Zobrazeno 1 - 10
of 52
pro vyhledávání: '"Albergo, Michael S."'
We propose an algorithm, termed the Non-Equilibrium Transport Sampler (NETS), to sample from unnormalized probability distributions. NETS can be viewed as a variant of annealed importance sampling (AIS) based on Jarzynski's equality, in which the sto
Externí odkaz:
http://arxiv.org/abs/2410.02711
Generative models based on dynamical transport of measure, such as diffusion models, flow matching models, and stochastic interpolants, learn an ordinary or stochastic differential equation whose trajectories push initial conditions from a known base
Externí odkaz:
http://arxiv.org/abs/2406.07507
Autor:
Abbott, Ryan, Albergo, Michael S., Boyda, Denis, Hackett, Daniel C., Kanwar, Gurtej, Romero-López, Fernando, Shanahan, Phiala E., Urban, Julian M.
Normalizing flows are machine-learned maps between different lattice theories which can be used as components in exact sampling and inference schemes. Ongoing work yields increasingly expressive flows on gauge fields, but it remains an open question
Externí odkaz:
http://arxiv.org/abs/2404.11674
Autor:
Abbott, Ryan, Albergo, Michael S., Boyda, Denis, Hackett, Daniel C., Kanwar, Gurtej, Romero-López, Fernando, Shanahan, Phiala E., Urban, Julian M.
Scale separation is an important physical principle that has previously enabled algorithmic advances such as multigrid solvers. Previous work on normalizing flows has been able to utilize scale separation in the context of scalar field theories, but
Externí odkaz:
http://arxiv.org/abs/2404.10819
Autor:
Chen, Yifan, Goldstein, Mark, Hua, Mengjian, Albergo, Michael S., Boffi, Nicholas M., Vanden-Eijnden, Eric
We propose a framework for probabilistic forecasting of dynamical systems based on generative modeling. Given observations of the system state over time, we formulate the forecasting problem as sampling from the conditional distribution of the future
Externí odkaz:
http://arxiv.org/abs/2403.13724
Autor:
Ma, Nanye, Goldstein, Mark, Albergo, Michael S., Boffi, Nicholas M., Vanden-Eijnden, Eric, Xie, Saining
We present Scalable Interpolant Transformers (SiT), a family of generative models built on the backbone of Diffusion Transformers (DiT). The interpolant framework, which allows for connecting two distributions in a more flexible way than standard dif
Externí odkaz:
http://arxiv.org/abs/2401.08740
These lecture notes provide an introduction to recent advances in generative modeling methods based on the dynamical transportation of measures, by means of which samples from a simple base measure are mapped to samples from a target measure of inter
Externí odkaz:
http://arxiv.org/abs/2310.11232
Autor:
Albergo, Michael S., Goldstein, Mark, Boffi, Nicholas M., Ranganath, Rajesh, Vanden-Eijnden, Eric
Generative models inspired by dynamical transport of measure -- such as flows and diffusions -- construct a continuous-time map between two probability densities. Conventionally, one of these is the target density, only accessible through samples, wh
Externí odkaz:
http://arxiv.org/abs/2310.03725
Given a set of $K$ probability densities, we consider the multimarginal generative modeling problem of learning a joint distribution that recovers these densities as marginals. The structure of this joint distribution should identify multi-way corres
Externí odkaz:
http://arxiv.org/abs/2310.03695
Autor:
Abbott, Ryan, Albergo, Michael S., Botev, Aleksandar, Boyda, Denis, Cranmer, Kyle, Hackett, Daniel C., Kanwar, Gurtej, Matthews, Alexander G. D. G., Racanière, Sébastien, Razavi, Ali, Rezende, Danilo J., Romero-López, Fernando, Shanahan, Phiala E., Urban, Julian M.
Applications of normalizing flows to the sampling of field configurations in lattice gauge theory have so far been explored almost exclusively in two space-time dimensions. We report new algorithmic developments of gauge-equivariant flow architecture
Externí odkaz:
http://arxiv.org/abs/2305.02402