Keynote Speakers

  • Game Theoretic Understanding of Social Economic System Design [Slides]
Speaker: Prof. Xiaotie Deng, Shanghai Jiaotong University

Dr. Xiaotie Deng got his BSc from Tsinghua University, MSc from Chinese Academy of Sciences, and PhD from Stanford University. He is currently a Zhiyuan Chair Professor of Shanghai Jiaotong University. He taught in the past at University of Liverpool, City University of Hong Kong, and York University. Before that, he was an NSERC international fellow at Simon Fraser University. Deng's current research focuses on algorithmic game theory, with applications to Internet Economics. His works cover online algorithms, parallel algorithms, and combinatorial optimization. He is an ACM fellow for his contribution to the interface of algorithms and game theory.


We study competition, cooperation and coordination in system design over the Internet, focusing on strategic behaviour of participating agents in response to system algorithms and protocols of learning, regulating and controlling. We discuss algorithmic game theoretical methodology and approaches to address such challenges.

  • Distributed Machine Learning on Big Data [Link]
Speaker: Prof. Eric P. Xing, Carnegie Mellon University

Dr. Eric Xing is a Professor of Machine Learning in the School of Computer Science at Carnegie Mellon University, and the director of the CMU Center for Machine Learning and Health under the Pittsburgh Health Data Alliance. His principal research interests lie in the development of machine learning and statistical methodology; especially for solving problems involving automated learning, reasoning, and decision-making in high-dimensional, multimodal, and dynamic possible worlds in social and biological systems. Professor Xing received his Ph.D. in Computer Science from UC Berkeley. He is an associate editor of the Annals of Applied Statistics (AOAS), the Journal of American Statistical Association (JASA), the IEEE Transaction of Pattern Analysis and Machine Intelligence (PAMI), the PLoS Journal of Computational Biology, and an Action Editor of the Machine Learning Journal (MLJ), the Journal of Machine Learning Research (JMLR). He is a member of the DARPA Information Science and Technology (ISAT) Advisory Group, and a Program Chair of ICML 2014.


In many modern applications such as web-scale content extraction via topic models, genome-wide association mapping via sparse regression, and image understanding via deep neural networks, one needs to handle large-scale machine learning (ML) problems running on distributed system with multiple CPU/GPU cores or computer nodes. A key issue of both theoretical and engineering interest in building effective distributed systems are the so-called “bridging models”, which specify how parallel workers should be coordinated. In this talk, I discuss the unique challenges and opportunities in designing these models for ML, and present a number of new bridging models including the stale synchronous parallel (SSP) model, the structure-aware parallel (SAP) model that can speed up both data- and model- parallel ML programs at orders of magnitudes over the conventional models used in existing distributed systems, and enjoy provable correctness guarantee. I will introduce the Petuum framework built on such models for Distributed Machine Learning on Big Data that offers low cost and fast solutions to industry-scale problems in text modeling (topic model with 1M topics), personalized genome medicine (sparse regression on 100M dimensions), and computer vision (deep neural network with billions of parameters).

Invited Speakers

  • Making the Impossible Possible: Randomized Machine Learning Algorithms for Big Data [Slides]
Speaker: Dr. Rong Jin, Alibaba

Dr. Rong Jin is currently a Principle Engineer at Alibaba. He was a professor in the Department of Computer Science and Engineering at Michigan State University. His research is focused on statistical machine learning and its application to big data analysis. He has published over 200 technical papers, most in prestigious conferences (NIPS, ICML, KDD, SIGIR, CVPR, ICCV) and journals (TPAMI, JMLR, JML, and TKDD). Dr. Jin has served as area chair for NIPS 2013 and SIGIR 2008, and associate editor for TPAMI and ACM KDD. He received his Ph.D in Computer Science from Carnegie Mellon University in 2003, NSF Career Award in 2006 and the best student paper award from COLT in 2012.


We are continuing to encounter an explosive growth in data: the number of web pages grows from 300 million in 1997 to 50 billion in 2013; about 10 billion images are indexed by Google and 6 billion videos are indexed by YouTube; Alibaba’s ecommerce platform receives billions of requests on a daily basis. This data explosion poses a great challenge in data analysis. Randomized algorithms have attracted significant interests in the recent studies of machine learning, mostly due to its computational efficiency. But, on the other hand, the formal limitations of randomized algorithms have been established for various learning tasks, making them less effective in exploiting the massive amount of data that is available to computer programs. In this talk, I will discuss, based on two examples, how to overcome the limitation of randomized machine learning algorithms by exploiting either the side information or prior knowledge of data. We have shown, both theoretically and empirically, that with a slight modification, it is possible to dramatically improve the effectiveness of randomized algorithms for machine learning. I will also introduce the successful cases of applying randomized algorithms in Alibaba.

  • Recent Advances in Deep Learning: Learning Structured, Robust, and Multimodal Deep Models [Slides]
Speaker: Prof. Ruslan Salakhutdinov, University of Toronto

Dr. Ruslan Salakhutdinov received his PhD in machine learning (computer science) from the University of Toronto in 2009. After spending two post-doctoral years at the Massachusetts Institute of Technology Artificial Intelligence Lab, he joined the University of Toronto as an Assistant Professor in the Department of Computer Science and Department of Statistics.

Dr. Salakhutdinov's primary interests lie in statistical machine learning, Deep Learning, probabilistic graphical models, and large-scale optimization. He is an action editor of the Journal of Machine Learning Research and served on the senior programme committee of several learning conferences including NIPS and ICML. He is the recipient of the Early Researcher Award, Connaught New Researcher Award, Alfred P. Sloan Research Fellowship, Microsoft Research Faculty Fellowship, Google Faculty Research Award, and is a Fellow of the Canadian Institute for Advanced Research.


Building intelligent systems that are capable of extracting meaningful representations from high-dimensional data lies at the core of solving many Artificial Intelligence tasks, including visual object recognition, information retrieval, speech perception, and language understanding.

In this talk I will first introduce a broad class of deep learning models and show that they can learn useful hierarchical representations from large volumes of high-dimensional data with applications in information retrieval, object recognition, and speech perception. I will then describe a new class of more complex models that combine deep learning models with structured hierarchical Bayesian models and show how these models can learn a deep hierarchical structure for sharing knowledge across hundreds of visual categories. Finally, I will introduce deep models that are capable of extracting a unified representation that fuses together multiple data modalities. I will discuss models that can generate natural language descriptions (captions) of images, as well as generate images from captions (using attention mechanism). I will show that on several tasks, including modelling images and text, video and sound, these models significantly improve upon many of the existing techniques.

  • Bayesian Deep Learning for Integrated Intelligence: Bridging the Gap between Perception and Inference [Slides]
Speaker: Prof. Dit-Yan Yeung, Hong Kong University of Science and Technology

Dr. Yeung received his BEng degree in electrical engineering and MPhil degree in computer science from the University of Hong Kong (HKU), and PhD degree in computer science from the University of Southern California (USC) in 1989. He started his academic career in the same year as an assistant professor at the Illinois Institute of Technology (IIT) in Chicago. He then joined the Hong Kong University of Science and Technology (HKUST) where he is now a full professor in computer science and engineering.

Dr. Yeung's research interests include computational and statistical approaches to machine learning and artificial intelligence. He is also interested in applying machine learning techniques to computer vision and social computing.


While perception tasks such as visual object recognition and text understanding play an important role in human intelligence, the subsequent tasks that involve inference, reasoning and planning require an even higher level of intelligence. The past few years have seen major advances in many perception tasks using deep learning models. For higher-level inference, however, probabilistic graphical models with their Bayesian nature are still more powerful and flexible. To achieve integrated intelligence that involves both perception and inference, we have been exploring along a research direction, which we call Bayesian deep learning, to tightly integrate deep learning and Bayesian models within a principled probabilistic framework. In this talk, some of our recent work on Bayesian deep learning with various applications in recommendation and representation learning will be presented.