Computational optimal transport: With applications to data science
Optimal transport (OT) theory can be informally described using the words of the French
mathematician Gaspard Monge (1746–1818): A worker with a shovel in hand has to move a …
mathematician Gaspard Monge (1746–1818): A worker with a shovel in hand has to move a …
Prnet: Self-supervised learning for partial-to-partial registration
Y Wang, JM Solomon - Advances in neural information …, 2019 - proceedings.neurips.cc
We present a simple, flexible, and general framework titled Partial Registration Network
(PRNet), for partial-to-partial point cloud registration. Inspired by recently-proposed learning …
(PRNet), for partial-to-partial point cloud registration. Inspired by recently-proposed learning …
Convolutional wasserstein distances: Efficient optimal transportation on geometric domains
This paper introduces a new class of algorithms for optimization problems involving optimal
transportation over geometric domains. Our main contribution is to show that optimal …
transportation over geometric domains. Our main contribution is to show that optimal …
Stochastic control liaisons: Richard sinkhorn meets gaspard monge on a schrodinger bridge
In 1931--1932, Erwin Schrödinger studied a hot gas Gedankenexperiment (an instance of
large deviations of the empirical distribution). Schrödinger's problem represents an early …
large deviations of the empirical distribution). Schrödinger's problem represents an early …
Why neural networks find simple solutions: The many regularizers of geometric complexity
In many contexts, simpler models are preferable to more complex models and the control of
this model complexity is the goal for many methods in machine learning such as …
this model complexity is the goal for many methods in machine learning such as …
Entropic metric alignment for correspondence problems
Many shape and image processing tools rely on computation of correspondences between
geometric domains. Efficient methods that stably extract" soft" matches in the presence of …
geometric domains. Efficient methods that stably extract" soft" matches in the presence of …
Wasserstein propagation for semi-supervised learning
Probability distributions and histograms are natural representations for product ratings, traffic
measurements, and other data considered in many machine learning applications. Thus …
measurements, and other data considered in many machine learning applications. Thus …
Earth mover's distances on discrete surfaces
We introduce a novel method for computing the earth mover's distance (EMD) between
probability distributions on a discrete surface. Rather than using a large linear program with …
probability distributions on a discrete surface. Rather than using a large linear program with …
A variational quantum algorithm for the Feynman-Kac formula
We propose an algorithm based on variational quantum imaginary time evolution for solving
the Feynman-Kac partial differential equation resulting from a multidimensional system of …
the Feynman-Kac partial differential equation resulting from a multidimensional system of …
Statistical optimal transport via factored couplings
We propose a new method to estimate Wasserstein distances and optimal transport plans
between two probability distributions from samples in high dimension. Unlike plug-in rules …
between two probability distributions from samples in high dimension. Unlike plug-in rules …