-
8:30am • Opening remarks, winner ISBA travel award
-
8:40am • Mark Beaumont, ABC and Population Genetics: any lessons for big data?
-
9:20am • Brandon Turner, Applications of Likelihood-free Bayesian Methods in Cognitive Science
-
10:30am • David Nott, Uses of ABC in prior choice and Bayesian model checking
-
11:10am • Mijung Park, K2-ABC: ABC with Kernel Embeddings
-
11:35am • Kenji Fukumizu, Kernel Mean Particle Filter with Intractable Likelihoods
-
2:30pm • Rob Deardon, ABC-based inference for epidemic models with uncertain underlying contact networks
-
3:10pm • Oksana Chkrebtii, Approximate Bayesian Computation for Inference on the Introduction and Spread Patterns of Invasive Species
-
4:30pm • Wentao Li, On the Asymptotic Behavior of ABC
-
5:00pm • Iain Murray, ABC as Learning
-
9:00am • Supervised learning labels in a fast moving environment, Alessandro Magnani (@WalmartsLab)
-
9:45am • Doubly Robust Off-policy Evaluation for Reinforcement Learning, Nan Jiang
-
10:30am • Why would you recommend me THAT!?, Aish Fenton (Netflix)
-
11:15am • Conservative Bandits, Roshan Shariff
-
11:30am • Attribute Extraction from Noisy Text Using Character-based Sequence Tagging Models, Pallika Kanani
-
11:45am • Filtering as a Multi-Armed Bandit, Fr√©d√©ric Guillou
-
2:30pm • Optimal A-B Testing, Vivek Farias (MIT)
-
3:00pm • Real-time Predictions using Time-series Data, Devavrat Shah (MIT)
-
3:30pm • A Ranking Approach to Address the Click Sparsity Problem in Personalized Ad Recommendation, Sougata Chaudhuri
-
3:45pm • Computing Strategic and Interpretable Recommendation Sets, Marek Petrik
-
4:30pm • Stochastically Transitive Models for Pairwise Comparisons: Statistical and Computational Issues, Nihar Shah
-
4:45pm • Collaborative Filtering with Stacked Denoising AutoEncoders and Sparse Inputs, Florian Strub
-
5:00pm • Automatic Layout Element Detection From E-Commerce Pages, Anura Bhardwaj.
-
5:15pm • Cost-sensitive Learning for Bidding in Online Advertising Auctions, Flavian Vasile
-
5:30pm • Deep Temporal Features to Predict Repeat Buyers, Pankaj Malhotra
-
5:45pm • From sale prediction to product recommendation: designing, learning, and evaluating large-scale models at Criteo, Nicolas Le Roux (Criteo)
-
8:20am • Introduction
-
8:30am • How to learn an algorithm, Juergen Schmidhuber (Invited)
-
9:05am • From Attention to Memory and towards Longer-Term Dependencies, Yoshua Bengio (Invited)
-
9:40am • Generating Images from Captions with Attention, Elman Mansimov (Contributed)
-
10:30am • Alex Graves, Google Deepmind (Invited)
-
11:05am • Exploiting cognitive constraints to improve machine-learning memory models, Mike Mozer (Invited)
-
11:40am • Structured Memory for Neural Turing Machines√Æ Wei Zhang, Yang Yu, Bowen Zhou (IBM Watson) (Contributed)
-
12:00pm • Towards Neural Network-based Reasoning, Baolin Peng, (Contributed)
-
12:20pm • Learning to learn neural networks, Tom Bosc, Inria.
-
12:25pm • Evolving Neural Turing Machines, Rasmus Boll Greve
-
2:30pm • Neural Machine Translation: Progress Report and Beyond, Kyunghyun Cho, NYU (Invited)
-
3:05pm • Sleep, learning and memory: optimal inference in the prefrontal cortex, Adrien Peyrache, NYU (Invited)
-
3:40pm • Dynamic Memory Networks for Natural Language Processing, Ankit Kumar (Contributed)
-
4:00pm • Neural Models for Simple Algorithmic Games, Sainbayar Sukhbaatar (Contributed)
-
4:20pm • Chess Q&A : Question Answering on Chess Games, Volkan Cirik
-
4:25pm • Considerations for Evaluating Models of Language Understanding and Reasoning, Gabriel Recchia
-
5:00pm • A Roadmap towards Machine Intelligence, Tomas Mikolov, Facebook AI Research (Invited)
-
5:35pm • Learning Deep Neural Network Policies with Continuous Memory States, Marvin Zhan (Contributed)
-
5:55pm • The Neural GPU and the Neural RAM machine, Ilya Sutskever, Google (Invited)
-
9:00am • Random sampling of bandlimited signals on graphs, Pierre Vandergheynst
-
9:40am • Multiresolution Matrix Factorization, Risi Kondor
-
10:30am • Beyond Nodes and Edges: Multiresolution Models of Complex Networks, Jure Leskovec
-
11:00am • Challenges in Multiresolution Methods for Graph-based Learning, Michael W. Mahoney
-
11:30am • Deep Convolutional Nets as a Multi-Scale Matrix Mixture Factorization, Ankit B. Patel
-
11:50am • Hierarchical Decomposition of Kernel Matrices, William B. March
-
2:00pm • Multigrid-inspired Methods for Networks, lya Safro
-
2:30pm • Fast Direct Methods for Gaussian Processes, Michael O'Neil
-
3:00pm • Approximating Gaussian Processes with H^2 Matrices, Steffen B√∂rm
-
3:20pm • A Multiresolution Approach for Tensor Factorization, Kunil Srivastava
-
3:40pm • Multiresolution analysis for the statistical analysis of incomplete rankings, Eric Sibony
-
4:30pm • Francis Bach
-
5:00pm • Scaling Phenomena in Stochastic Topology, Sayan Mukherjee
-
9:00am • Methods overview: Andreas Schaefer, University College London
-
9:30am • Computational discussant: Konrad Kording, Northwestern University
-
10:20am • Methods overview: Narayanan Kasthuri, Argonne National Lab, U Chicago
-
10:50am • Computational discussant: Randal Burns, Johns Hopkins University
-
11:20am • Methods overview: Karl Deisseroth, Stanford University
-
11:50am • Computational discussant: Guillermo Sapiro, Duke University
-
12:20pm • Poster Spotlights
-
1:00pm • Poster Session
-
2:00pm • Alex Szalay, Johns Hopkins University
-
2:40pm • Discussion with Alex
-
3:00pm • David Woodruff, IBM Almaden
-
4:30pm • Richard G. Baraniuk, Rice University
-
8:50am • Introductions
-
9:00am • Michael Littman, Brown University: 'Reinforcement Learning from users: New algorithms and frameworks'
-
10:30am • Jerry Zhu, University of Wisconsin Madison: 'Machine Teaching for Personalized Education, Security, Interactive Machine Learning'
-
11:15am • Hoang M. Le, Yisong Yue, & Peter Carr. 'Smooth Imitation Learning.'
-
1:30pm • John Langford, Microsoft Research: 'An Interactive Learning Platform for Making Decisions'
-
2:15pm • Neil Heffernan, Worcester Polytechnic Institute: 'Enabling real-time evaluation of crowdsourced machine learning algorithms: Experimentation and Personalization in math problems on ASSISTments.org'
-
3:00pm • Spotlights & Posters
-
4:30pm • Ambuj Tewari, Huitian Lei, & Susan Murphy. University of Michigan. 'From Ads to Interventions: Contextual Bandit Algorithms for Mobile Health'. (NIH application to 'Heartsteps')
-
5:30pm • Panel & Group Discussion on Conclusions & Future Directions. Finale Doshi-Velez, Ambuj Tewari, Joseph Jay Williams, Neil Heffernan