DeepAI AI Chat
Log In Sign Up

Optimizing Functionals on the Space of Probabilities with Input Convex Neural Networks

by   David Alvarez-Melis, et al.

Gradient flows are a powerful tool for optimizing functionals in general metric spaces, including the space of probabilities endowed with the Wasserstein metric. A typical approach to solving this optimization problem relies on its connection to the dynamic formulation of optimal transport and the celebrated Jordan-Kinderlehrer-Otto (JKO) scheme. However, this formulation involves optimization over convex functions, which is challenging, especially in high dimensions. In this work, we propose an approach that relies on the recently introduced input-convex neural networks (ICNN) to parameterize the space of convex functions in order to approximate the JKO scheme, as well as in designing functionals over measures that enjoy convergence guarantees. We derive a computationally efficient implementation of this JKO-ICNN framework and use various experiments to demonstrate its feasibility and validity in approximating solutions of low-dimensional partial differential equations with known solutions. We also explore the use of our JKO-ICNN approach in high dimensions with an experiment in controlled generation for molecular discovery.


page 17

page 19


Unconditional convergence for discretizations of dynamical optimal transport

The dynamical formulation of optimal transport, also known as Benamou-Br...

Non-asymptotic convergence bounds for Sinkhorn iterates and their gradients: a coupling approach

Computational optimal transport (OT) has recently emerged as a powerful ...

Sliced-Wasserstein Gradient Flows

Minimizing functionals in the space of probability distributions can be ...

The Deep Minimizing Movement Scheme

Solutions of certain partial differential equations (PDEs) are often rep...

Large-Scale Wasserstein Gradient Flows

Wasserstein gradient flows provide a powerful means of understanding and...

Operator-splitting schemes for degenerate conservative-dissipative systems

The theory of Wasserstein gradient flows in the space of probability mea...

Deep learning for gradient flows using the Brezis-Ekeland principle

We propose a deep learning method for the numerical solution of partial ...