–
Coffee and Check-In
–
Opening Remarks
–
Geometry, Optimization and Generalization in Multilayer Networks
Nathan Srebro, TTI Chicago
–
A Non-generative Framework and Convex Relaxations for Unsupervised Learning
Elad Hazan, Princeton University
–
Break
–
Representations for Language: From Word Embeddings to Sentence Meanings
Christopher Manning, Stanford University
–
Lunch
–
The Missing Signal
Leon Bottou, Facebook AI Research
–
Break
–
Representations of Relationships in Images and Text
Hal Daume, University of Maryland at College Park
–
Spotlight Talk: A Formalization of Representation Learning
Andrej Risteski, Princeton University
–
Spotlight Talk: Semi-Random Units for Learning Neural Networks with Guarantees
Bo Xie, Georgia Institute of Technology
–
Reception
–
Coffee and Check-In
–
Unsupervised Discovery Through Adversarial Self-Play
Rob Fergus, New York University
–
Learning from Unlabeled Video
Kristen Grauman, University of Texas, Austin
–
Break
–
Deep Reinforcement Learning
Pieter Abbeel, UC Berkeley
–
Lunch
–
Supersizing Self-Supervision: Learning Perception and Action without Human Supervision
Abhinav Gupta, Carnegie Mellon University
–
Failures of Deep Learning
Shai Shalev-Shwartz, Hebrew University of Jerusalem
–
Break
–
Panel
–
Coffee and Check-In
–
Continuous State Machines and Grammars for Linguistic Structure Prediction
Noah Smith, University of Washington
–
Adversarial Perceptual Representation Learning Across Diverse Modalities and Domains
Trevor Darrell, UC Berkeley
–
Break
–
Evaluating Neural Network Representations Against Human Cognition
Tom Griffiths, UC Berkeley
–
Lunch
–
Representation Learning for Reading Comprehension
Russ Salakhutdinov, Carnegie Mellon University
–
Tractable Learning in Structured Probability Spaces
Adnan Darwiche, UCLA
–
Break
–
Spotlight Talk: Convolutional Dictionary Learning through Tensor Factorization
Furong Huang, UC Irvine
–
Spotlight Talk: How to Escape Saddle Points Efficiently
Praneeth Netrapalli, Microsoft Research India
–
Coffee and Check-In
–
Re-Thinking Representational Learning in Robotics and Music
Sham Kakade, University of Washington
–
Representation Learning of Grounded Language and Knowledge: with and without End-to-End Learning
Yejin Choi, University of Washington
–
Break
–
TBD
Yann LeCun, New York University
–
Lunch
–
Generalization and Equilibrium in Generative Adversarial Nets (GANs)
Sanjeev Arora, Princeton University
–
Provably Learning of Noisy-or Networks
Rong Ge, Duke University
–
Break
–
Panel
–
Coffee and Check-In
–
Learning Paraphrastic Representations of Natural Language Sentences
Kevin Gimpel, TTI Chicago
–
Formation and Association of Symbolic Memories in the Brain
Christos Papadimitriou, UC Berkeley
–
Break
–
Learning Representations for Active Vision
Bruno Olshausen, UC Berkeley
–
Lunch
–
Resilient Representation and Provable Generalization
Dawn Song, UC Berkeley
–
Word Representation Learning without <unk> Assumptions
Chris Dyer, Carnegie Mellon University
–
Break
–
Spotlight Talk: Performance Guarantees for Transferring Representations
Daniel McNamara, Australian National University