Shooting Schrödinger's Cat

David Lopes Fernandes; Francisco Vargas; Carl Henrik Ek; Neill D. F. Campbell

Back to publications

Shooting Schrödinger's Cat

David Lopes Fernandes, Francisco Vargas, Carl Henrik Ek, Neill D. F. Campbell

Fourth Symposium on Advances in Approximate Bayesian Inference, 2022.

Abstract

We present a variational inference scheme to learn a model that solves the Schrödinger Bridge Problem (SBP). In contrast to previous work, our approach is solver-agnostic and guarantees solutions that respect the prior beyond the first fitting iteration. Having this solution allows us to generate new samples from one of the distributions by first sampling from the other one and then solving the dynamical system. We show that our model is able to learn the transformation between the Gaussian distribution and arbitrary data, as well as learning dynamics that follow a potential function.

Links

Cite this Paper

BibTeX


@InProceedings{publications/shooting-schrödinger’s-cat,
  title = 	 {Shooting Schrödinger's Cat},
  author = 	 {Lopes Fernandes, David and Vargas, Francisco and Ek, Carl Henrik and Campbell, Neill D. F.},
  booktitle = 	 {Fourth Symposium on Advances in Approximate Bayesian Inference},
  year = 	 {2022},
  url = 	 {/publications/shooting-schr%C3%B6dinger-s-cat.html},
  abstract = 	 {We present a variational inference scheme to learn a model that solves the Schrödinger Bridge Problem (SBP). In contrast to previous work, our approach is solver-agnostic and guarantees solutions that respect the prior beyond the first fitting iteration. Having this solution allows us to generate new samples from one of the distributions by first sampling from the other one and then solving the dynamical system. We show that our model is able to learn the transformation between the Gaussian distribution and arbitrary data, as well as learning dynamics that follow a potential function.}
}

Endnote

%0 Conference Paper
%T Shooting Schrödinger's Cat
%A David Lopes Fernandes
%A Francisco Vargas
%A Carl Henrik Ek
%A Neill D. F. Campbell
%B Fourth Symposium on Advances in Approximate Bayesian Inference
%D 2022	
%F publications/shooting-schrödinger’s-cat
%U /publications/shooting-schr%C3%B6dinger-s-cat.html
%X We present a variational inference scheme to learn a model that solves the Schrödinger Bridge Problem (SBP). In contrast to previous work, our approach is solver-agnostic and guarantees solutions that respect the prior beyond the first fitting iteration. Having this solution allows us to generate new samples from one of the distributions by first sampling from the other one and then solving the dynamical system. We show that our model is able to learn the transformation between the Gaussian distribution and arbitrary data, as well as learning dynamics that follow a potential function.

RIS


TY  - CPAPER
TI  - Shooting Schrödinger's Cat
AU  - David Lopes Fernandes
AU  - Francisco Vargas
AU  - Carl Henrik Ek
AU  - Neill D. F. Campbell
BT  - Fourth Symposium on Advances in Approximate Bayesian Inference
DA  - 2022/01/15	
ID  - publications/shooting-schrödinger’s-cat
UR  - /publications/shooting-schr%C3%B6dinger-s-cat.html
AB  - We present a variational inference scheme to learn a model that solves the Schrödinger Bridge Problem (SBP). In contrast to previous work, our approach is solver-agnostic and guarantees solutions that respect the prior beyond the first fitting iteration. Having this solution allows us to generate new samples from one of the distributions by first sampling from the other one and then solving the dynamical system. We show that our model is able to learn the transformation between the Gaussian distribution and arbitrary data, as well as learning dynamics that follow a potential function.
ER  -

APA


Lopes Fernandes, D., Vargas, F., Ek, C.H. & Campbell, N.D.F.. (2022). Shooting Schrödinger's Cat. Fourth Symposium on Advances in Approximate Bayesian Inference Available from /publications/shooting-schr%C3%B6dinger-s-cat.html.