Neural autoregressive flows
Normalizing flows and autoregressive models have been successfully combined to produce
state-of-the-art results in density estimation, via Masked Autoregressive Flows (MAF)(…
state-of-the-art results in density estimation, via Masked Autoregressive Flows (MAF)(…
A variational perspective on diffusion-based generative models and score matching
… , Jae Hyun Lim, Aaron Courville University of Montreal & Mila {chin-wei.huang, jae.hyun.lim,
aaron.courville}@umontreal.ca … Chin-Wei is supported by the Google PhD fellowship. …
aaron.courville}@umontreal.ca … Chin-Wei is supported by the Google PhD fellowship. …
Riemannian diffusion models
Diffusion models are recent state-of-the-art methods for image generation and likelihood
estimation. In this work, we generalize continuous-time diffusion models to arbitrary …
estimation. In this work, we generalize continuous-time diffusion models to arbitrary …
Two for one: Diffusion models and force fields for coarse-grained molecular dynamics
Coarse-grained (CG) molecular dynamics enables the study of biological processes at
temporal and spatial scales that would be intractable at an atomistic resolution. However, …
temporal and spatial scales that would be intractable at an atomistic resolution. However, …
Neural language modeling by jointly learning syntax and lexicon
We propose a neural language model capable of unsupervised syntactic structure induction.
The model leverages the structure information to form better semantic representations and …
The model leverages the structure information to form better semantic representations and …
R&D, productivity, and market value: An empirical study from high-technology firms
Although prior research has addressed the influence of production activity and research and
development (R&D) on productivity, it is not clear whether production and R&D affect the …
development (R&D) on productivity, it is not clear whether production and R&D affect the …
Bayesian hypernetworks
We study Bayesian hypernetworks: a framework for approximate Bayesian inference in neural
networks. A Bayesian hypernetwork $\h$ is a neural network which learns to transform a …
networks. A Bayesian hypernetwork $\h$ is a neural network which learns to transform a …
Influence of seizures on stroke outcomes: a large multicenter study
Objective: We compared clinical characteristics of seizures at ischemic stroke presentation (SSP)
to seizures during hospitalization post ischemic stroke (SDH), and their impacts on …
to seizures during hospitalization post ischemic stroke (SDH), and their impacts on …
Measurement of tourist hotels׳ productive efficiency, occupancy, and catering service effectiveness using a modified two-stage DEA model in Taiwan
This study develops a modified two-stage model to evaluate productive efficiency, occupancy,
and catering service effectiveness of Taiwan׳s international tourist hotels. The difference …
and catering service effectiveness of Taiwan׳s international tourist hotels. The difference …
vgraph: A generative model for joint community detection and node representation learning
This paper focuses on two fundamental tasks of graph analysis: community detection and
node representation learning, which capture the global and local structures of graphs …
node representation learning, which capture the global and local structures of graphs …