Geometric Analysis Approach to AI Workshop

Due to inclement weather on Sunday, the second half of the workshop has been moved forward one day. Sunday and Monday’s talks will now take place on Monday and Tuesday. 

On January 18-21, 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 Shing-Tung 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.

Please register here

Speakers: 

Schedule:

Friday, Jan. 18
TIME SPEAKER INSTITUTION TALK  TITLE
8:30-9:00 Breakfast
9:00-10:00 Eric Xing Carnegie Mellon University
10:00-11:00am Jiajun Wu Massachusetts Institute

of Technology

Physical Scene Understanding with Compositional Structure

Slides

Video

11:00-11:30am Coffee
11:30-12:30pm Tomaso Poggio Massachusetts Institute of Technology Three puzzles in the theory of Deep Learning
12:30- 2:00pm Lunch
2:00-3:00pm Vivienne Sze Massachusetts Institute of Technology Enabling Efficient Processing of Deep Neural Networks

Slides

3:00-4:00pm Xianfeng

David Gu

 

Stony Brook University GAN, Optimal Transport and Monge-Ampere Equation

Slides

4:00-4:30pm Coffee

Saturday, Jan. 19
TIME SPEAKER INSTITUTION TALK  TITLE
8:30-9:00am Breakfast
9:00-10:00am Johannes Schmidt-Hieber University of Twente From network sparsity to statistical guarantees

Slides

10:00-11:00am Steven Skiena Stony Brook University Word and Graph Embeddings, with Applications

Slides

11:00-11:30am Coffee
11:30-12:30pm Guy Bresler Massachusetts Institute

of Technology

Reducibility and Computational Lower Bounds for some High-Dimensional Statistics Problems
12:30-2:00pm Lunch
2:00-3:00pm Yingnian Wu UCLA A representational theory of grid cells
3:00-4:00pm Francesco Orabona Boston University Parameter-free Machine Learning through Coin Betting

Slides

4:00-4:30pm Coffee
4:30-5:30pm Tina

Eliassi-Rad

Northeastern University Graph Distance from the Topological View of Non-backtracking Cycles

Slides

Sunday, Jan. 20

No talks Sunday due to inclement weather.

Monday, Jan. 21
TIME SPEAKER INSTITUTION TALK  TITLE
8:30-9:00am Breakfast
9:00-10:00am Cengiz Pehlevan Harvard A similarity-based normative theory of biologically-plausible learning in neural networks

Slides available upon request

10:00-11:00am Brian Kulis Boston University Small-Variance Asymptotics for Large-Scale Learning

Slides

11:00-11:30am Coffee
11:30-12:30pm Minh Hoai Nguyen Stony Brook University Slides
12:30-2:00pm Lunch
2:00-3:00pm Zhiwei

(Tony) Qin

DiDi Research America Reinforcement Learning with Applications in Ridesharing and Transportation
3:00-4:00pm Gangqiang Xia Morgan Stanley Alternative Data and Machine Learning in Fixed Income Modeling
4:00-4:30pm Coffee
4:30-5:30pm Zhu, Juhua Argus Investment

Management

The Application of Machine Learning in Quantitative Trading

Tuesday, Jan. 22
TIME SPEAKER INSTITUTION TALK  TITLE
8:30-9:00am Breakfast
9:00-10:00am Kate Saenko Boston University Adaptive Deep Learning for Visual Understanding

Slides

10:00-11:00am Na Lei  Dalian University of Technology  Tropical Geometry, OMT and Neural Network

Slides

11:00-11:30am Coffee
11:30-12:30pm Sarah Adel Bargal Boston University Grounding Deep Models of Visual Data

Slides

12:30-2:00pm Lunch
2:00-3:00pm Alan Yuille Johns Hopkins University
3:00-4:00pm Donghui Yan UMass Dartmouth Random projection forests

Slides

Video

4:00-4:30pm Coffee
4:30-5:30pm Yun Raymond Fu Northeastern University


Related Posts