On January 1821, 2019 the Center of Mathematical Sciences and Applications will be hosting a workshop on the Geometric Analysis Approach to AI.
This workshop will focus on the theoretic foundations of AI, especially various methods in Deep Learning. The topics will cover the relationship between deep learning and optimal transportation theory, DL and information geometry, DL Learning and information bottle neck and renormalization theory, DL and manifold embedding and so on. Furthermore, the recent advancements, novel methods, and real world applications of Deep Learning will also be reported and discussed.
The workshop will take place from January 18th to January 23rd, 2019. In the first four days, from January 18th to January 21, the speakers will give short courses; On the 22nd and 23rd, the speakers will give conference representations. This workshop is organized by Xianfeng Gu and ShingTung Yau.
The workshop will be held in room G10 of the CMSA, located at 20 Garden Street, Cambridge, MA.
For a list of lodging options convenient to the Center, please visit our recommended lodgings page.
Speakers:
Friday, Jan. 18  
TIME  SPEAKER  INSTITUTION  TALK TITLE 
8:309:00  Breakfast  
9:0010:00  Eric Xing  Carnegie Mellon University  
10:0011:00am  Jiajun Wu  Massachusetts Institute
of Technology 
Physical Scene Understanding with Compositional Structure 
11:0011:30am  Coffee  
11:3012:30pm  Tomaso Poggio  Massachusetts Institute of Technology  Three puzzles in the theory of Deep Learning 
12:30 2:00pm  Lunch  
2:003:00pm  Vivienne Sze  Massachusetts Institute of Technology  Enabling Efficient Processing of Deep Neural Networks 
3:004:00pm  Xianfeng
David Gu

Stony Brook University  GAN, Optimal Transport and MongeAmpere Equation 
4:004:30pm  Coffee 
Saturday, Jan. 19  
TIME  SPEAKER  INSTITUTION  TALK TITLE 
8:309:00am  Breakfast  
9:0010:00am  Johannes SchmidtHieber  University of Twente  From network sparsity to statistical guarantees 
10:0011:00am  Steven Skiena  Stony Brook University  Word and Graph Embeddings, with Applications 
11:0011:30am  Coffee  
11:3012:30pm  Guy Bresler  Massachusetts Institute
of Technology 
Reducibility and Computational Lower Bounds for some HighDimensional Statistics Problems 
12:302:00pm  Lunch  
2:003:00pm  Yingnian Wu  UCLA  A representational theory of grid cells 
3:004:00pm  Francesco Orabona  Boston University  Parameterfree Machine Learning through Coin Betting 
4:004:30pm  Coffee  
4:305:30pm  Tina
EliassiRad 
Northeastern University  Graph Distance from the Topological View of Nonbacktracking Cycles 
Sunday, Jan. 20
No talks Sunday due to inclement weather.
Monday, Jan. 21  
TIME  SPEAKER  INSTITUTION  TALK TITLE 
8:309:00am  Breakfast  
9:0010:00am  Cengiz Pehlevan  Harvard  A similaritybased normative theory of biologicallyplausible learning in neural networks
Slides available upon request 
10:0011:00am  Brian Kulis  Boston University  SmallVariance Asymptotics for LargeScale Learning 
11:0011:30am  Coffee  
11:3012:30pm  Minh Hoai Nguyen  Stony Brook University  Slides 
12:302:00pm  Lunch  
2:003:00pm  Zhiwei
(Tony) Qin 
DiDi Research America  Reinforcement Learning with Applications in Ridesharing and Transportation 
3:004:00pm  Gangqiang Xia  Morgan Stanley  Alternative Data and Machine Learning in Fixed Income Modeling 
4:004:30pm  Coffee  
4:305:30pm  Zhu, Juhua  Argus Investment
Management 
The Application of Machine Learning in Quantitative Trading 
Tuesday, Jan. 22  
TIME  SPEAKER  INSTITUTION  TALK TITLE 
8:309:00am  Breakfast  
9:0010:00am  Kate Saenko  Boston University  Adaptive Deep Learning for Visual Understanding 
10:0011:00am  Na Lei  Dalian University of Technology  Tropical Geometry, OMT and Neural Network 
11:0011:30am  Coffee  
11:3012:30pm  Sarah Adel Bargal  Boston University  Grounding Deep Models of Visual Data 
12:302:00pm  Lunch  
2:003:00pm  Alan Yuille  Johns Hopkins University  
3:004:00pm  Donghui Yan  UMass Dartmouth  Random projection forests 
4:004:30pm  Coffee  
4:305:30pm  Yun Raymond Fu  Northeastern University 