Schedule

Preliminary schedule (subject to change)

8:00am	Registration opens
8:00am	Breakfast at the LinkedIn Café
9:05am	Welcome to BayLearn 2016! Rómer Rosales
9:15am	Keynote 1	Two Big Challenges in Machine Learning Leon Bottou, Facebook.
10:00am	Session 1 Session Chair: Rómer Rosales	Mean Field Neural Networks. Samuel Schoenholz, Google Brain; Justin Gilmer, Google Brain; Jascha Sohl-Dickstein, Google Brain. Data Noising as Smoothing in Neural Sequence Models. Ziang Xie, Stanford. Regularizing Neural Networks by Penalizing Their Output Distribution. Gabriel Pereyra, Google; George Tucker, Google; Lukasz Kaiser, Google; Geoffrey Hinton, Google.
10:45am	Break
11:15am	Keynote 2	Bringing AI to 100 Million People with Deep Learning Adam Coates, Baidu.
12:00pm	Session 2 Session Chair: Jean-Francois Paiement	Rethinking Email Volume Optimization. Rupesh Gupta, LinkedIn; Guanfeng Liang, LinkedIn; Rómer Rosales, LinkedIn. Amazon Stream: Personalized, Diversified Ranking for Visual Browsing. Daniel Hill, Amazon.com, Inc.; Choon Hui Teo, Amazon; SVN Vishwanathan, UC Santa Cruz.
12:30pm	Poster session and complimentary lunch at the LinkedIn Café
2:00pm	Keynote 3	Deep Reinforcement Learning for Robotics Pieter Abbeel, UC Berkeley.
2:45pm	Session 3 Session Chair: Alexey Pozdnukhov	End to End Active Perception. Ilya Kostrikov, RWTH Aachen; Dumitru Erhan, Google; Sergey Levine, Google. Canopy - Fast Sampling with Cover Trees. Manzil Zaheer, CMU; Amr Ahmed, Google; Alex Smola, Amazon.
3:15pm	Break
3:45pm	Keynote 4 Session Chair: Samy Bengio	Recent Advances in Robotics and Generative Modeling Ilya Sutskever, OpenAI.
4:30pm	Poster session and Reception (in parallel with Photon ML Tutorial)*
7:00pm	End of the Symposium

* At 5pm, LinkedIn will open its Machine Learning Library tutorial to BayLearn attendees:

Building Personalized Recommender Systems using Photon ML (Open Source). XianXing Zhang, Alex Shelkovnykov, Bee-Chung Chen, Paul Ogilvie (LinkedIn)

Location: 1st floor, Branson Conference Room

Time: 5pm (~90 minutes)

Full list of accepted abstracts

O1. Mean Field Neural Networks. Samuel Schoenholz, Google Brain; Justin Gilmer, Google Brain; Jascha Sohl-Dickstein, Google Brain.
O2. Data Noising as Smoothing in Neural Sequence Models. Ziang Xie, Stanford.
O3. Regularizing Neural Networks by Penalizing Their Output Distribution. Gabriel Pereyra, Google; George Tucker, Google; Lukasz Kaiser, Google; Geoffrey Hinton, Google.
O4. Rethinking Email Volume Optimization. Rupesh Gupta, LinkedIn; Guanfeng Liang, LinkedIn; Rómer Rosales, LinkedIn.
O5. Amazon Stream: Personalized, Diversified Ranking for Visual Browsing. Daniel Hill, Amazon.com, Inc.; Choon Hui Teo, Amazon; SVN Vishwanathan, UC Santa Cruz
O6. End to End Active Perception. Ilya Kostrikov, RWTH Aachen; Dumitru Erhan, Google; Sergey Levine, Google.
O7. Canopy - Fast Sampling with Cover Trees. Manzil Zaheer, CMU; Amr Ahmed, Google; Alex Smola, Amazon.

Posters

P8. Ensemble Validation: Selectivity has a Price, but Variety is Free. Eric Bax, Yahoo; Farshad Kooti, Facebook.
P9. Learning to Remember. Ofir Nachum, Google; Lukasz Kaiser, Google.
P10. Scalable HOGWILD! for Big Models. Chengjie Qin, UC Merced; Florin Rusu, UC Merced; Martín Torres, UC Merced.
P11. On Learning High Dimensional Structured Single Index Models. Ravi Ganti, Walmart Labs; Nikhil Rao, Technicolor Research.
P12. Multi Task Convolutional Music Models. Cinjon Resnick, Google Brain; Diego Ardila, Google; Adam Roberts, Google Brain; Douglas Eck, Google Brain.
P13. Scalable Machine Learning on Spark for multiclass problems. Gautham Kamath, Georgia State University; Sauptik Dhar, Robert Bosch LLC; Naveen Ramakrishnan, Robert Bosch LLC; David Hallac, Stanford; Jure Leskovec, Stanford; Mohak Shah, Robert Bosch LLC.
P14. Time Series Symbolization and Deep Learning for Rare Event Prediction. Shengdong Zhang, Bosch; Soheil Bahrampour, Bosch; Naveen Ramakrishnan, Bosch; Lukas Schott, Bosch; Mohak Shah, Bosch.
P15. Optimizing Affinity-Based Binary Hashing Using Auxiliary Coordinates. Ramin Raziperchikolaei, UC Merced; Miguel Carreira-Perpiñán, UC Merced.
P16. Second-Order Stochastic Variational Inference. Jeffrey Regier, UC Berkeley; Jon McAuliffe, UC Berkeley.
P17. Towards Generating Higher Resolution Images with Generative Adversarial Networks. Augustus Odena, Google Brain.
P18. Intelligent Candidate Generation for Large-Scale Link Recommendation. Myunghwan Kim, LinkedIn; Wei Lu, LinkedIn; Souvik Ghosh, LinkedIn; Hema Raghavan, LinkedIn.
P19. Combining Deep Learning and Survival Analysis for Asset Health Management. Linxia Liao, GE Digital.
P20. Fingerprint Verification with Siamese Networks. Cédric Vachaudez, University Paris-saclay; Baiyu Chen, University of California Berkeley; Isabelle Guyon, UPSud, INRIA, University Paris-saclay and ChaLearn; Bernhard Boser, University of California Berkeley.
P21. Personality Trait Estimation from Short Videos. Víctor Ponce - López, Computer Vision Center; Baiyu Chen, University of California Berkeley; Marc Oliu Simón, University of Barcelona; Ciprian Corneanu, Universitat de Barcelona; Albert Clapes, Universitat de Barcelona; Isabelle Guyon, UPSud, INRIA, University Paris-saclay and ChaLearn; Xavier Baró, Universitat Oberta de Catalunya & Computer Vision Center; Hugo Jair Escalante, INAOE; Sergio Escalera, CVC and University of Barcelona; Evelyne Viegas, Microsoft Research.
P22. Generalization of ERM in Stochastic Convex Optimization: The Dimension Strikes Back. Vitaly Feldman, IBM Research - Almaden.
P23. Joint Online Spoken Language Understanding and Language Modeling with RNNs. Bing Liu, Carnegie Mellon University; Ian Lane, Carnegie Mellon University.
P24. Efficient Vector Representation for Documents. Minmin Chen, Criteo
P25. Cost-Sensitive Learning for Promoting Network Growth. Lingjie Weng, Linkedin
P26. Machine Learning in LinkedIn Knowledge Graph. Qi He, LinkedIn; Bee-Chung Chen, LinkedIn; Deepak Agarwal, LinkedIn.
P27. On the expressive power of deep networks. Maithra Raghu, Google Brain/Cornell; Ben Poole, Stanford/Google Brain; Jon Kleinberg, Cornell; Surya Ganguli, Stanford; Jascha Sohl-Dickstein, Google Brain
P28. Hierarchical Concept Drift Detection and Adaptation. Zubin Abraham, Robert Bosch; Shujian Yu, University of Florida
P29. Serving Content Email Digest with Per-Article Models at LinkedIn. Ankan Saha, LinkedIn; Ajith Muralidharan, LinkedIn.
P30. A Blocking Scheme for Deep Learning Acceleration. Mohammad Samragh Razlighi, University of California San Diego; Azalia Mirhoseini, Rice University; Farinaz Koushanfar, UC San Diego.
P31. Dual Experimental Setup for Testing Different Link Formation Strategies in a Network. Shilpa Gupta, LinkedIn; Aastha Jain, LinkedIn; Shaunak Chatterjee, LinkedIn; Ya Xu, LinkedIn.

Subpages (1): Building Personalized Recommender Systems using Photon ML