Accepted Papers

Reinforcement Learning

• • Philip Thomas and Emma Brunskill. Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning

  • Yarin Gal, Rowan Mcallister and Carl Rasmussen. Improving PILCO with Bayesian Neural Network Dynamics Models

  • Rowan McAllister, Mark van der Wilk and Carl Rasmussen. Data-Efficient Policy Search using PILCO and Directed-Exploration

  • Angela Zhou, Haitham Bou Ammar and Warren Powell. Sequential Decision Making over Networks: Coupon Targeting

  • Supratik Paul, Kamil Ciosek, Michael Osborne and Shimon Whiteson. Alternating Optimisation and Quadrature for Robust Reinforcement Learning

Deep Learning

• • Harrison Edwards and Amos Storkey. Neural Statistician

  • Eric Nalisnick and Padhraic Smyth. Nonparametric Deep Generative Models with Stick-Breaking Priors

  • Cedric De Boom, Sam Leroux, Steven Bohez, Pieter Simoens, Thomas Demeester and Bart Dhoedt. Efficiency Evaluation of Character-level RNN Training Schedules

  • Augustus Odena. Semi-Supervised Learning with Generative Adversarial Networks

  • Pierre Thodoroff and Joelle Pineau. Automatic seizure detection using Deep Learning

  • Enoch Yeung, Lauren Charles-Smith and Courtney Corley. Distributed Doc2Vec Models for Fine-Grained Classification

  • Yarin Gal. A Theoretically Grounded Application of Dropout in Recurrent Neural Networks

Probabilistic Reasoning and Bayesian Analysis

• • Willie Neiswanger and Eric Xing Efficient Bayesian Inference with Prior Swapping

  • Marta Soare, Mohammad Ammad-Ud-Din and Samuel Kaski. Regression with n->1 by Expert Knowledge Elicitation

  • Nina Balcan, Travis Dick and Yishay Mansour. Data Efficient Algorithms for Multi-class Output-code Based Learning

  • Ritabrata Dutta, Paul Blomstedt and Samuel Kaski. Bayesian inference in hierarchical models by combining independent posteriors

  • Thang Bui, Carl Rasmussen and Richard Turner. Bayesian Gaussian Process State Space Models via Power-Expectation Propagation

  • Wittawat Jitkrittum, Zoltan Szabo, Kacper Chwialkowski and Arthur Gretton. Distinguishing Distributions with Interpretable Features

  • Yining Wang and Aarti Singh. Minimax Linear Regression under Measurement Constraints

  • Harsh Nisar and Bhanu Pratap Singh Rawat. Can Evolutionary Sampling Improve Bagged Ensembles?

  • Jonathan Falk and Andrew Gelman. No Trump: A statistical exercise in priming.

Active Learning and Bayesian Optimization

• • Rika Antonova, Joe Runde, Christoph Dann and Emma Brunskill. Improving the Sample Efficiency of Bayesian Optimization Policy Search for Optimal Stopping Problems

  • Joachim van der Herten, Ivo Couckuyt, Dirk Deschrijver and Tom Dhaene. Active Learning for Approximation of Expensive Functions with Normal Distributed Output Uncertainty

  • Matthew Berger, Lucas Magee, Eric Heim and Lee Seversky. Spatial Active Learning For Cost-Effective Sensing and Feature Extraction

  • Yifei Ma, Roman Garnett and Jeff Schneider. Active Search for Sparse Signals with Region Sensing

  • Alina Beygelzimer, Daniel Hsu, John Langford and Chicheng Zhang. Search Improves Label for Active Learning

  • Angela Zhou, Irineo Cabreros and Karan Singh. Dynamic Task Allocation for Crowdsourcing Settings