Publications

Cache-Efficient Dynamic Programming MDP Solver

Jaël Champagne Gareau

Guillaume Gosset

Éric Beaudry

Vladimir Makarenkov

2023-01-01

European Conference on Artificial Intelligence (publié)

doi.org

Can Forward Gradient Match Backpropagation?

Louis Fournier

Stephane Rivaud

Eugene Belilovsky

Michael Eickenberg

Edouard Oyallon

Forward Gradients - the idea of using directional derivatives in forward differentiation mode - have recently been shown to be utilizable fo… (voir plus)r neural network training while avoiding problems generally associated with backpropagation gradient computation, such as locking and memorization requirements. The cost is the requirement to guess the step direction, which is hard in high dimensions. While current solutions rely on weighted averages over isotropic guess vector distributions, we propose to strongly bias our gradient guesses in directions that are much more promising, such as feedback obtained from small, local auxiliary networks. For a standard computer vision neural network, we conduct a rigorous study systematically covering a variety of combinations of gradient targets and gradient guesses, including those previously presented in the literature. We find that using gradients obtained from a local loss as a candidate direction drastically improves on random noise in Forward Gradient methods.

2023-01-01

ICML (publié)

doi.org

openreview.net

Can AI Read the Minds of Corporate Executives?

Nicolas Chapados

Zhenzhen Fan

Ruslan Goyenko

Issam Hadj Laradji

Fred Liu

Chengyu Zhang

2023-01-01

SSRN Electronic Journal (publié)

doi.org

Can Workers Meaningfully Consent to Workplace Wellbeing Technologies?

Shreya Chowdhary

Anna Kawakami

Jina Suh

Mary L Gray

Alexandra Olteanu

Koustuv Saha

2023-01-01

FAccT (publié)

doi.org

arxiv.org

A circulating proteome-informed prognostic model of COVID-19 disease activity that relies on 1 routinely available clinical laboratories 2

William Ma

Antoine Soulé

Karine Tremblay

Simon Rousseau

Amin Emad

Abstract

2023-01-01

(publié)

www.semanticscholar.org

A circulating proteome-informed prognostic model of COVID-19 disease activity that relies on 1 routinely available clinical laboratories 2

William Ma

Antoine Soulé

Karine Tremblay

Simon Rousseau

Amin Emad

Abstract

Combining Spatial and Temporal Abstraction in Planning for Better Generalization

Mingde Zhao

Safa Alver

Harm van Seijen

Romain Laroche

Doina Precup

Yoshua Bengio

2023-01-01

arXiv.org (prépublication)

doi.org

Conditional Flow Matching: Simulation-Free Dynamic Optimal Transport

Alexander Tong

Yanlei Zhang

Kilian FATRAS

2023-01-01

arXiv.org (prépublication)

doi.org

Conditional Flow Matching: Simulation-Free Dynamic Optimal Transport

Alexander Tong

Yanlei Zhang

Kilian FATRAS

Continuous normalizing ﬂows (CNFs) are an attractive generative modeling technique, but they have thus far been held back by limitations i… (voir plus)n their simulation-based maximum likelihood training. In this paper, we introduce a new technique called conditional ﬂow matching (CFM), a simulation-free training objective for CNFs. CFM features a stable regression objective like that used to train the stochastic ﬂow in diffusion models but enjoys the efﬁcient inference of deterministic ﬂow models. In contrast to both diffusion models and prior CNF training algorithms, our CFM objec-tive does not require the source distribution to be Gaussian or require evaluation of its density. Based on this new objective, we also introduce optimal transport CFM (OT-CFM), which creates simpler ﬂows that are more stable to train and lead to faster inference, as evaluated in our experiments. Training CNFs with CFM improves results on a variety of conditional and unconditional generation tasks such as inferring single cell dynamics, unsupervised image translation, and Schr ¨ odinger bridge inference. Code is available at https://github.com/atong01/ conditional-flow-matching .

2023-01-01

arXiv.org (prépublication)

doi.org

Constant Memory Attentive Neural Processes

Leo Feng

Frederick Tung

Hossein Hajimirsadeghi

Yoshua Bengio

Mohamed Osama Ahmed

2023-01-01

arXiv.org (prépublication)

doi.org