Ji Liu

Lossless CNN Channel Pruning via Gradient Resetting and Convolutional Re-parameterization

Channel pruning (a.k.a. filter pruning) aims to slim down a convolutiona...
07/07/2020 ∙ by Xiaohan Ding, et al. ∙ 0 ∙ share

read it
On Effective Parallelization of Monte Carlo Tree Search

Despite its groundbreaking success in Go and computer games, Monte Carlo...
06/15/2020 ∙ by Anji Liu, et al. ∙ 0 ∙ share

read it
Neural Network Activation Quantization with Bitwise Information Bottlenecks

Recent researches on information bottleneck shed new light on the contin...
06/09/2020 ∙ by Xichuan Zhou, et al. ∙ 0 ∙ share

read it
Proximal Gradient Temporal Difference Learning: Stable Reinforcement Learning with Polynomial Sample Complexity

In this paper, we introduce proximal gradient temporal difference learni...
06/06/2020 ∙ by Bo Liu, et al. ∙ 0 ∙ share

read it
Regularized Off-Policy TD-Learning

We present a novel l_1 regularized off-policy convergent TD-learning met...
06/06/2020 ∙ by Bo Liu, et al. ∙ 0 ∙ share

read it
Data Poisoning Attacks on Federated Machine Learning

Federated machine learning which enables resource constrained node devic...
04/19/2020 ∙ by Gan Sun, et al. ∙ 0 ∙ share

read it
A Private and Finite-Time Algorithm for Solving a Distributed System of Linear Equations

This paper studies a system of linear equations, denoted as Ax = b, whic...
04/09/2020 ∙ by Shripad Gade, et al. ∙ 0 ∙ share

read it
Depth Edge Guided CNNs for Sparse Depth Upsampling

Guided sparse depth upsampling aims to upsample an irregularly sampled s...
03/23/2020 ∙ by Yi Guo, et al. ∙ 12 ∙ share

read it
Stochastic Recursive Momentum for Policy Gradient Methods

In this paper, we propose a novel algorithm named STOchastic Recursive M...
03/09/2020 ∙ by Huizhuo Yuan, et al. ∙ 0 ∙ share

read it
IMRAM: Iterative Matching with Recurrent Attention Memory for Cross-Modal Image-Text Retrieval

Enabling bi-directional retrieval of images and texts is important for u...
03/08/2020 ∙ by Hui Chen, et al. ∙ 8 ∙ share

read it
End-to-end Robustness for Sensing-Reasoning Machine Learning Pipelines

As machine learning (ML) being applied to many mission-critical scenario...
02/28/2020 ∙ by Zhuolin Yang, et al. ∙ 25 ∙ share

read it
MKPipe: A Compiler Framework for Optimizing Multi-Kernel Workloads in OpenCL for FPGA

OpenCL for FPGA enables developers to design FPGAs using a programming m...
02/05/2020 ∙ by Ji Liu, et al. ∙ 0 ∙ share

read it
A novel tree-structured point cloud dataset for skeletonization algorithm evaluation

Curve skeleton extraction from unorganized point cloud is a fundamental ...
01/09/2020 ∙ by Yan Lin, et al. ∙ 0 ∙ share

read it
Stochastic Recursive Variance Reduction for Efficient Smooth Non-Convex Compositional Optimization

Stochastic compositional optimization arises in many important machine l...
12/31/2019 ∙ by Huizhuo Yuan, et al. ∙ 0 ∙ share

read it
ATZSL: Defensive Zero-Shot Recognition in the Presence of Adversaries

Zero-shot learning (ZSL) has received extensive attention recently espec...
10/24/2019 ∙ by Xingxing Zhang, et al. ∙ 0 ∙ share

read it
Hierarchical Prototype Learning for Zero-Shot Recognition

Zero-Shot Learning (ZSL) has received extensive attention and successes ...
10/24/2019 ∙ by Xingxing Zhang, et al. ∙ 0 ∙ share

read it
Learning Sparsity and Quantization Jointly and Automatically for Neural Network Compression via Constrained Optimization

Deep Neural Networks (DNNs) are widely applied in a wide range of usecas...
10/14/2019 ∙ by Haichuan Yang, et al. ∙ 0 ∙ share

read it
Central Server Free Federated Learning over Single-sided Trust Social Networks

Federated learning has become increasingly important for modern machine ...
10/11/2019 ∙ by Chaoyang He, et al. ∙ 0 ∙ share

read it
An Interactive Control Approach to 3D Shape Reconstruction

The ability to accurately reconstruct the 3D facets of a scene is one of...
10/07/2019 ∙ by Bipul Islam, et al. ∙ 9 ∙ share

read it
Global Sparse Momentum SGD for Pruning Very Deep Neural Networks

Deep Neural Network (DNN) is powerful but computationally expensive and ...
09/27/2019 ∙ by Xiaohan Ding, et al. ∙ 0 ∙ share

read it
PINE: Universal Deep Embedding for Graph Nodes via Partial Permutation Invariant Set Functions

Graph node embedding aims at learning a vector representation for all no...
09/25/2019 ∙ by Shupeng Gui, et al. ∙ 0 ∙ share

read it
DeepSqueeze: Decentralization Meets Error-Compensated Compression

Communication is a key bottleneck in distributed training. Recently, an ...
07/17/2019 ∙ by Hanlin Tang, et al. ∙ 0 ∙ share

read it
DeepSqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compression

Communication is a key bottleneck in distributed training. Recently, an ...
07/17/2019 ∙ by Hanlin Tang, et al. ∙ 0 ∙ share

read it
Stochastic Convergence Results for Regularized Actor-Critic Methods

In this paper, we present a stochastic convergence proof, under suitable...
07/13/2019 ∙ by Wesley Suttle, et al. ∙ 0 ∙ share

read it
A Communication-Efficient Multi-Agent Actor-Critic Algorithm for Distributed Reinforcement Learning

This paper considers a distributed reinforcement learning problem in whi...
07/06/2019 ∙ by Yixuan Lin, et al. ∙ 0 ∙ share

read it
DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compression

A standard approach in large scale machine learning is distributed stoch...
05/15/2019 ∙ by Hanlin Tang, et al. ∙ 0 ∙ share

read it
A Multi-Agent Off-Policy Actor-Critic Algorithm for Distributed Reinforcement Learning

This paper extends off-policy reinforcement learning to the multi-agent ...
03/15/2019 ∙ by Wesley Suttle, et al. ∙ 0 ∙ share

read it
Optimal Projection Guided Transfer Hashing for Image Retrieval

Recently, learning to hash has been widely studied for image retrieval t...
03/01/2019 ∙ by Ji Liu, et al. ∙ 0 ∙ share

read it
SCEF: A Support-Confidence-aware Embedding Framework for Knowledge Graph Refinement

Knowledge graph (KG) refinement mainly aims at KG completion and correct...
02/18/2019 ∙ by Yu Zhao, et al. ∙ 0 ∙ share

read it
Adversarially Trained Model Compression: When Robustness Meets Efficiency

The robustness of deep models to adversarial attacks has gained signific...
02/10/2019 ∙ by Shupeng Gui, et al. ∙ 15 ∙ share

read it
Decentralized Online Learning: Take Benefits from Others' Data without Sharing Your Own to Track Global Trend

Decentralized Online Learning (online learning in decentralized networks...
01/29/2019 ∙ by Yawei Zhao, et al. ∙ 24 ∙ share

read it
Monocular 3D Pose Recovery via Nonconvex Sparsity with Theoretical Analysis

For recovering 3D object poses from 2D images, a prevalent method is to ...
12/29/2018 ∙ by Jianqiao Wangni, et al. ∙ 24 ∙ share

read it
Consensus and Disagreement of Heterogeneous Belief Systems in Influence Networks

Recently, an opinion dynamics model has been proposed to describe a netw...
12/12/2018 ∙ by Mengbin Ye, et al. ∙ 0 ∙ share

read it
ECC: Energy-Constrained Deep Neural Network Compression via a Bilinear Regression Model

Many DNN-enabled vision applications constantly operate under severe ene...
12/05/2018 ∙ by Haichuan Yang, et al. ∙ 0 ∙ share

read it
Distributed Learning of Average Belief Over Networks Using Sequential Observations

This paper addresses the problem of distributed learning of average beli...
11/19/2018 ∙ by Kaiqing Zhang, et al. ∙ 0 ∙ share

read it
Stochastic Primal-Dual Method for Empirical Risk Minimization with O(1) Per-Iteration Complexity

Regularized empirical risk minimization problem with linear predictor ap...
11/03/2018 ∙ by Conghui Tan, et al. ∙ 0 ∙ share

read it
Dantzig Selector with an Approximately Optimal Denoising Matrix and its Application to Reinforcement Learning

Dantzig Selector (DS) is widely used in compressed sensing and sparse le...
11/02/2018 ∙ by Bo Liu, et al. ∙ 0 ∙ share

read it
P-MCGS: Parallel Monte Carlo Acyclic Graph Search

Recently, there have been great interests in Monte Carlo Tree Search (MC...
10/28/2018 ∙ by Chen Yu, et al. ∙ 0 ∙ share

read it
Distributed Learning over Unreliable Networks

Most of today's distributed machine learning systems assume reliable ne...
10/17/2018 ∙ by Hanlin Tang, et al. ∙ 0 ∙ share

read it
Revisit Batch Normalization: New Understanding from an Optimization View and a Refinement via Composition Optimization

Batch Normalization (BN) has been used extensively in deep learning to a...
10/15/2018 ∙ by Xiangru Lian, et al. ∙ 0 ∙ share

read it
Parametrized Deep Q-Networks Learning: Reinforcement Learning with Discrete-Continuous Hybrid Action Space

Most existing deep reinforcement learning (DRL) frameworks consider eith...
10/10/2018 ∙ by Jiechao Xiong, et al. ∙ 0 ∙ share

read it
Proximal Online Gradient is Optimum for Dynamic Regret

In online learning, the dynamic regret metric chooses the reference (opt...
10/08/2018 ∙ by Yawei Zhao, et al. ∙ 0 ∙ share

read it
Fully Implicit Online Learning

Regularized online learning is widely used in machine learning. In this ...
09/25/2018 ∙ by Chaobing Song, et al. ∙ 8 ∙ share

read it
TStarBots: Defeating the Cheating Level Builtin AI in StarCraft II in the Full Game

Starcraft II (SCII) is widely considered as the most challenging Real Ti...
09/19/2018 ∙ by Peng Sun, et al. ∙ 10 ∙ share

read it
Stochastically Controlled Stochastic Gradient for the Convex and Non-convex Composition problem

In this paper, we consider the convex and non-convex composition problem...
09/06/2018 ∙ by Liu Liu, et al. ∙ 0 ∙ share

read it
Marginal Policy Gradients for Complex Control

Many complex domains, such as robotics control and real-time strategy (R...
06/13/2018 ∙ by Carson Eisenach, et al. ∙ 0 ∙ share

read it
End-to-End Learning of Energy-Constrained Deep Neural Networks

Deep Neural Networks (DNN) are increasingly deployed in highly energy-co...
06/12/2018 ∙ by Haichuan Yang, et al. ∙ 0 ∙ share

read it
GESF: A Universal Discriminative Mapping Mechanism for Graph Representation Learning

Graph embedding is a central problem in social network analysis and many...
05/28/2018 ∙ by Shupeng Gui, et al. ∙ 0 ∙ share

read it
Parallel Computation of PDFs on Big Spatial Data Using Spark

We consider big spatial data, which is typically produced in scientific ...
05/08/2018 ∙ by Ji Liu, et al. ∙ 0 ∙ share

read it
Learning Simple Thresholded Features with Sparse Support Recovery

The thresholded feature has recently emerged as an extremely efficient, ...
04/16/2018 ∙ by Zhangyang Wang, et al. ∙ 0 ∙ share

read it

Ji Liu

Featured Co-authors