The aim of this workshop is to bring together a broad set of researchers looking at algorithmic questions that arise in machine learning. The primary target areas will be large-­scale learning, including algorithms for Bayesian estimation and variational inference, nonlinear and nonparametric function estimation, reinforcement learning, and stochastic processes including diffusion, point processes and MCMC. While many of these methods have been central to statistical modeling and machine learning, recent advances in their scope and applicability lead to basic questions about their computational efficiency. The latter is often linked to modeling assumptions and objectives. The workshop will examine progress and challenges and include a set of tutorials on the state of the art by leading experts.

Le Song (Georgia Institute of Technology)
Invited Participants

Ryan Adams (Harvard University), Anima Anandkumar (UC Irvine), 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), David Blei (Columbia University), Joan Bruna (UC Berkeley), Moses Charikar (Stanford University), Ben Cousins (Georgia Institute of Technology), Sanjoy Dasgupta (UC San Diego), Hal Daume (University of Maryland at College Park), Ilias Diakonikolas (University of Southern California), David Dunson (Duke University), David Duvenaud (University of Toronto), Alex Edmonds (University of Toronto), Reza Eghbali (University of Washington), Justin Eldridge (Ohio State University), Maryam Fazel (University of Washington), Vitaly Feldman (IBM Research - Almaden), Dylan Foster (Cornell University), Emily Fox (University of Washington), Yoav Freund (UC San Diego), Navin Goyal (Microsoft Research, India), Moritz Hardt (UC Berkeley), Hamed Hassani (ETH Zurich), Katherine Heller (Duke University), Dorit Hochbaum (UC Berkeley), Daniel Hsu (Columbia University), Stefanie Jegelka (Massachusetts Institute of Technology), Mike Jordan (UC Berkeley), Ravi Kannan (Microsoft Research India), Amin Karbasi (Yale University), Andreas Krause (ETH Zurich), Shrinu Kushagra (University of Waterloo), John Langford (Microsoft Research New York), Yin Tat Lee (Massachusetts Institute of Technology), Yingyu Liang (Princeton University), Mike Luby (Qualcomm Technologies, Inc.), Tengyu Ma (Princeton University), Cheng Mao (Massachusetts Institute of Technology), Marina Meila (University of Washington), Shay Moran (Technion), Rob Nowak (University of Wisconsin-Madison), Christos Papadimitriou (UC Berkeley), Samantha Petti (Georgia Institute of Technology), 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), Ohad Shamir (Weizmann Institute), Kevin Shi (Columbia University), Yoram Singer (Princeton University), Aarti Singh (Carnagie Mellon University), Mahdi Soltanolkotabi (University of Southern California), Le Song (Georgia Tech), Suvrit Sra (Massachusetts Institute of Technology), Nati Srebro Bartom (Toyota Technological Institute at Chicago), Karthik Sridharan (Cornell University), Xiaorui Sun (Columbia University), Matus Telgarsky (UIUC), 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), John Wilmes (Georgia Institute of Technology), Eric Xing (Carnegie Mellon University), Jun Yang (University of Toronto)