327 citations · 947 across the 25 of their papers we have counts for
25 papers
Divergence-Augmented Policy Optimization
Qing Wang, Yingru Li, Jiechao Xiong +1
In deep reinforcement learning, policy optimization methods need to deal with issues such as function approximation and the reuse of off-policy data. Standard policy gradient metho…
VOL: Towards Optimal Regret in Model-free RL with Nonlinear Function Approximation
Alekh Agarwal, Yujia Jin, Tong Zhang
We study time-inhomogeneous episodic reinforcement learning (RL) under general function approximation and sparse rewards. We design a new algorithm, Variance-weighted Optimistic $Q…
Picasso: A Sparse Learning Library for High Dimensional Data Analysis in R and Python
Jason Ge, Xingguo Li, Haoming Jiang +4
We describe a new library named picasso, which implements a unified framework of pathwise coordinate optimization for a variety of sparse learning problems (e.g., sparse linear reg…
Estimating and Inferring the Maximum Degree of Stimulus-Locked Time-Varying Brain Connectivity Networks
Kean Ming Tan, Junwei Lu, Tong Zhang +1
Neuroscientists have enjoyed much success in understanding brain functions by constructing brain connectivity networks using data collected under highly controlled experimental set…
Dynamic Layer Aggregation for Neural Machine Translation with Routing-by-Agreement
Zi-Yi Dou, Zhaopeng Tu, Xing Wang +3
With the promising progress of deep neural networks, layer aggregation has been used to fuse information across layers in various fields, such as computer vision and machine transl…
Sharp Analysis for Nonconvex SGD Escaping from Saddle Points
Cong Fang, Zhouchen Lin, Tong Zhang
In this paper, we give a sharp analysis for Stochastic Gradient Descent (SGD) and prove that SGD is able to efficiently escape from saddle points and find an -appr…
Finite-Sample Analysis For Decentralized Batch Multi-Agent Reinforcement Learning With Networked Agents
Kaiqing Zhang, Zhuoran Yang, Han Liu +2
Despite the increasing interest in multi-agent reinforcement learning (MARL) in multiple communities, understanding its theoretical foundation has long been recognized as a challen…
A convex formulation for high-dimensional sparse sliced inverse regression
Kean Ming Tan, Zhaoran Wang, Tong Zhang +2
Sliced inverse regression is a popular tool for sufficient dimension reduction, which replaces covariates with a minimal set of their linear combinations without loss of informatio…
Adaptive Sampling Towards Fast Graph Representation Learning
Wenbing Huang, Tong Zhang, Yu Rong +1
Graph Convolutional Networks (GCNs) have become a crucial tool on learning representations of graph vertices. The main challenge of adapting GCNs on large-scale graphs is the scala…
Diffusion Approximations for Online Principal Component Estimation and Global Convergence
Chris Junchi Li, Mengdi Wang, Han Liu +1
In this paper, we propose to adopt the diffusion approximation tools to study the dynamics of Oja's iteration which is an online stochastic gradient descent method for the principa…
Error Compensated Quantized SGD and its Applications to Large-scale Distributed Optimization
Jiaxiang Wu, Weidong Huang, Junzhou Huang +1
Large-scale distributed optimization is of great importance in various applications. For data-parallel based distributed learning, the inter-node gradient communication often becom…
Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents
Kaiqing Zhang, Zhuoran Yang, Han Liu +2
We consider the problem of \emph{fully decentralized} multi-agent reinforcement learning (MARL), where the agents are located at the nodes of a time-varying communication network.…
Neural Stereoscopic Image Style Transfer
Xinyu Gong, Haozhi Huang, Lin Ma +3
Neural style transfer is an emerging technique which is able to endow daily-life images with attractive artistic styles. Previous work has succeeded in applying convolutional neura…
Candidates vs. Noises Estimation for Large Multi-Class Classification Problem
Lei Han, Yiheng Huang, Tong Zhang
This paper proposes a method for multi-class classification problems, where the number of classes K is large. The method, referred to as Candidates vs. Noises Estimation (CANE), se…
Second-Order Methods with Cubic Regularization Under Inexact Information
Saeed Ghadimi, Han Liu, Tong Zhang
In this paper, we generalize (accelerated) Newton's method with cubic regularization under inexact second-order information for (strongly) convex optimization problems. Under mild…
Graphical Nonconvex Optimization for Optimal Estimation in Gaussian Graphical Models
Qiang Sun, Kean Ming Tan, Han Liu +1
We consider the problem of learning high-dimensional Gaussian graphical models. The graphical lasso is one of the most popular methods for estimating Gaussian graphical models. How…
Efficient Distributed Learning with Sparsity
Jialei Wang, Mladen Kolar, Nathan Srebro +1
We propose a novel, efficient approach for distributed sparse learning in high-dimensions, where observations are randomly partitioned across machines. Computationally, at each rou…
Sparse Generalized Eigenvalue Problem: Optimal Statistical Rates via Truncated Rayleigh Flow
Kean Ming Tan, Zhaoran Wang, Han Liu +1
Sparse generalized eigenvalue problem (GEP) plays a pivotal role in a large family of high-dimensional statistical models, including sparse Fisher's discriminant analysis, canonica…
Local Uncertainty Sampling for Large-Scale Multi-Class Logistic Regression
Lei Han, Kean Ming Tan, Ting Yang +1
A major challenge for building statistical models in the big data era is that the available data volume far exceeds the computational capability. A common approach for solving this…
Near-Optimal Stochastic Approximation for Online Principal Component Estimation
Chris Junchi Li, Mengdi Wang, Han Liu +1
Principal component analysis (PCA) has been a prominent tool for high-dimensional data analysis. Online algorithms that estimate the principal component by processing streaming dat…
I-LAMM for Sparse Learning: Simultaneous Control of Algorithmic Complexity and Statistical Error
Jianqing Fan, Han Liu, Qiang Sun +1
We propose a computational framework named iterative local adaptive majorize-minimization (I-LAMM) to simultaneously control algorithmic complexity and statistical error when fitti…
Pathwise Coordinate Optimization for Sparse Learning: Algorithm and Theory
Tuo Zhao, Han Liu, Tong Zhang
The pathwise coordinate optimization is one of the most important computational frameworks for high dimensional convex and nonconvex sparse learning problems. It differs from the c…
Bayesian Model Averaging with Exponentiated Least Square Loss
Dong Dai, Lei Han, Ting Yang +1
The model averaging problem is to average multiple models to achieve a prediction accuracy not much worse than that of the best single model in terms of mean squared error. It is k…
Optimal computational and statistical rates of convergence for sparse nonconvex learning problems
Zhaoran Wang, Han Liu, Tong Zhang
We provide theoretical analysis of the statistical and computational properties of penalized -estimators that can be formulated as the solution to a possibly nonconvex optimizat…