LightLDA: Big Topic Models on Modest Compute Clusters

Dec 04, 2014

Jinhui Yuan, Fei Gao, Qirong Ho, Wei Dai, Jinliang Wei, Xun Zheng, Eric P. Xing, Tie-Yan Liu, Wei-Ying Ma

Dec 04, 2014

Jinhui Yuan, Fei Gao, Qirong Ho, Wei Dai, Jinliang Wei, Xun Zheng, Eric P. Xing, Tie-Yan Liu, Wei-Ying Ma

**Click to Read Paper and Get Code**

SurfelWarp: Efficient Non-Volumetric Single View Dynamic Reconstruction

Apr 30, 2019

Wei Gao, Russ Tedrake

Apr 30, 2019

Wei Gao, Russ Tedrake

* RSS 2018. The video and source code are available on https://sites.google.com/view/surfelwarp/home

**Click to Read Paper and Get Code**

FilterReg: Robust and Efficient Probabilistic Point-Set Registration using Gaussian Filter and Twist Parameterization

Nov 26, 2018

Wei Gao, Russ Tedrake

Probabilistic point-set registration methods have been gaining more attention for their robustness to noise, outliers and occlusions. However, these methods tend to be much slower than the popular iterative closest point (ICP) algorithms, which severely limits their usability. In this paper, we contribute a novel probabilistic registration method that achieves state-of-the-art robustness as well as substantially faster computational performance than modern ICP implementations. This is achieved using a rigorous yet computationally-efficient probabilistic formulation. Point-set registration is cast as a maximum likelihood estimation and solved using the EM algorithm. We show that with a simple augmentation, the E step can be formulated as a filtering problem, allowing us to leverage advances in efficient Gaussian filtering methods. We also propose a customized permutohedral filter for improved efficiency while retaining sufficient accuracy for our task. Additionally, we present a simple and efficient twist parameterization that generalizes our method to the registration of articulated and deformable objects. For articulated objects, the complexity of our method is almost independent of the Degrees Of Freedom (DOFs), which makes it highly efficient even for high DOF systems. The results demonstrate the proposed method consistently outperforms many competitive baselines on a variety of registration tasks.
Nov 26, 2018

Wei Gao, Russ Tedrake

* The video demo and source code are on https://sites.google.com/view/filterreg/home

**Click to Read Paper and Get Code**

Optical Mapping Near-eye Three-dimensional Display with Correct Focus Cues

May 24, 2017

Wei Cui, Liang Gao

May 24, 2017

Wei Cui, Liang Gao

* 5 pages, 6 figures, 2 tables, short article for Optics Letters

**Click to Read Paper and Get Code**

AUC (area under ROC curve) is an important evaluation criterion, which has been popularly used in many learning tasks such as class-imbalance learning, cost-sensitive learning, learning to rank, etc. Many learning approaches try to optimize AUC, while owing to the non-convexity and discontinuousness of AUC, almost all approaches work with surrogate loss functions. Thus, the consistency of AUC is crucial; however, it has been almost untouched before. In this paper, we provide a sufficient condition for the asymptotic consistency of learning approaches based on surrogate loss functions. Based on this result, we prove that exponential loss and logistic loss are consistent with AUC, but hinge loss is inconsistent. Then, we derive the $q$-norm hinge loss and general hinge loss that are consistent with AUC. We also derive the consistent bounds for exponential loss and logistic loss, and obtain the consistent bounds for many surrogate loss functions under the non-noise setting. Further, we disclose an equivalence between the exponential surrogate loss of AUC and exponential surrogate loss of accuracy, and one straightforward consequence of such finding is that AdaBoost and RankBoost are equivalent.

**Click to Read Paper and Get Code**
Great successes of deep neural networks have been witnessed in various real applications. Many algorithmic and implementation techniques have been developed, however, theoretical understanding of many aspects of deep neural networks is far from clear. A particular interesting issue is the usefulness of dropout, which was motivated from the intuition of preventing complex co-adaptation of feature detectors. In this paper, we study the Rademacher complexity of different types of dropout, and our theoretical results disclose that for shallow neural networks (with one or none hidden layer) dropout is able to reduce the Rademacher complexity in polynomial, whereas for deep neural networks it can amazingly lead to an exponential reduction of the Rademacher complexity.

* 20 pagea

* 20 pagea

**Click to Read Paper and Get Code*** Artificial Intelligence 203:1-18 2013

* 35 pages

**Click to Read Paper and Get Code**

Exploring Graph Learning for Semi-Supervised Classification Beyond Euclidean Data

Apr 23, 2019

Xiang Gao, Wei Hu, Zongming Guo

Apr 23, 2019

Xiang Gao, Wei Hu, Zongming Guo

**Click to Read Paper and Get Code**

* 5 pages,6 figures,1 table,conference

**Click to Read Paper and Get Code**

Structure Learning of Deep Neural Networks with Q-Learning

Oct 31, 2018

Guoqiang Zhong, Wencong Jiao, Wei Gao

Oct 31, 2018

Guoqiang Zhong, Wencong Jiao, Wei Gao

**Click to Read Paper and Get Code**

Learning from Synthetic Data for Crowd Counting in the Wild

Mar 08, 2019

Qi Wang, Junyu Gao, Wei Lin, Yuan Yuan

Recently, counting the number of people for crowd scenes is a hot topic because of its widespread applications (e.g. video surveillance, public security). It is a difficult task in the wild: changeable environment, large-range number of people cause the current methods can not work well. In addition, due to the scarce data, many methods suffer from over-fitting to a different extent. To remedy the above two problems, firstly, we develop a data collector and labeler, which can generate the synthetic crowd scenes and simultaneously annotate them without any manpower. Based on it, we build a large-scale, diverse synthetic dataset. Secondly, we propose two schemes that exploit the synthetic data to boost the performance of crowd counting in the wild: 1) pretrain a crowd counter on the synthetic data, then finetune it using the real data, which significantly prompts the model's performance on real data; 2) propose a crowd counting method via domain adaptation, which can free humans from heavy data annotations. Extensive experiments show that the first method achieves the state-of-the-art performance on four real datasets, and the second outperforms our baselines. The dataset and source code are available at https://gjy3035.github.io/GCC-CL/.
Mar 08, 2019

Qi Wang, Junyu Gao, Wei Lin, Yuan Yuan

* Accepted by CVPR2019

**Click to Read Paper and Get Code**

Reinforcement Learning Based Argument Component Detection

Feb 21, 2017

Yang Gao, Hao Wang, Chen Zhang, Wei Wang

Feb 21, 2017

Yang Gao, Hao Wang, Chen Zhang, Wei Wang

**Click to Read Paper and Get Code**

This paper considers generalized linear models using rule-based features, also referred to as rule ensembles, for regression and probabilistic classification. Rules facilitate model interpretation while also capturing nonlinear dependences and interactions. Our problem formulation accordingly trades off rule set complexity and prediction accuracy. Column generation is used to optimize over an exponentially large space of rules without pre-generating a large subset of candidates or greedily boosting rules one by one. The column generation subproblem is solved using either integer programming or a heuristic optimizing the same objective. In experiments involving logistic and linear regression, the proposed methods obtain better accuracy-complexity trade-offs than existing rule ensemble algorithms. At one end of the trade-off, the methods are competitive with less interpretable benchmark models.

* Published in the Proceedings of the 36th International Conference on Machine Learning (ICML), PMLR 97:6687-6696, 2019. 17 pages, 7 figures

* Published in the Proceedings of the 36th International Conference on Machine Learning (ICML), PMLR 97:6687-6696, 2019. 17 pages, 7 figures

**Click to Read Paper and Get Code**
kPAM: KeyPoint Affordances for Category-Level Robotic Manipulation

Mar 15, 2019

Lucas Manuelli, Wei Gao, Peter Florence, Russ Tedrake

Mar 15, 2019

Lucas Manuelli, Wei Gao, Peter Florence, Russ Tedrake

* First two authors contributed equally. The video and supplemental material is available on https://sites.google.com/view/kpam

**Click to Read Paper and Get Code**

On the Resistance of Nearest Neighbor to Random Noisy Labels

Sep 13, 2018

Wei Gao, Bin-Bin Yang, Zhi-Hua Zhou

Nearest neighbor has always been one of the most appealing non-parametric approaches in machine learning, pattern recognition, computer vision, etc. Previous empirical studies partly shows that nearest neighbor is resistant to noise, yet there is a lack of deep analysis. This work presents the finite-sample and distribution-dependent bounds on the consistency of nearest neighbor in the random noise setting. The theoretical results show that, for asymmetric noises, k-nearest neighbor is robust enough to classify most data correctly, except for a handful of examples, whose labels are totally misled by random noises. For symmetric noises, however, k-nearest neighbor achieves the same consistent rate as that of noise-free setting, which verifies the resistance of k-nearest neighbor to random noisy labels. Motivated by the theoretical analysis, we propose the Robust k-Nearest Neighbor (RkNN) approach to deal with noisy labels. The basic idea is to make unilateral corrections to examples, whose labels are totally misled by random noises, and classify the others directly by utilizing the robustness of k-nearest neighbor. We verify the effectiveness of the proposed algorithm both theoretically and empirically.
Sep 13, 2018

Wei Gao, Bin-Bin Yang, Zhi-Hua Zhou

* 35 pages

**Click to Read Paper and Get Code**

Generative Adversarial Networks with Decoder-Encoder Output Noise

Jul 11, 2018

Guoqiang Zhong, Wei Gao, Yongbin Liu, Youzhao Yang

Jul 11, 2018

Guoqiang Zhong, Wei Gao, Yongbin Liu, Youzhao Yang

**Click to Read Paper and Get Code**

Person Transfer GAN to Bridge Domain Gap for Person Re-Identification

Jun 25, 2018

Longhui Wei, Shiliang Zhang, Wen Gao, Qi Tian

Jun 25, 2018

Longhui Wei, Shiliang Zhang, Wen Gao, Qi Tian

* 10 pages, 9 figures; accepted in CVPR 2018

**Click to Read Paper and Get Code**

Modern Physiognomy: An Investigation on Predicting Personality Traits and Intelligence from the Human Face

Apr 26, 2016

Rizhen Qin, Wei Gao, Huarong Xu, Zhanyi Hu

Apr 26, 2016

Rizhen Qin, Wei Gao, Huarong Xu, Zhanyi Hu

**Click to Read Paper and Get Code**

Online dictionary learning for kernel LMS. Analysis and forward-backward splitting algorithm

Jun 22, 2013

Wei Gao, Jie Chen, Cédric Richard, Jianguo Huang

Jun 22, 2013

Wei Gao, Jie Chen, Cédric Richard, Jianguo Huang

**Click to Read Paper and Get Code**

3D Dynamic Point Cloud Denoising via Spatio-temporal Graph Modeling

Apr 28, 2019

Qianjiang Hu, Zehua Wang, Wei Hu, Xiang Gao, Zongming Guo

Apr 28, 2019

Qianjiang Hu, Zehua Wang, Wei Hu, Xiang Gao, Zongming Guo

**Click to Read Paper and Get Code**