2.2k citations · 10.9k across the 144 of their papers we have counts for
17 papers · 1 filter
Feature Quantization Improves GAN Training
Yang Zhao, Chunyuan Li, Ping Yu +2
The instability in GAN training has been a long-standing problem despite remarkable research efforts. We identify that instability issues stem from difficulties of performing featu…
Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving
Imanol Schlag, Paul Smolensky, Roland Fernandez +3
We incorporate Tensor-Product Representations within the Transformer in order to better support the explicit representation of relation structure. Our Tensor-Product Transformer (T…
Implicit Deep Latent Variable Models for Text Generation
Le Fang, Chunyuan Li, Jianfeng Gao +2
Deep latent variable models (LVM) such as variational auto-encoder (VAE) have recently played an important role in text generation. One key factor is the exploitation of smooth lat…
On the Variance of the Adaptive Learning Rate and Beyond
Liyuan Liu, Haoming Jiang, Pengcheng He +4
The learning rate warmup heuristic achieves remarkable success in stabilizing training, accelerating convergence and improving generalization for adaptive stochastic optimization a…
Model Adaptation via Model Interpolation and Boosting for Web Search Ranking
Jianfeng Gao, Qiang Wu, Chris Burges +5
This paper explores two classes of model adaptation methods for Web search ranking: Model Interpolation and error-driven learning approaches based on a boosting algorithm. The resu…
Towards Amortized Ranking-Critical Training for Collaborative Filtering
Sam Lobel, Chunyuan Li, Jianfeng Gao +1
Collaborative filtering is widely used in modern recommender systems. Recent research shows that variational autoencoders (VAEs) yield state-of-the-art performance by integrating f…
Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing
Hao Fu, Chunyuan Li, Xiaodong Liu +3
Variational autoencoders (VAEs) with an auto-regressive decoder have been applied for many natural language processing (NLP) tasks. The VAE objective consists of two terms, (i) rec…
A User Simulator for Task-Completion Dialogues
Xiujun Li, Zachary C. Lipton, Bhuwan Dhingra +3
Despite widespread interests in reinforcement-learning for task-oriented dialogue systems, several obstacles can frustrate research and development progress. First, reinforcement l…
Combating Reinforcement Learning's Sisyphean Curse with Intrinsic Fear
Zachary C. Lipton, Kamyar Azizzadenesheli, Abhishek Kumar +3
Many practical environments contain catastrophic states that an optimal agent would visit infrequently or never. Even on toy problems, Deep Reinforcement Learning (DRL) agents tend…
ReasoNet: Learning to Stop Reading in Machine Comprehension
Yelong Shen, Po-Sen Huang, Jianfeng Gao +1
Teaching a computer to read and answer general questions pertaining to a document is a challenging yet unsolved problem. In this paper, we describe a novel neural network architect…
BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems
Zachary C. Lipton, Xiujun Li, Jianfeng Gao +3
We present a new algorithm that significantly improves the efficiency of exploration for deep Q-learning agents in dialogue systems. Our agents explore via Thompson sampling, drawi…
Unsupervised Learning of Predictors from Unpaired Input-Output Samples
Jianshu Chen, Po-Sen Huang, Xiaodong He +2
Unsupervised learning is the most challenging problem in machine learning and especially in deep learning. Among many scenarios, we study an unsupervised learning problem of high e…
Stacked Attention Networks for Image Question Answering
Zichao Yang, Xiaodong He, Jianfeng Gao +2
This paper presents stacked attention networks (SANs) that learn to answer natural language questions from images. SANs use semantic representation of a question as query to search…
Recurrent Reinforcement Learning: A Hybrid Approach
Xiujun Li, Lihong Li, Jianfeng Gao +4
Successful applications of reinforcement learning in real-world problems often require dealing with partially observable states. It is in general very challenging to construct and…
End-to-end Learning of LDA by Mirror-Descent Back Propagation over a Deep Architecture
Jianshu Chen, Ji He, Yelong Shen +5
We develop a fully discriminative learning approach for supervised Latent Dirichlet Allocation (LDA) model using Back Propagation (i.e., BP-sLDA), which maximizes the posterior pro…
A Deep Embedding Model for Co-occurrence Learning
Yelong Shen, Ruoming Jin, Jianshu Chen +3
Co-occurrence Data is a common and important information source in many areas, such as the word co-occurrence in the sentences, friends co-occurrence in social networks and product…
Online Classification Using a Voted RDA Method
Tianbing Xu, Jianfeng Gao, Lin Xiao +1
We propose a voted dual averaging method for online classification problems with explicit regularization. This method employs the update rule of the regularized dual averaging (RDA…