (voir plus)ontinual-learning scenarios have opened new avenues of research. In meta-continual learning, the model is pre-trained to minimize catastrophic forgetting of previous tasks. In continual-meta learning, the aim is to train agents for faster remembering of previous tasks through adaptation. In their original formulations, both methods have limitations. We stand on their shoulders to propose a more general scenario, OSAKA, where an agent must quickly solve new (out-of-distribution) tasks, while also requiring fast remembering. We show that current continual learning, meta-learning, meta-continual learning, and continual-meta learning techniques fail in this new scenario. We propose Continual-MAML, an online extension of the popular MAML algorithm as a strong baseline for this scenario. We empirically show that Continual-MAML is better suited to the new scenario than the aforementioned methodologies, as well as standard continual learning and meta-learning approaches.
2020-12-06
Conference on Neural Information Processing Systems (Accept (poster))
doi.org
arxiv.org