This workshop will focus on dramatic advances in representation and learning taking place in natural language processing, speech and vision.  For instance, deep learning can be thought of as a method that combines the tasks of finding a classifier (which we can think of as the top layer of the deep net) with the task of learning a representation (namely, the representation computed at the last-but-one layer).

Developing a theory for such empirical work is an exciting quest, especially since the empirical work draws upon non-convex optimization.  The workshop will draw a mix of theorists and practitioners, and the following is a list of sample issues that will be discussed:  (a) Which models for representation make more sense than
others, and why? (In other words, what patterns in data are they capturing, and how are those patterns useful?)  (b) What is an analog of generalization theory for representation learning?  Can it lead to a theory of transfer learning to new distributions of inputs?  (c) How can we design algorithms for representation learning with provable guarantees?  What progress has already been made, and what lessons can we draw from it?  (d) How can we learn representations that combine probabilities and logic?

Visit the schedule page for the archived videos.

Invited Participants

Pieter Abbeel (UC Berkeley), Jake Abernethy (University of Michigan), Sanjeev Arora (Princeton University), Kamyar Azizzadenesheli (UC Irvine), Nina Balcan (Carnegie Mellon University), Peter Bartlett (UC Berkeley), Misha Belkin (Ohio State University), Shai Ben-David (University of Waterloo), Jeff Bilmes (University of Washington), Leon Bottou (Facebook AI Research), Joan Bruna (UC Berkeley), Moses Charikar (Stanford University), Yejin Choi (University of Washington), Trevor Darrell (UC Berkeley), Adnan Darwiche (UCLA), Sanjoy Dasgupta (UC San Diego), Hal Daume (University of Maryland at College Park), Chris Dyer (Carnegie Mellon University), Reza Eghbali (University of Washington), Justin Eldridge (Ohio State University), Ali Farhadi (University of Washington), Maryam Fazel (University of Washington), Rob Fergus (New York University), Dylan Foster (Cornell University), Rong Ge (Duke University), Kevin Gimpel (TTI-Chicago), Amir Globerson (Tel Aviv University), Kristen Grauman (University of Texas at Austin), Tom Griffiths (UC Berkeley), Abhinav Gupta (Carnegie Mellon University), Hamed Hassani (ETH Zurich), Elad Hazan (ETH Zurich), Daniel Hsu (Columbia University), Prateek Jain (Microsoft Research India), Mike Jordan (UC Berkeley), Sham Kakade (University of Washington), Ravi Kannan (Microsoft Research India), Amin Karbasi (Yale University), Adam Klivans (University of Texas at Austin), Andreas Krause (ETH Zurich), Shrinu Kushagra (University of Waterloo), Yann LeCun (New York University), Yingyu Liang (Princeton University), Mike Luby (Qualcomm Technologies, Inc.), Tengyu Ma (Princeton University), Chris Manning (Stanford University), Cheng Mao (Massachusetts Institute of Technology), Marina Meila (University of Washington), Ankur Moitra (MIT), Shay Moran (Technion), Rob Nowak (University of Wisconsin-Madison), Bruno Olshausen (UC Berkeley), Christos Papadimitriou (UC Berkeley), Luis Rademacher (Ohio State University), Maithra Raghu (Cornell University and Google Inc.), Anup Rao (Georgia Institute of Technology), Ben Recht (UC Berkeley), Philippe Rigollet (Massachusetts Institute of Technology), Andrej Risteski (Princeton University), Daniel Roy (University of Toronto), Karolina Roy (University of Cambridge), Ruslan Salakhutdinov (Carnegie Mellon University), Shai Shalev-Shwartz (The Hebrew University of Jerusalem), Ohad Shamir (Weizmann Institute), Kevin Shi (Columbia University), Noah Smith (University of Washington), Mahdi Soltanolkotabi (University of Southern California), Nathan Srebro Bartom (Toyota Technological Institute at Chicago), Karthik Sridharan (Cornell University), Xiaorui Sun (Columbia University), Matus Telgarsky (UIUC), Josh Tenenbaum (MIT), Ambuj Tewari (University of Michigan), Chris Tosh (UC San Diego), Ruth Urner (Max Planck Institute for Intelligent Systems, Tuebingen), Greg Valiant (Stanford University), Santosh Vempala (Georgia Institute of Technology), Xinan Wang (UC San Diego), Yusu Wang (Ohio State University), Manfred K. Warmuth (UC Santa Cruz), Jun Yang (University of Toronto)