Portrait de Jarrid Rector-Brooks n'est pas disponible

Jarrid Rector-Brooks

jarrid.rector-brooks@mila.quebec
Doctorat - Université de Montréal
Superviseur⋅e principal⋅e
Yoshua Bengio
Co-superviseur⋅e
Sarath Chandar Anbil Parthipan

Publications

Learning GFlowNets from partial episodes for improved convergence and stability
Kanika Madan
Jarrid Rector-Brooks
Maksym Korablyov
Emmanuel Bengio
Moksh J. Jain
Andrei Cristian Nica
Tom Bosc
Yoshua Bengio
Nikolay Malkin
Generative flow networks (GFlowNets) are a family of algorithms for training a sequential sampler of discrete objects under an unnormalized … (voir plus)target density and have been successfully used for various probabilistic modeling tasks. Existing training objectives for GFlowNets are either local to states or transitions, or propagate a reward signal over an entire sampling trajectory. We argue that these alternatives represent opposite ends of a gradient bias-variance tradeoff and propose a way to exploit this tradeoff to mitigate its harmful effects. Inspired by the TD(
2023-01-01
ICML (publié)
doi.org
openreview.net