UAI 2015 - Program Overview

Sunday July 12 (Tutorials) - Room UvA 1-4

7:30 - 18:30	Opening hours Registration Desk
08:30 - 10:20	Tutorial I: Algorithms for Learning Bayesian Network Structures Changhe Yuan, James Cussens, Brandon Malone
10:20 - 10:40	coffee break
10:40 - 12:30	Tutorial II: Computational Complexity of Bayesian Networks Johan Kwisthout, Cassio De Campos
12:30 - 14:30	lunch break
14:30 - 16:20	Tutorial III: Belief functions for the working scientist Thierry Denoeux, Fabio Cuzzolin
16:20 - 16:40	break
16:40 - 18:30	Tutorial IV: Non-parametric Causal Models Robin Evans, Thomas Richardson

See tutorials for more details.

Monday July 13 - Room UvA 1-4

7:30 - 18:55	Opening hours Registration Desk
8:30 - 8:40	Welcome
8:40 - 9:40	Keynote: David MacKay
9:40 - 10:30	Oral Session: Reinforcement learning
10:30 - 10:50	coffee break
10:50 - 12:05	Oral Session: Decision theory
12:05 - 14:05	lunch
14:05 - 15:20	Oral Session: Bayesian networks I
15:20 - 15:40	coffee break
15:40 - 16:30	Oral Session: Bayesian networks II
16:30 - 16:55	Poster Spotlights
16:55 - 18:55	Poster Session

Tuesday July 14 - Room UvA 1-4

8:00 - 18:00	Opening hours Registration Desk
8:30 - 9:30	Keynote: Peter Bühlmann
9:30 - 10:20	Oral Session: Representation
10:20 - 10:50	coffee break
10:50 - 12:05	Oral Session: Causality
12:05 - 14:05	lunch
14:05 - 15:20	Oral Session: Bayesian methods
15:20 - 15:45	Poster Spotlights
15:45 - 17:45	Poster Session (coffee at the start of the poster session)
18:00-18:15	Buses waiting outside of Casa 400
18:15 (sharp)	Buses leave to IJkantine
18:45-22:30	Banquet at IJkantine
22:30-23:00	Buses return from IJkantine to Casa 400

Wednesday July 15 - Room UvA 1-4

8:00 - 18:45	Opening hours Registration Desk
8:30 - 10:10	Oral Session: Learning theory and algorithms
10:10 - 10:30	coffee break
10:30 - 12:10	Oral Session: Approximate inference I
12:10 - 14:10	lunch
14:10 - 15:10	Keynote: David Silver
15:10 - 15:30	coffee break
15:30 - 16:20	Oral Session: Approximate inference II
16:20 - 16:45	Poster Spotlights
16:45 - 18:45	Poster Session
16:45 - 17:15	Business Meeting

Thursday July 16 (Workshops) - Room UvA 1-4

See the workshop page

---

Detailed Program

Monday July 13

7:30 - 18:30	Opening hours Registration Desk
8:30 - 8:40	Welcome
8:40 - 9:40	Keynote: David MacKay Why climate change action is difficult, and how we can make a difference See here for details
9:40 - 10:30	Oral Session: Reinforcement learning   chair: Rich Sutton ID: 38 (pdf)| Finite-Sample Analysis of Proximal Gradient TD Algorithms | Bo Liu, University of Massachusetts Am; Ji Liu, University of Rochester; Mohammad Ghavamzadeh, Researcher / Chargé de Recherche (CR1), INRIA Lille - Team SequeL; Sridhar Mahadevan, School of Computer Science University of Massachusetts Amherst; Marek Petrik, IBM Research ID: 281 (pdf)| Online Bellman Residual Algorithms with Predictive Error Guarantees | Wen Sun, Carnegie Mellon University; J. Andrew Bagnell, Carnegie Mellon University
10:30 - 10:50	coffee break
10:50 - 12:05	Oral Session: Decision theory   chair: Ross Shachter ID: 31 (pdf)| Budget Constraints in Prediction Markets | Nikhil Devanur, Microsoft Research; Miroslav Dudik, Microsoft Research; Zhiyi Huang, University of Hong Kong; David Pennock, Microsoft Research ID: 67 (pdf)| Planning under Uncertainty with Weighted State Scenarios | Erwin Walraven, Delft University of Technology; Matthijs Spaan, Delft University of Technology ID: 308 (pdf)| Multitasking: Optimal Planning for Bandit Superprocesses | Dylan Hadfield-Menell, UC Berkeley; Stuart Russell
12:05 - 14:05	lunch
14:05 - 15:20	Oral Session: Bayesian networks I   chair: Alexandra Carvalho ID: 13 (pdf)| The Long-Run Behavior of Continuous Time Bayesian Networks | Liessman Sturlaugson, Montana State University; John Sheppard, Montana State University ID: 114 (pdf)| An Upper Bound on the Global Optimum in Parameter Estimation | Khaled Refaat, UCLA; Adnan Darwiche, UCLA ID: 139 (pdf)| Efficient Algorithms for Bayesian Network Parameter Learning from Incomplete Data | Guy Van den Broeck, Karthika Mohan, Arthur Choi, UCLA; Judea Pearl
15:20 - 15:40	coffee break
15:40 - 16:30	Oral Session: Bayesian networks II   chair: Marloes Maathuis ID: 190 (pdf)| Probabilistic Graphical Models Parameter Learning with Transferred Prior and Constraints | Yun Zhou, Queen Mary University of Londo; Norman Fenton, Queen Mary University of London; Timothy Hospedales, Queen Mary University of London; Martin Neil, Queen Mary University of London ID: 302 (pdf)| Mesochronal Structure Learning | Sergey Plis, The Mind Research Network; Jianyu Yang, the Mind Research Network; David Danks, Carnegie Mellon University
16:30 - 16:55	Poster Spotlights   chair: Kathryn Laskey ID: 235 (pdf)| Kernel-Based Just-In-Time Learning for Passing Expectation Propagation Messages | Wittawat Jitkrittum, University College London; Arthur Gretton, Gatsby unit, University College London; Nicolas Heess, S. M. Ali Eslami, Google DeepMind; Balaji Lakshminarayanan, Gatsby/University College London; Dino Sejdinovic, University of Oxford; Zoltan Szabo, Gatsby unit, University College London ID: 9 (pdf)| Bethe and Related Pairwise Entropy Approximations | Adrian Weller, University of Cambridge ID: 266 (pdf)| Hamiltonian ABC | Edward Meeds, University of Amsterdam; Max Welling, Robert Leenders ID: 316 (pdf)| Learning Latent Variable Models by Improving Spectral Solutions with Exterior Point Method | Amirreza Shaban, Georgia Institute of Technolog; Mehrdad Farajtabar, Georgia Institute of Technology; Bo Xie, Georgia Institute of Technology; Le Song, Georgia Tech; Byron Boots, Georgia Institute of Technology ID: 252 (pdf)| Selective Greedy Equivalence Search: Finding Optimal Bayesian Networks Using a Polynomial Number of Score Evaluations | Max Chickering, Microsoft Research; Chris Meek, Microsoft Research ID: 103 (pdf) | Disciplined Convex Stochastic Programming: A New Framework for Stochastic Optimization | Alnur Ali, Carnegie Mellon University; J. Zico Kolter, Carnegie Mellon University; Steven Diamond, Stanford University; Stephen Boyd, Stanford University ID: 97 (pdf)| A Finite Population Likelihood Ratio Test of the Sharp Null Hypothesis for Compliers | Wen Wei Loh, University of Washington; Thomas Richardson, University of Washington ID: 293 (pdf)| Robust reconstruction of causal graphical models based on conditional 2-point and 3-point information | Herve Isambert, CNRS; Severine Affeldt, Institut Curie ID: 221 (pdf)| Learning from Pairwise Marginal Independencies | Johannes Textor, Utrecht University; Alexander Idelberger, Universität zu Lübeck; maciej Liskiewicz, Universität zu Lübeck ID: 155 (pdf)| A Complete Generalized Adjustment Criterion | Emilija Perkovic, ETH Zurich; Johannes Textor, Utrecht University; Markus Kalisch, ETH Zurich; Marloes Maathuis, ETH Zurich ID: 86 (pdf)| Learning the Structure of Causal Models with Relational and Temporal Dependence | Katerina Marazopoulou, University of Massachusetts Am; Marc Maier, University of Massachusetts Amherst; David Jensen, University of Massachusetts Amherst ID: 35 (pdf)| Intelligent Affect: Rational Decision Making for Socially Aligned Agents | Nabiha Asghar, University of Waterloo; Jesse Hoey, University of Waterloo ID: 16 (pdf)| Complexity of the Exact Solution to the Test Sequencing Problem | Wenhao Liu, Stanford University; Ross Shachter, Stanford University ID: 224 (pdf)| Estimating Mutual Information by Local Gaussian Approximation | Shuyang Gao, USC; Greg Ver Steeg, Information Sciences Institute; Aram Galstyan, Information Sciences Institute ID: 258 (pdf)| A Probabilistic Logic for Reasoning about Uncertain Temporal Information | Dragan Doder, University of Luxembourg; Zoran Ognjanovic, Mathematical Institute, Serbian Academy of Sciences and Arts — ID: 300 (pdf)| Multi-Context Models for Reasoning under Partial Knowledge: Generative Process and Inference Grammar | Ardavan Salehi Nobandegani, McGill University ; Ioannis Psaromiligkos, McGill University ID: 213 (pdf)| Psychophysical Detection Testing with Bayesian Active Learning | Jacob Gardner, Washington University in St. L; Xinyu Song, Washington University in St. Louis; Kilian Weinberger, Washington University in St. Louis; John Cunningham, Columbia University; Dennis Barbour, Washington University in St. Louis ID: 307 (pdf)| Active Search and Bandits on Graphs Using Sigma-Optimality | Yifei Ma, CMU; Tzu-Kuo Huang, Microsoft Research; Jeff Schneider, Carnegie Mellon Univ ID: 41 (pdf)| Classification of Sparse and Irregularly Sampled Time Series with Mixtures of Expected Gaussian Kernels and Random Features | Steven Cheng-Xian Li, UMass Amherst; Benjamin Marlin, UMass Amherst ID: 33 (pdf)| Adversarial Cost-Sensitive Classification | Kaiser Asif, U of Illinois at Chicago; Wei Xing, U of Illinois at Chicago; Sima Behpour, U of Illinois at Chicago; Brian Ziebart, University of Illinois at Chicago ID: 141 (pdf)| Communication Efficient Coresets for Empirical Loss Minimization | Sashank Jakkam Reddi, Carnegie Mellon University; Barnabas Poczos, Alex Smola ID: 57 (pdf)| Incremental region selection for mini-bucket elimination bounds | Sholeh Forouzan, UC, Irvine; Alexander Ihler, UC Irvine ID: 165 (pdf)| Off-policy learning based on weighted importance sampling with linear computational complexity | Ashique Rupam Mahmood, University of Alberta; Richard Sutton, University of Alberta
16:55 - 18:55	Poster Session Will include all papers presented today

See the proceedings for more details about the papers including supplementary material

Tuesday July 14

8:00 - 18:00	Opening hours Registration Desk
8:30 - 9:30	Keynote: Peter Bühlmann High-dimensional causal inference: exploiting the power of heterogeneous data See here for details
9:30 - 10:20	Oral Session: Representation   chair: Pradeep Ravikumar ID: 46 (pdf)| Extend Transferable Belief Models with Probabilistic Priors | Chunlai Zhou, Renmin University of China; Yuan Feng, University of Technology, Sydney ID: 180 (pdf)| Encoding Markov logic networks in Possibilistic Logic | Ondrej Kuzelka, Cardiff University; Jesse Davis, KU Leuven; Steven Schockaert, Cardiff University
10:20 - 10:50	coffee break
10:50 - 12:05	Oral Session: Causality   chair: Vanessa Didelez ID: 109 (pdf)| Visual Causal Feature Learning | Krzysztof Chalupka, Caltech; Pietro Perona, Caltech; Frederick Eberhardt, Caltech ID: 127 (pdf)| Do-calculus when the True Graph is Unknown | Antti Hyttinen, University of Helsinki; Frederick Eberhardt, Caltech; Matti Järvisalo, University of Helsinki ID: 204 (pdf)| Missing Data as a Causal and Probabilistic Problem | Ilya Shpitser, University of Southampton; Karthika Mohan, UCLA; Judea Pearl, UCLA
12:05 - 14:05	lunch
14:05 - 15:20	Oral Session: Bayesian methods   chair: Ioannis Tsamardinos ID: 47 (pdf)| Population Empirical Bayes | Alp Kucukelbir, Columbia University; David Blei, Columbia University ID: 135 (pdf)| Clustered Sparse Bayesian Learning | Yu Wang, Cambridge University; David Wipf, Jeong Min Yun, Wei Chen, Ian Wassell ID: 319 (pdf)| Zero-Truncated Poisson Tensor Factorization for Massive Binary Tensors | Changwei Hu, Duke University; Piyush Rai, Duke University; Lawrence Carin, Duke University
15:20 - 15:45	Poster Spotlights   chair: David Jensen ID: 191 (pdf)| Large-scale randomized-coordinate descent methods with non-separable linear constraints | Ahmed Hefny, Carnegie Mellon University; Sashank Jakkam Reddi, Carnegie Mellon University; Carlton Downey, Carnegie Mellon University; Avinava Dubey, Carnegie Mellon University; Suvrit Sra, MIT ID: 203 (pdf)| Budgeted Online Collective Inference | Jay Pujara, University of Maryland; Ben London, University of Maryland; Lise Getoor, University of California, Santa Cruz ID: 143 (pdf)| Importance sampling over sets: a new probabilistic inference scheme | Stefan Hadjis, Stanford University; Stefano Ermon, Stanford University ID: 106 (pdf)| Max-Product Belief Propagation for Linear Programming: Applications to Combinatorial Optimization | Sejun Park, KAIST; Jinwoo Shin, KAIST ID: 111 (pdf)| The Limits of Knowledge Compilation for Exact Model Counting | Vincent Liew, University of Washington; Paul Beame, University of Washington ID: 167 (pdf)| State Sequence Analysis in Hidden Markov Models | Yuri Grinberg, Ottawa Hospital Research Inst.; Theodore Perkins, Ottawa Hospital Research Institute ID: 294 (pdf)| Auxiliary Gibbs Sampling for Inference in Piecewise-Constant Conditional Intensity Models | Zhen Qin, UC-Riverside; Christian Shelton, UC-Riverside ID: 209 (pdf)| Large-Margin Determinantal Point Processes | Wei-Lun Chao, USC; Boqing Gong, USC; Kristen Grauman, U. of Texas at Austin; Fei Sha, USC ID: 208 (pdf)| Scalable Recommendation with Hierarchical Poisson Factorization | Prem Gopalan, Princeton University; Jake Hofman, Microsoft Research; David Blei, Columbia University ID: 83 (pdf)| Learning the Structure of Sum-Product Networks via an SVD-based Algorithm | Tameem Adel, Radboud University Nijmegen; David Balduzzi, Victoria University of Wellington; Ali Ghodsi, University of Waterloo ID: 189 (pdf)| Learning Optimal Chain Graphs with Answer Set Programming | Dag Sonntag, Linköping University; Matti Järvisalo, University of Helsinki; Jose Pena, Linkoping University; Antti Hyttinen, University of Helsinki ID: 105 (pdf)| Structure Learning Constrained by Node-Specific Degree Distribution | Jianzhu Ma, TTIC; Qingming Tang, TTIC; Sheng Wang, TTIC; Feng Zhao, TTIC; Jinbo Xu, TTIC ID: 89 (pdf)| On the Computability of AIXI | Jan Leike, ANU; Marcus Hutter, The Australian National University ID: 102 (pdf)| Optimal Threshold Control for Energy Arbitrage with Degradable Battery Storage | Marek Petrik, IBM; Xiaojian Wu, UMASS ID: 130 (pdf)| A Markov Game Model for Valuing Player Actions in Ice Hockey | Kurt Routley, Simon Fraser University; Oliver Schulte, Simon Fraser University ID: 231 (pdf)| Non-parametric Revenue Optimization for Generalized Second Price Auctions. | Mehryar Mohri, NYU; Andres Munoz Medina, NYU ID: 246 (pdf)| The Survival Filter: Joint Survival Analysis with a Latent Time Series | Rajesh Ranganath, Princeton University; Adler Perotte, Columbia University; Noemie Elhadad, Columbia University; David Blei, Columbia University ID: 77 (pdf)| Discriminative Switching Linear Dynamical Systems applied to Physiological Condition Monitoring | Konstantinos Georgatzis, University of Edinburgh; Christopher Williams, University of Edinburgh ID: 202 (pdf)| Stable Spectral Learning Based on Schur Decomposition | Nikos Vlassis, Adobe; Nicolo Colombo, LCSB, Univ of Luxembourg ID: 228 (pdf)| Equitable Partitions of Concave Free Energies | Martin Mladenov, TU Dortmund; Kristian Kersting, TU Dortmund University ID: 123 (pdf)| Generalization Bounds for Transfer Learning under Model Shift | Xuezhi Wang, Carnegie Mellon Univ.; Jeff Schneider, Carnegie Mellon Univ ID: 146 (pdf)| Novel Bernstein-like Concentration Inequalities for the Missing Mass | Bahman Yari Saeed Khanloo, Monash; Gholamreza Haffari, Monash University ID: 188 (pdf)| Bayesian Network Learning with Discrete Case-Control Data | Giorgos Borboudakis, University of Crete; Ioannis Tsamardinos, University of Crete ID: 329 (pdf)| Polynomial-time algorithm for learning optimal tree-augmented dynamic Bayesian networks | Alexandra Carvalho, Instituto de Telecomunicações; José Monteiro, IST; Susana Vinga, IDMEC
15:45 - 17:45	Poster Session Will include all papers presented today and coffee at the start of the session
18:00 -	Banquet Banquet Speaker: Raphael Slawinski Should we go for it? Risk and decision-making in the mountains See here for details Bus details: 18:00-18:15 Buses waiting outside of Casa 400 18:15 (sharp) Buses leave to IJkantine 18:45-22:30 Banquet at IJkantine 22:30-23:00 Buses return from IJkantine to Casa 400

See the proceedings for more details about the papers including supplementary material

Wednesday July 15

8:00 - 18:45	Opening hours Registration Desk
8:30 - 10:10	Oral Session: Learning theory and algorithms   chair: Changhe Yuan ID: 72 (pdf)| Bayes Optimal Feature Selection for Supervised Learning with General Performance Measures | Saneem Ahmed CG, IBM India Research Lab; Harikrishna Narasimhan, Indian Institute of Science; Shivani Agarwal, Indian Institute of Science ID: 121 (pdf)| Fast Relative-Error Approximation Algorithm for Ridge Regression | Shouyuan Chen, CUHK; Yang Liu, The Chinese University of Hong Kong; Michael Lyu, Chinese University of Hong Kong; Irwin King, The Chinese University of Hong Kong; Shengyu Zhang, The Chinese University of Hong Kong ID: 305 (pdf)| Representation Learning for Clustering: A Statistical Framework | Hassan Ashtiani, University of Waterloo; Shai Ben-David, University of Waterloo ID: 62 (pdf)| Parameterizing the Distance Distribution of Undirected Networks | Christian Bauckhage, Fraunhofer IAIS and University of Bonn; Kristian Kersting, TU Dortmund University; Fabian Hadiji, TU Dortmund University
10:10 - 10:30	coffee break
10:30 - 12:10	Oral Session: Approximate inference I   chair: Nikos Vlassis ID: 12 (pdf)| Tracking with ranked signals | Tianyang Li, UT Austin; Harsh Pareek, UT Austin; Pradeep Ravikumar, UT Austin; Dhruv Balwada, Geophysical Fluid Dynamics Institute at Florida State University; Kevin Speer, Geophysical Fluid Dynamics Institute at Florida State University ID: 158 (pdf)| Locally Conditioned Belief Propagation | Thomas Geier, Ulm University; Felix Richter, Ulm University; Susanne Biundo, Ulm University ID: 248 (pdf)| High-Dimensional Stochastic Integration via Error-Correcting Codes | Dimitris Achlioptas, UCSC; Pei Jiang ID: 321 (pdf)| Minimizing Expected Losses in Perturbation Models with Multidimensional Parametric Min-cuts | Adrian Kim, Seoul National University; Kyomin Jung, Daniel Tarlow, Pushmeet Kohli, Microsoft Research
12:10 - 14:10	lunch
14:10 - 15:10	Keynote: David Silver Deep Reinforcement Learning See here for details
15:10 - 15:30	coffee break
15:30 - 16:20	Oral Session: Approximate inference II   chair: Johan Kwisthout ID: 120 (pdf)| Estimating the Partition Function by Discriminance Sampling | Qiang Liu, MIT; Jian Peng, UIUC; Alexander Ihler, UC Irvine; John Fisher III, MIT ID: 187 (pdf)| Approximate Probabilistic Inference in Hybrid Domains by Hashing | Vaishak Belle, KU Leuven; Guy Van den Broeck, KU Leuven; Andrea Passerini, University of Trento
16:20 - 16:45	Poster Spotlights   chair: Ann Nicholson ID: 81 (pdf)| Progressive Abstraction Refinement for Sparse Sampling | Jesse Hostetler, Oregon State University; Alan Fern, Oregon State University; Thomas Dietterich, Oregon State University ID: 37 (pdf)| Are You Doing What I Think You Are Doing? Criticising Uncertain Agent Models | Stefano Albrecht, The University of Edinburgh; Subramanian Ramamoorthy, The University of Edinburgh ID: 312 (pdf)| Revisiting Non-Progressive Influence Models: Scalable Influence Maximization in Social Networks | Golshan Golnari, University of Minnesota; Amir Asiaee T., University of Minnesota; Arindam Banerjee, University of Minnesota; Zhi-Li Zhang, University of Minnesota ID: 285 (pdf)| Fast Algorithms for Learning with Long $N$-grams via Suffix Tree Based Matrix Multiplication | Hristo Paskov, Stanford University; Trevor Hastie, Stanford; John Mitchell, Stanford ID: 96 (pdf)| Improved Asymmetric Locality Sensitive Hashing (ALSH) for Maximum Inner Product Search (MIPS) | Anshumali Shrivastava, Cornell University; Ping Li, Rutgers University ID: 226 (pdf)| Semi-described and semi-supervised learning with Gaussian processes | Andreas Damianou, University of Sheffield; Neil Lawrence ID: 230 (pdf)| Training generative neural networks via Maximum Mean Discrepancy optimization | Gintare Karolina Dziugaite, University of Cambridge; Zoubin Ghahramani, Cambridge University; Daniel Roy, University of Toronto ID: 55 (pdf)| Computing Optimal Bayesian Decisions for Rank Aggregation via MCMC Sampling | David Hughes, RPI; Kevin Hwang, RPI; Lirong Xia, Rensselaer Polytechnic Institute ID: 271 (pdf)| Bayesian Optimal Control of Smoothly Parameterized Systems | Yasin Abbasi-Yadkori, QUT; Csaba Szepesvari, University of Alberta ID: 131 (pdf)| Impact of Learning Strategies on the Quality of Bayesian Networks: An Empirical Evaluation | Brandon Malone, Max Planck Institute; Matti Järvisalo, University of Helsinki; Petri Myllymaki, Helsinki Institute for Information Technology ID: 298 (pdf)| Averaging of Decomposable Graphs by Dynamic Programming and Sampling | Kustaa Kangas, University of Helsinki; Teppo Niinimäki, University of Helsinki; Mikko Koivisto, Helsinki Institute for Information Technology ID: 91 (pdf)| Bethe Projections for Non-Local Inference | Luke Vilnis, UMass Amherst; David Belanger, UMass Amherst; Daniel Sheldon, UMass Amherst; Andrew McCallum, UMass Amherst ID: 107 (pdf)| How matroids occur in the context of learning Bayesian network structure | Milan Studeny, Inst. Info. Theory and Autom. ID: 227 (pdf)| Bayesian Structure Learning for Stationary Time Series | Alex Tank, University of Washington; Emily Fox, University of Washington; Nicholas Foti, University of Washington ID: 160 (pdf)| Optimal expert elicitation to reduce interval uncertainty | Nadia Ben Abdallah, Université de Technologie de C; Sébastien Destercke, Université de Technologie de Compiègne ID: 249 (pdf)| Geometric Network Comparisons | Dena Asta, Carnegie Mellon University; Cosma Shalizi, Carnegie Mellon University ID: 277 (pdf)| Learning and Planning with Timing Information in Markov Decision Processes | Pierre-Luc Bacon, McGill University; Borja Balle, McGill University; Doina Precup, McGill University ID: 268 (pdf)| Memory-Efficient Symbolic Online Planning for Factored MDPs | Aswin Raghavan, Oregon State University; Prasad Tadepalli, Oregon State University; Alan Fern, Oregon State University; Roni Khardon, Tufts University ID: 73 (pdf)| Annealed Gradient Descent for Deep Learning | Hengyue Pan, York University; Hui Jiang, York University ID: 58 (pdf)| (Nearly) Optimal Differentially Private Stochastic Multi-Arm Bandits | Nikita Mishra, UChicago; Abhradeep Thakurta, Yahoo! ID: 239 (pdf)| Efficient Transition Probability Computation for Continuous-Time Branching Processes via Compressed Sensing | Jason Xu, University of Washington; Vladimir Minin, University of Washington ID: 168 (pdf)| On the Error of Random Fourier Features | Danica Sutherland, Carnegie Mellon University; Jeff Schneider, Carnegie Mellon Univ ID: 177 (pdf)| A Smart-Dumb/Dumb-Smart Algorithm for Efficient Split-Merge MCMC | Wei WANG, UPMC; Stuart Russell ID: 326 (pdf)| Learning and Inference in Tractable Probabilistic Knowledge Bases | Mathias Niepert, University of Washington; Pedro Domingos, University of Washington
16:45 - 18:45	Poster Session
16:45 - 17:15	Business Meeting

See the proceedings for more details about the papers including supplementary material