research
∙
08/12/2022
Gradient Estimation for Binary Latent Variables via Gradient Variance Clipping
Gradient estimation is often necessary for fitting generative models wit...
share
research
∙
06/14/2022
Probabilistic Conformal Prediction Using Conditional Random Samples
This paper proposes probabilistic conformal prediction (PCP), a predicti...
research
∙
09/24/2021
Optimization-based Causal Estimation from Heterogenous Environments
This paper presents a new optimization approach to causal estimation. Gi...
research
∙
06/11/2020
Probabilistic Best Subset Selection via Gradient-Based Optimization
In high-dimensional statistics, variable selection is an optimization pr...
research
∙
06/11/2020
Probabilistic Best Subset Selection by Gradient-Based Optimization
In high-dimensional statistics, variable selection is an optimization pr...
research
∙
05/21/2020
Pairwise Supervised Hashing with Bernoulli Variational Auto-Encoder and Self-Control Gradient Estimator
Semantic hashing has become a crucial component of fast similarity searc...
research
∙
02/10/2020
Discrete Action On-Policy Learning with Action-Value Critic
Reinforcement learning (RL) in discrete action space is ubiquitous in re...
research
∙
12/09/2019
Meta-Learning without Memorization
The ability to learn new concepts with small amounts of data is a critic...
research
∙
07/29/2019
A Theoretical Case Study of Structured Variational Inference for Community Detection
Mean-field variational inference (MFVI) has been widely applied in large...
research
∙
05/29/2019
Semi-Implicit Generative Model
To combine explicit and implicit generative models, we introduce semi-im...
research
∙
05/04/2019
ARSM: Augment-REINFORCE-Swap-Merge Estimator for Gradient Backpropagation Through Categorical Variables
To address the challenge of backpropagating the gradient through categor...
research
∙
03/13/2019
Augment-Reinforce-Merge Policy Gradient for Binary Stochastic Policy
Due to the high variance of policy gradients, on-policy optimization alg...
research
∙
07/30/2018
ARM: Augment-REINFORCE-Merge Gradient for Discrete Latent Variable Models
To backpropagate the gradients through discrete stochastic layers, we en...
research
∙
05/28/2018