We show that for any convex differentiable loss function, a deep linear network has no spurious local minima as long as it is true for the two layer case. When applied to the quadratic loss, our result immediately implies the powerful result in [Kawaguchi 2016] that there is no spurious local minima in deep linear networks. Further, with the recent work [Zhou and Liang 2018], we can remove all the assumptions in [Kawaguchi 2016]. Our proof is short and elementary. It builds on the recent work of [Laurent and von Brecht 2018] and uses a new rank one perturbation argument.

**Click to Read Paper**
Adversarial adaptive 1-D convolutional neural networks for bearing fault diagnosis under varying working condition

May 09, 2018

Bo Zhang, Wei Li, Jie Hao, Xiao-Li Li, Meng Zhang

May 09, 2018

Bo Zhang, Wei Li, Jie Hao, Xiao-Li Li, Meng Zhang

**Click to Read Paper**

Deep Reinforcement Learning-based Image Captioning with Embedding Reward

Apr 12, 2017

Zhou Ren, Xiaoyu Wang, Ning Zhang, Xutao Lv, Li-Jia Li

Apr 12, 2017

Zhou Ren, Xiaoyu Wang, Ning Zhang, Xutao Lv, Li-Jia Li

**Click to Read Paper**

Hyperbolic Recommender Systems

Sep 05, 2018

Tran Dang Quang Vinh, Yi Tay, Shuai Zhang, Gao Cong, Xiao-Li Li

Sep 05, 2018

Tran Dang Quang Vinh, Yi Tay, Shuai Zhang, Gao Cong, Xiao-Li Li

**Click to Read Paper**

Sparse Recovery with Very Sparse Compressed Counting

Dec 31, 2013

Ping Li, Cun-Hui Zhang, Tong Zhang

Dec 31, 2013

Ping Li, Cun-Hui Zhang, Tong Zhang

**Click to Read Paper**

Large-Scale Multi-Label Learning with Incomplete Label Assignments

Jul 06, 2014

Xiangnan Kong, Zhaoming Wu, Li-Jia Li, Ruofei Zhang, Philip S. Yu, Hang Wu, Wei Fan

Jul 06, 2014

Xiangnan Kong, Zhaoming Wu, Li-Jia Li, Ruofei Zhang, Philip S. Yu, Hang Wu, Wei Fan

**Click to Read Paper**

**Click to Read Paper**

**Click to Read Paper**

* 15pages, 11 figures

**Click to Read Paper**

Exploring Correlations in Multiple Facial Attributes through Graph Attention Network

Oct 22, 2018

Yan Zhang, Li Sun

Oct 22, 2018

Yan Zhang, Li Sun

* 9 pages, 5 figures, summit to AAAI2019

**Click to Read Paper**

A Regressive Convolution Neural network and Support Vector Regression Model for Electricity Consumption Forecasting

Oct 21, 2018

Youshan Zhang, Qi Li

Oct 21, 2018

Youshan Zhang, Qi Li

* Future of Information and Communications Conference (FICC) 2019

**Click to Read Paper**

Effectiveness of Scaled Exponentially-Regularized Linear Units (SERLUs)

Jul 27, 2018

G. Zhang, H. Li

Jul 27, 2018

G. Zhang, H. Li

* 9 pages

**Click to Read Paper**

A Many-Objective Evolutionary Algorithm Based on Decomposition and Local Dominance

Jul 13, 2018

Yingyu Zhang, Yuanzhen Li

Jul 13, 2018

Yingyu Zhang, Yuanzhen Li

* arXiv admin note: substantial text overlap with arXiv:1803.06282, arXiv:1806.10950

**Click to Read Paper**

Webpage Saliency Prediction with Two-stage Generative Adversarial Networks

May 29, 2018

Yu Li, Ya Zhang

May 29, 2018

Yu Li, Ya Zhang

**Click to Read Paper**

**Click to Read Paper**

A Simple Yet Efficient Rank One Update for Covariance Matrix Adaptation

Oct 22, 2017

Zhenhua Li, Qingfu Zhang

Oct 22, 2017

Zhenhua Li, Qingfu Zhang

* 10 pages, 10 figures

**Click to Read Paper**

PSA: A novel optimization algorithm based on survival rules of porcellio scaber

Sep 28, 2017

Yinyan Zhang, Shuai Li

Sep 28, 2017

Yinyan Zhang, Shuai Li

* 3 pages, 4 figures

**Click to Read Paper**

An Optimal Online Method of Selecting Source Policies for Reinforcement Learning

Sep 24, 2017

Siyuan Li, Chongjie Zhang

Sep 24, 2017

Siyuan Li, Chongjie Zhang

**Click to Read Paper**

An Optimal Treatment Assignment Strategy to Evaluate Demand Response Effect

May 02, 2017

Pan Li, Baosen Zhang

May 02, 2017

Pan Li, Baosen Zhang

* A shorter version appeared in Proceedings of the 2016 Allerton Conference

**Click to Read Paper**

Generating ordered list of Recommended Items: a Hybrid Recommender System of Microblog

Nov 27, 2015

Yingzhen Li, Ye Zhang

Precise recommendation of followers helps in improving the user experience and maintaining the prosperity of twitter and microblog platforms. In this paper, we design a hybrid recommender system of microblog as a solution of KDD Cup 2012, track 1 task, which requires predicting users a user might follow in Tencent Microblog. We describe the background of the problem and present the algorithm consisting of keyword analysis, user taxonomy, (potential)interests extraction and item recommendation. Experimental result shows the high performance of our algorithm. Some possible improvements are discussed, which leads to further study.
Nov 27, 2015

Yingzhen Li, Ye Zhang

* 7 pages

**Click to Read Paper**