research
∙
06/11/2023
On Kinetic Optimal Probability Paths for Generative Models
Recent successful generative models are trained by fitting a neural netw...
share
research
∙
02/11/2023
Distributional GFlowNets with Quantile Flows
Generative Flow Networks (GFlowNets) are a new family of probabilistic s...
research
∙
02/07/2023
Riemannian Flow Matching on General Geometries
We propose Riemannian Flow Matching (RFM), a simple yet powerful framewo...
research
∙
12/28/2022
Latent Discretization for Continuous-time Sequence Compression
Neural compression offers a domain-agnostic approach to creating codecs ...
research
∙
10/06/2022
Flow Matching for Generative Modeling
We introduce a new paradigm for generative modeling built on Continuous ...
research
∙
10/04/2022
Neural Conservation Laws: A Divergence-Free Perspective
We investigate the parameterization of deep neural networks that by desi...
research
∙
10/03/2022
Latent State Marginalization as a Low-cost Approach for Improving Exploration
While the maximum entropy (MaxEnt) reinforcement learning (RL) framework...
research
∙
09/06/2022
Unifying Generative Models with GFlowNets
There are many frameworks for deep generative modeling, each often prese...
research
∙
07/11/2022
Matching Normalizing Flows and Probability Paths on Manifolds
Continuous Normalizing Flows (CNFs) are a class of generative models tha...
research
∙
03/14/2022
Semi-Discrete Normalizing Flows through Differentiable Tessellation
Mapping between discrete and continuous distributions is a difficult tas...
research
∙
02/12/2021
Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equations
We perform scalable approximate inference in a recently-proposed family ...
research
∙
12/10/2020
Convex Potential Flows: Universal Probability Distributions with Optimal Transport and Convex Optimization
Flow-based models are powerful tools for designing probabilistic models ...
research
∙
11/09/2020
Self-Tuning Stochastic Optimization with Curvature-Aware Gradient Filtering
Standard first-order stochastic optimization algorithms base their updat...
research
∙
11/09/2020
Neural Spatio-Temporal Point Processes
We propose a new class of parameterizations for spatio-temporal point pr...
research
∙
11/08/2020
Learning Neural Event Functions for Ordinary Differential Equations
The existing Neural ODE formulation relies on an explicit knowledge of t...
research
∙
09/20/2020
"Hey, that's not an ODE": Faster ODE Adjoints with 12 Lines of Code
Neural differential equations may be trained by backpropagating gradient...
research
∙
04/01/2020
SUMO: Unbiased Estimation of Log Marginal Probability for Latent Variable Models
Standard variational lower bounds used to train latent variable models p...
research
∙
01/05/2020
Scalable Gradients for Stochastic Differential Equations
The adjoint sensitivity method scalably computes gradients of solutions ...
research
∙
12/08/2019
Neural Networks with Cheap Differential Operators
Gradients of neural networks can be computed efficiently for any archite...
research
∙
07/08/2019
Latent ODEs for Irregularly-Sampled Time Series
Time series with non-uniform intervals occur in many applications, and a...
research
∙
06/06/2019
Residual Flows for Invertible Generative Modeling
Flow-based generative models parameterize probability distributions thro...
research
∙
10/02/2018
