Robust Federated Training via Collaborative Machine Teaching using Trusted Instances

May 08, 2019

Yufei Han, Xiangliang Zhang

May 08, 2019

Yufei Han, Xiangliang Zhang

**Click to Read Paper and Get Code**

Optimal Sparse Singular Value Decomposition for High-dimensional High-order Data

Sep 06, 2018

Anru Zhang, Rungang Han

Sep 06, 2018

Anru Zhang, Rungang Han

* 73 pages

**Click to Read Paper and Get Code**

In this paper we consider the problem of grouped variable selection in high-dimensional regression using $\ell_1-\ell_q$ regularization ($1\leq q \leq \infty$), which can be viewed as a natural generalization of the $\ell_1-\ell_2$ regularization (the group Lasso). The key condition is that the dimensionality $p_n$ can increase much faster than the sample size $n$, i.e. $p_n \gg n$ (in our case $p_n$ is the number of groups), but the number of relevant groups is small. The main conclusion is that many good properties from $\ell_1-$regularization (Lasso) naturally carry on to the $\ell_1-\ell_q$ cases ($1 \leq q \leq \infty$), even if the number of variables within each group also increases with the sample size. With fixed design, we show that the whole family of estimators are both estimation consistent and variable selection consistent under different conditions. We also show the persistency result with random design under a much weaker condition. These results provide a unified treatment for the whole family of estimators ranging from $q=1$ (Lasso) to $q=\infty$ (iCAP), with $q=2$ (group Lasso)as a special case. When there is no group structure available, all the analysis reduces to the current results of the Lasso estimator ($q=1$).

* 25 pages

* 25 pages

**Click to Read Paper and Get Code**
GMC: Grid Based Motion Clustering in Dynamic Environment

Feb 25, 2019

Handuo Zhang, Karunasekera Hasith, Han Wang

Feb 25, 2019

Handuo Zhang, Karunasekera Hasith, Han Wang

* 14 pages

**Click to Read Paper and Get Code**

Candidates vs. Noises Estimation for Large Multi-Class Classification Problem

Sep 13, 2018

Lei Han, Yiheng Huang, Tong Zhang

Sep 13, 2018

Lei Han, Yiheng Huang, Tong Zhang

* Published in ICML 2018

**Click to Read Paper and Get Code**

Reinforced dynamics for enhanced sampling in large atomic and molecular systems

Feb 19, 2018

Linfeng Zhang, Han Wang, Weinan E

Feb 19, 2018

Linfeng Zhang, Han Wang, Weinan E

**Click to Read Paper and Get Code**

Multisensory Omni-directional Long-term Place Recognition: Benchmark Dataset and Analysis

Apr 18, 2017

Ashwin Mathur, Fei Han, Hao Zhang

Recognizing a previously visited place, also known as place recognition (or loop closure detection) is the key towards fully autonomous mobile robots and self-driving vehicle navigation. Augmented with various Simultaneous Localization and Mapping techniques (SLAM), loop closure detection allows for incremental pose correction and can bolster efficient and accurate map creation. However, repeated and similar scenes (perceptual aliasing) and long term appearance changes (e.g. weather variations) are major challenges for current place recognition algorithms. We introduce a new dataset Multisensory Omnidirectional Long-term Place recognition (MOLP) comprising omnidirectional intensity and disparity images. This dataset presents many of the challenges faced by outdoor mobile robots and current place recognition algorithms. Using MOLP dataset, we formulate the place recognition problem as a regularized sparse convex optimization problem. We conclude that information extracted from intensity image is superior to disparity image in isolating discriminative features for successful long term place recognition. Furthermore, when these discriminative features are extracted from an omnidirectional vision sensor, a robust bidirectional loop closure detection approach is established, allowing mobile robots to close the loop, regardless of the difference in the direction when revisiting a place.
Apr 18, 2017

Ashwin Mathur, Fei Han, Hao Zhang

* 15 pages

**Click to Read Paper and Get Code**

Pathwise Coordinate Optimization for Sparse Learning: Algorithm and Theory

Feb 09, 2017

Tuo Zhao, Han Liu, Tong Zhang

Feb 09, 2017

Tuo Zhao, Han Liu, Tong Zhang

* Accepted by the Annals of Statistics, 2016+

**Click to Read Paper and Get Code**

Multi-lingual Geoparsing based on Machine Translation

Nov 06, 2015

Xu Chen, Han Zhang, Judith Gelernter

Nov 06, 2015

Xu Chen, Han Zhang, Judith Gelernter

* 7 pages, 4 figures,

**Click to Read Paper and Get Code**

Optimal computational and statistical rates of convergence for sparse nonconvex learning problems

Jan 27, 2015

Zhaoran Wang, Han Liu, Tong Zhang

Jan 27, 2015

Zhaoran Wang, Han Liu, Tong Zhang

* Annals of Statistics 2014, Vol. 42, No. 6, 2164-2201

* Published in at http://dx.doi.org/10.1214/14-AOS1238 the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)

**Click to Read Paper and Get Code**

A Unified Mammogram Analysis Method via Hybrid Deep Supervision

Aug 31, 2018

Rongzhao Zhang, Han Zhang, Albert C. S. Chung

Aug 31, 2018

Rongzhao Zhang, Han Zhang, Albert C. S. Chung

**Click to Read Paper and Get Code**

Structured Local Optima in Sparse Blind Deconvolution

Jun 01, 2018

Yuqian Zhang, Han-Wen Kuo, John Wright

Jun 01, 2018

Yuqian Zhang, Han-Wen Kuo, John Wright

* 66 pages, 6 figures

**Click to Read Paper and Get Code**

An Extreme-Value Approach for Testing the Equality of Large U-Statistic Based Correlation Matrices

Mar 30, 2018

Cheng Zhou, Fang Han, Xinsheng Zhang, Han Liu

Mar 30, 2018

Cheng Zhou, Fang Han, Xinsheng Zhang, Han Liu

* to appear in Bernoulli

**Click to Read Paper and Get Code**

DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics

Dec 31, 2017

Han Wang, Linfeng Zhang, Jiequn Han, Weinan E

Dec 31, 2017

Han Wang, Linfeng Zhang, Jiequn Han, Weinan E

**Click to Read Paper and Get Code**

Sequence-based Multimodal Apprenticeship Learning For Robot Perception and Decision Making

Feb 24, 2017

Fei Han, Xue Yang, Yu Zhang, Hao Zhang

Apprenticeship learning has recently attracted a wide attention due to its capability of allowing robots to learn physical tasks directly from demonstrations provided by human experts. Most previous techniques assumed that the state space is known a priori or employed simple state representations that usually suffer from perceptual aliasing. Different from previous research, we propose a novel approach named Sequence-based Multimodal Apprenticeship Learning (SMAL), which is capable to simultaneously fusing temporal information and multimodal data, and to integrate robot perception with decision making. To evaluate the SMAL approach, experiments are performed using both simulations and real-world robots in the challenging search and rescue scenarios. The empirical study has validated that our SMAL approach can effectively learn plans for robots to make decisions using sequence of multimodal observations. Experimental results have also showed that SMAL outperforms the baseline methods using individual images.
Feb 24, 2017

Fei Han, Xue Yang, Yu Zhang, Hao Zhang

* 8 pages, 6 figures, accepted by ICRA'17

**Click to Read Paper and Get Code**

Local Relation Networks for Image Recognition

Apr 25, 2019

Han Hu, Zheng Zhang, Zhenda Xie, Stephen Lin

Apr 25, 2019

Han Hu, Zheng Zhang, Zhenda Xie, Stephen Lin

**Click to Read Paper and Get Code**

Spatial-Temporal Relation Networks for Multi-Object Tracking

Apr 25, 2019

Jiarui Xu, Yue Cao, Zheng Zhang, Han Hu

Apr 25, 2019

Jiarui Xu, Yue Cao, Zheng Zhang, Han Hu

**Click to Read Paper and Get Code**

**Click to Read Paper and Get Code**

Attribute-Aware Attention Model for Fine-grained Representation Learning

Jan 02, 2019

Kai Han, Jianyuan Guo, Chao Zhang, Mingjian Zhu

Jan 02, 2019

Kai Han, Jianyuan Guo, Chao Zhang, Mingjian Zhu

* Accepted by ACM Multimedia 2018 (Oral)

**Click to Read Paper and Get Code**

Weakly-Supervised Hierarchical Text Classification

Dec 29, 2018

Yu Meng, Jiaming Shen, Chao Zhang, Jiawei Han

Dec 29, 2018

Yu Meng, Jiaming Shen, Chao Zhang, Jiawei Han

* AAAI 2019

**Click to Read Paper and Get Code**