Timezone: »

 
Poster
How to Train Your Neural ODE: the World of Jacobian and Kinetic Regularization
Chris Finlay · Joern-Henrik Jacobsen · Levon Nurbekyan · Adam Oberman

Thu Jul 16 06:00 AM -- 06:45 AM & Thu Jul 16 05:00 PM -- 05:45 PM (PDT) @
in Poster Session 41 »

Training neural ODEs on large datasets has not been tractable due to the necessity of allowing the adaptive numerical ODE solver to refine its step size to very small values. In practice this leads to dynamics equivalent to many hundreds or even thousands of layers. In this paper, we overcome this apparent difficulty by introducing a theoretically-grounded combination of both optimal transport and stability regularizations which encourage neural ODEs to prefer simpler dynamics out of all the dynamics that solve a problem well. Simpler dynamics lead to faster convergence and to fewer discretizations of the solver, considerably decreasing wall-clock time without loss in performance. Our approach allows us to train neural ODE-based generative models to the same performance as the unregularized dynamics, with significant reductions in training time. This brings neural ODEs closer to practical relevance in large-scale applications.

Keywords: Generative Models · Unsupervised and Semi-supervised Learning · Unsupervised Learning · Other · Probabilistic Inference - Models and Probabilistic Programming

Author Information

Chris Finlay (McGill University)
Joern-Henrik Jacobsen (Apple Inc.)
Levon Nurbekyan (UCLA)
Adam Oberman (McGill University)

More from the Same Authors