activity
20132023
most citedMASS: Masked Sequence to Sequence Pre-training for Language Generation

578 citations · 2.7k across the 91 of their papers we have counts for

collaborators
Showing stat.MLShow all

6 papers · 1 filter

stat.ML2022

TD3 with Reverse KL Regularizer for Offline Reinforcement Learning from Mixed Datasets

Yuanying Cai, Chuheng Zhang, Li Zhao +6

We consider an offline reinforcement learning (RL) setting where the agent need to learn from a dataset collected by rolling out multiple behavior policies. There are two challenge…

stat.ML2020

Learning Causal Semantic Representation for Out-of-Distribution Prediction

Chang Liu, Xinwei Sun, Jindong Wang +5

Conventional supervised learning methods, especially deep ones, are found to be sensitive to out-of-distribution (OOD) examples, largely because the learned representation mixes th…

stat.ML2018

Differential Equations for Modeling Asynchronous Algorithms

Li He, Qi Meng, Wei Chen +2

Asynchronous stochastic gradient descent (ASGD) is a popular parallel optimization algorithm in machine learning. Most theoretical analysis on ASGD take a discrete view and prove u…

stat.ML2018

Train Feedfoward Neural Network with Layer-wise Adaptive Rate via Approximating Back-matching Propagation

Huishuai Zhang, Wei Chen, Tie-Yan Liu

Stochastic gradient descent (SGD) has achieved great success in training deep neural network, where the gradient is computed through back-propagation. However, the back-propagated…

stat.ML2018

-SGD: Optimizing ReLU Neural Networks in its Positively Scale-Invariant Space

Qi Meng, Shuxin Zheng, Huishuai Zhang +3

It is well known that neural networks with rectified linear units (ReLU) activation functions are positively scale-invariant. Conventional algorithms like stochastic gradient desce…

stat.ML201718 cited

Convergence Analysis of Distributed Stochastic Gradient Descent with Shuffling

Qi Meng, Wei Chen, Yue Wang +2

When using stochastic gradient descent to solve large-scale machine learning problems, a common practice of data processing is to shuffle the training data, partition the data acro…