181 citations · 1.7k across the 107 of their papers we have counts for
17 papers · 1 filter
Adaptive Correlated Monte Carlo for Contextual Categorical Sequence Generation
Xinjie Fan, Yizhe Zhang, Zhendong Wang +1
Sequence generation models are commonly refined with reinforcement learning over user-defined metrics. However, high gradient variance hinders the practical use of this method. To…
Recurrent Hierarchical Topic-Guided RNN for Language Generation
Dandan Guo, Bo Chen, Ruiying Lu +1
To simultaneously capture syntax and global semantics from a text corpus, we propose a new larger-context recurrent neural network (RNN) based language model, which extracts recurr…
Meta-Learning without Memorization
Mingzhang Yin, George Tucker, Mingyuan Zhou +2
The ability to learn new concepts with small amounts of data is a critical aspect of intelligence that has proven challenging for deep learning methods. Meta-learning has emerged a…
Weibull Racing Survival Analysis with Competing Events, Left Truncation, and Time-varying Covariates
Quan Zhang, Yanxun Xu, Mei-Cheng Wang +1
We propose Bayesian nonparametric Weibull delegate racing (WDR) for survival analysis with competing events and achieve both model interpretability and flexibility. Utilizing a nat…
ARSM Gradient Estimator for Supervised Learning to Rank
Siamak Zamani Dadaneh, Shahin Boluki, Mingyuan Zhou +1
We propose a new model for supervised learning to rank. In our model, the relevance labels are assumed to follow a categorical distribution whose probabilities are constructed base…
Poisson-Randomized Gamma Dynamical Systems
Aaron Schein, Scott W. Linderman, Mingyuan Zhou +2
This paper presents the Poisson-randomized gamma dynamical system (PRGDS), a model for sequentially observed count tensors that encodes a strong inductive bias toward sparsity and…
Semi-supervised Learning using Adversarial Training with Good and Bad Samples
Wenyuan Li, Zichen Wang, Yuguang Yue +4
In this work, we investigate semi-supervised learning (SSL) for image classification using adversarial training. Previous results have illustrated that generative adversarial netwo…
Thompson Sampling via Local Uncertainty
Zhendong Wang, Mingyuan Zhou
Thompson sampling is an efficient algorithm for sequential decision making, which exploits the posterior uncertainty to address the exploration-exploitation dilemma. There has been…
Semi-Implicit Stochastic Recurrent Neural Networks
Ehsan Hajiramezanali, Arman Hasanzadeh, Nick Duffield +3
Stochastic recurrent neural networks with latent random variables of complex dependency structures have shown to be more successful in modeling sequential data than deterministic d…
Variational Graph Recurrent Neural Networks
Ehsan Hajiramezanali, Arman Hasanzadeh, Nick Duffield +3
Representation learning over graph structured data has been mostly studied in static graph settings while efforts for modeling dynamic graphs are still scant. In this paper, we dev…
Semi-Implicit Graph Variational Auto-Encoders
Arman Hasanzadeh, Ehsan Hajiramezanali, Nick Duffield +3
Semi-implicit graph variational auto-encoder (SIG-VAE) is proposed to expand the flexibility of variational graph auto-encoders (VGAE) to model graph data. SIG-VAE employs a hierar…
Variational Autoencoders for Sparse and Overdispersed Discrete Data
He Zhao, Piyush Rai, Lan Du +2
Many applications, such as text modelling, high-throughput sequencing, and recommender systems, require analysing sparse, high-dimensional, and overdispersed discrete (count-valued…
Convolutional Poisson Gamma Belief Network
Chaojie Wang, Bo Chen, Sucheng Xiao +1
For text analysis, one often resorts to a lossy representation that either completely ignores word order or embeds each word as a low-dimensional dense feature vector. In this pape…
Semi-Implicit Generative Model
Mingzhang Yin, Mingyuan Zhou
To combine explicit and implicit generative models, we introduce semi-implicit generator (SIG) as a flexible hierarchical model that can be trained in the maximum likelihood framew…
Variational Hetero-Encoder Randomized GANs for Joint Image-Text Modeling
Hao Zhang, Bo Chen, Long Tian +2
For bidirectional joint image-text modeling, we develop variational hetero-encoder (VHE) randomized generative adversarial network (GAN), a versatile deep generative model that int…
ARSM: Augment-REINFORCE-Swap-Merge Estimator for Gradient Backpropagation Through Categorical Variables
Mingzhang Yin, Yuguang Yue, Mingyuan Zhou
To address the challenge of backpropagating the gradient through categorical variables, we propose the augment-REINFORCE-swap-merge (ARSM) gradient estimator that is unbiased and h…
Augment-Reinforce-Merge Policy Gradient for Binary Stochastic Policy
Yunhao Tang, Mingzhang Yin, Mingyuan Zhou
Due to the high variance of policy gradients, on-policy optimization algorithms are plagued with low sample efficiency. In this work, we propose Augment-Reinforce-Merge (ARM) polic…