UAI 2018 Program Schedule


August 6th: Tutorials

Time Event
09:00am - 10:30am Anima Anandkumar, Zach Lipton:
Tackling Data Scarcity in Deep Learning
10:30am - 11:00amCoffee break
11:00am - 12:30pm Matt Hoffman:
Bayesian Optimisation
12:30pm - 02:00pmLunch break
02:00pm - 03:30pm Sebastian Riedel, Johannes Welbl, Dirk Weissenborn:
Machine Reading
03:30pm - 04:00pmCoffee break
04:00pm - 05:30pm Tengyu Ma:
Recent Progress in the Theory of Deep Learning

August 7th: Main conference

Time Event
07:30am - 09:00amRegistration
08:45am - 09:00amOpening words
09:00am - 10:00amRaquel Urtasun - Invited talk
10:00am - 10:10amShort break
10:10am - 11:10amOral session 1: Deep Learning
11:10am - 11:40amCoffee break
11:40pm - 12:40pmOral session 2: Inference in Graphical Models
12:40pm - 02:30pmLunch break
02:30pm - 03:30pmOral session 3: Optimization
03:30pm - 04:00pmCoffee break
04:00pm - 05:00pmMichael C. Frank - Invited talk
05:00pm - 07:00pmPoster session

August 8th: Main conference

Time Event
09:00am - 10:00amStuart Russell - Invited talk
10:00am - 10:10amShort break
10:10am - 11:10amOral Session 4: Reinforcement Learning
11:10am - 11:40amCoffee break
11:40am - 12:40pmOral Session 5: Bayesian Nonparametrics
12:40pm - 02:30pmLunch break
02:30pm - 03:30pmOral Session 6: Sampling
03:30pm - 05:30pmPoster session
05:30pm - 06:10pmOral Session 7: Causality 1
07:00pm - 10:30pmBanquet at the Monterey Aquarium

August 9th: Main conference

Time Event
09:00am - 10:00amJoelle Pineau - Invited talk
10:00am - 10:10amShort break
10:10am - 11:10amOral Session 8: Causality 2
11:10am - 11:40amCoffee break
11:40am - 12:40pmOral Session 9: Learning Theory
12:40pm - 02:30pmLunch break
02:30pm - 04:30pmPoster session
04:30pm - 05:30pmOral Session 10: Latent Variable Models
05:30pm - 06:30pmBusiness Meeting

August 10: Workshops*

Time Event
09:00am - 06:00pm Safety, Risk and Uncertainty in RL
09:00am - 06:00pm Causal Inference Workshop
09:00am - 06:00pm Uncertainty in Deep Learning

*Coffee to be served at 10:30am - 11:00am and 03:30pm - 04:00pm

Oral Session 1 - Deep Learning

The Variational Homoencoder: Learning to learn high capacity generative models from few examples
Luke B. Hewitt, Maxwell I. Nye, Andreea Gane, Tommi Jaakkola, Joshua B. Tenenbaum
Sylvester Normalizing Flows for Variational Inference
Rianne van den Berg, Leonard Hasenclever, Jakub Tomczak, Max Welling
Hyperspherical Variational Auto-Encoders
Tim Davidson, Luca Falorsi, Nicola De Cao, Thomas Kipf, Jakub M. Tomczak
Back to schedule

Oral Session 2 - Inference in Graphical Models

A Forest Mixture Bound for Block-Free Parallel Inference
Neal Lawton, Greg Ver Steeg, Aram Galstyan
Learning Fast Optimizers for Contextual Stochastic Integer Programs
Vinod Nair, Dj Dvijotham, Iain Dunning, Oriol Vinyals
Abstraction Sampling in Graphical Models
Filjor Broka, Rina Dechter, Alexander Ihler, Kalev Kask
Back to schedule

Oral Session 3 - Optimization

Adaptive Stratified Sampling for Precision-Recall Estimation
Ashish Sabharwal, Yexiang Xue
Constraint-based Causal Discovery for Non-Linear Structural Causal Models with Cycles and Latent Confounders*
Patrick Forré, Joris M. Mooij
A Dual Approach to Scalable Verification of Deep Networks (Best Paper Award)
Krishnamurthy Dvijotham, Robert Stanforth, Sven Gowal, Timothy Mann, Pushmeet Kohli

*Kindly agreed to be moved from Session 10, "Latent variable models", to accommodate speaker's travel constraints.

Back to schedule

Oral Session 4 - Reinforcement Learning

Fast Policy Learning through Imitation and Reinforcement
Ching-An Cheng, Xinyan Yan, Nolan Wagener, Byron Boots
Comparing Direct and Indirect Temporal-Difference Methods for Estimating the Variance of the Return
Craig Sherstan, Dylan R. Ashley, Brendan Bennett, Kenny Young, Adam White, Martha White, Richard S. Sutton
Finite-State Controllers of POMDPs using Parameter Synthesis
Sebastian Junges, Nils Jansen, Ralf Wimmer, Tim Quatmann, Leonore Winterer, Joost-Pieter Katoen, Bernd Becker
Back to schedule

Oral Session 5 - Bayesian Nonparametrics

Efficient Bayesian Inference for a Gaussian Process Density Model
Christian Donner, Manfred Opper
Sampling and Inference for Beta Neutral-to-the-Left Models of Sparse Networks
Benjamin Bloem-Reddy, Adam Foster, Emile Mathieu, Yee Whye Teh
Variational zero-inflated Gaussian processes with sparse kernels
Pashupati Hegde, Markus Heinonen, Samuel Kaski
Back to schedule

Oral Session 6 - Sampling

Lifted Marginal MAP Inference
Vishal Sharma, Noman Ahmed Sheikh, Happy Mittal, Vibhav Gogate, Parag Singla
A Unified Particle-Optimization Framework for Scalable Bayesian Sampling
Changyou Chen, Ruiyi Zhang, Wenlin Wang, Bai Li, Liqun Chen
Discrete Sampling using Semigradient-based Product Mixtures
Alkis Gotovos, Hamed Hassani, Andreas Krause, Stefanie Jegelka
Back to schedule

Oral Session 7 - Causality 1

Causal Discovery with Linear Non-Gaussian Models under Measurement Error: Structural Identifiability Results
Kun Zhang, Mingming Gong, Joseph Ramsey, Kayhan Batmanghelich, Peter Spirtes, Clark Glymour
Causal Identification under Markov Equivalence (Best Student Paper Award)
Amin Jaber, Jiji Zhang, Elias Bareinboim
Back to schedule

Oral Session 8 - Causality 2

Causal Learning for Partially Observed Stochastic Dynamical Systems
Søren Wengel Mogensen, Daniel Malinsky, Niels Richard Hansen
Identification of Personalized Effects Associated With Causal Pathways
Ilya Shpitser, Eli Sherman
Non-Parametric Path Analysis in Structural Causal Models
Junzhe Zhang, Elias Bareinboim
Back to schedule

Oral Session 9 - Learning Theory

Towards Flatter Loss Surface via Nonmonotonic Learning Rate Scheduling
Sihyeon Seong, Yegang Lee, Youngwook Kee, Dongyoon Han, Junmo Kim
Averaging Weights Leads to Wider Optima and Better Generalization
Pavel Izmailov, Dmitrii Podoprikhin, Timur Garipov, Dmitry Vetrov, Andrew Gordon Wilson
Revisiting differentially private linear regression: optimal and adaptive prediction & estimation in unbounded domain
Yu-Xiang Wang
Back to schedule

Oral Session 10 - Latent Variable Models

Unsupervised Learning of Latent Physical Properties Using Perception-Prediction Networks
David Zheng, Vinson Luo, Jiajun Wu, Joshua Tenenbaum
A Lagrangian Perspective on Latent Variable Generative Models
Shengjia Zhao, Jiaming Song, Stefano Ermon
Constant Step Size Stochastic Gradient Descent for Probabilistic Modeling*
Dmitry Babichev, Francis Bach

*Moved from Session 3, "Optimization", to accommodate speaker's travel constraints.

Back to schedule Back to schedule

Poster Session - August 7th - Tuesday

Sparse Multi-Prototype Classification
Vikas K. Garg, Lin Xiao, Ofer Dekel
A Univariate Bound of Area Under ROC
Siwei Lyu, Yiming Ying
How well does your sampler really work?
Ryan Turner, Brady Neal
From Deterministic ODEs to Dynamic Structural Causal Models
Paul K. Rubenstein, Stephan Bongers, Joris M. Mooij, Bernhard Schoelkopf
Learning Time Series Segmentation Models from Temporally Imprecise Labels
Roy Adams, Benjamin M. Marlin
Stochastic Learning for Sparse Discrete Markov Random Fields with Controlled Gradient Approximation Error
Sinong Geng, Zhaobin Kuang, Jie Liu, Stephen Wright, David Page
Active Information Acquisition for Linear Optimization
Shuran Zheng, Bo Waggoner, Yang Liu, Yiling Chen
Learning the Causal Structure of Copula Models with Latent Variables
Ruifei Cui, Perry Groot, Moritz Schauer, Tom Heskes
Constant Step Size Stochastic Gradient Descent for Probabilistic Modeling
Dmitry Babichev, Francis Bach
Variational Inference for Gaussian Processes with Panel Count Data
Hongyi Ding, Young Lee, Issei Sato, Masashi Sugiyama
Unsupervised Multi-view Nonlinear Graph Embedding
Jiaming Huang, Zhao Li, Vincent W. Zheng, Wen Wen, Yifan Yang, Yuanmi Chen
GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs
Jiani Zhang, Xingjian Shi, Junyuan Xie, Hao Ma, Irwin King, Dit-yan Yeung
Sylvester Normalizing Flows for Variational Inference
Rianne van den Berg, Leonard Hasenclever, Jakub Tomczak, Max Welling
Holistic Representations for Memorization and Inference
Yunpu Ma, Marcel Hildebrandt, Volker Tresp, Stephan Baier
Variational Inference for Gaussian Process Models for Survival Analysis
Minyoung Kim, Vladimir Pavlovic
A Cost-Effective Framework for Preference Elicitation and Aggregation
Zhibing Zhao, Haoming Li, Junming Wang, Jeffrey O. Kephart, Nicholas Mattei, Hui Su, Lirong Xia
Clustered Fused Graphical Lasso
Yizhi Zhu, Oluwasanmi Koyejo
A Dual Approach to Scalable Verification of Deep Networks
Krishnamurthy Dvijotham, Robert Stanforth, Sven Gowal, Timothy Mann, Pushmeet Kohli
Causal Discovery in the Presence of Measurement Error
Tineke Blom, Anna Klimovskaia, Sara Magliacane, Joris M. Mooij
Learning Fast Optimizers for Contextual Stochastic Integer Programs
Vinod Nair, Dj Dvijotham, Iain Dunning, Oriol Vinyals
High-confidence error estimates for learned value functions
Touqir Sajed, Wesley Chung, Martha White
Stable Gradient Descent
Yingxue Zhou, Sheng Chen, Arindam Banerjee
Learning to select computations
Frederick Callaway, Sayan Gul, Paul M. Krueger, Thomas L. Griffiths, Falk Lieder
Per-decision Multi-step Temporal Difference Learning with Control Variates
Kristopher De Asis, Richard S. Sutton
The Indian Buffet Hawkes Process to Model Evolving Latent Influences
Xi Tan, Vinayak Rao, Jennifer Neville
Adaptive Stratified Sampling for Precision-Recall Estimation
Ashish Sabharwal, Yexiang Xue
Hyperspherical Variational Auto-Encoders
Tim Davidson, Luca Falorsi, Nicola De Cao, Thomas Kipf, Jakub M. Tomczak
Max-margin learning with the Bayes factor
Rahul G. Krishnan, Arjun Khandelwal, Rajesh Ranganath, David Sontag
Densified Winner Take All (WTA) Hashing for Sparse Datasets
Beidi Chen, Anshumali Shrivastava
Lifted Marginal MAP Inference
Vishal Sharma, Noman Ahmed Sheikh, Happy Mittal, Vibhav Gogate, Parag Singla
Pure Exploration of Multi-Armed Bandits with Heavy-Tailed Payoffs
Xiaotian Yu, Han Shao, Michael R. Lyu, Irwin King
Decentralized Planning for Non-dedicated Agent Teams with Submodular Rewards in Uncertain Environments
Pritee Agrawal, Pradeep Varakantham, William Yeoh
A Forest Mixture Bound for Block-Free Parallel Inference
Neal Lawton, Greg Ver Steeg, Aram Galstyan
The Variational Homoencoder: Learning to learn high capacity generative models from few examples
Luke B. Hewitt, Maxwell I. Nye, Andreea Gane, Tommi Jaakkola, Joshua B. Tenenbaum
Bayesian optimization and attribute adjustment
Stephan Eismann, Daniel Levy, Rui Shu, Stefan Bartzsch, Stefano Ermon
Join Graph Decomposition Bounds for Influence Diagrams
Junkyu Lee, Alexander Ihler, Rina Dechter
Soft-Robust Actor-Critic Policy-Gradient
Esther Derman, Daniel J Mankowitz, Timothy A Mann, Shie Mannor
Back to schedule

Poster Session - August 8th - Wednesday

Identification of Strong Edges in AMP Chain Graphs
Jose M. Peña
Efficient Bayesian Inference for a Gaussian Process Density Model
Christian Donner, Manfred Opper
Comparing Direct and Indirect Temporal-Difference Methods for Estimating the Variance of the Return
Craig Sherstan, Dylan R. Ashley, Brendan Bennett, Kenny Young, Adam White, Martha White, Richard S. Sutton
Multi-Target Optimisation via Bayesian Optimisation and Linear Programming
Alistair Shilton, Santu Rana, Sunil Gupta, Svetha Venkatesh
$f_{BGD}$: Learning Embeddings From Positive Unlabeled Data with BGD
Fajie YUAN, Xin Xin, Xiangnan He, Guibing Guo, Weinan Zhang, CHUA Tat-Seng, Joemon Jose
Discrete Sampling using Semigradient-based Product Mixtures
Alkis Gotovos, Hamed Hassani, Andreas Krause, Stefanie Jegelka
Combining Knowledge and Reasoning through Probabilistic Soft Logic for Image Puzzle Solving
Somak Aditya, Yezhou Yang, Chitta Baral, Yiannis Aloimonos
Marginal Weighted Maximum Log-likelihood for Efficient Learning of Perturb-and-Map models
Tatiana Shpakova, Francis Bach, Anton Osokin
Variational zero-inflated Gaussian processes with sparse kernels
Pashupati Hegde, Markus Heinonen, Samuel Kaski
KBlrn: End-to-End Learning of Knowledge Base Representations with Latent, Relational, and Numerical Features
Alberto Garcia-Duran, Mathias Niepert
Probabilistic AND-OR Attribute Grouping for Zero-Shot Learning
Yuval Atzmon, Gal Chechik
Quantile-Regret Minimisation in Infinitely Many-Armed Bandits
Arghya Roy Chaudhuri, Shivaram Kalyanakrishnan
Incremental Learning-to-Learn with Statistical Guarantees
Giulia Denevi, Carlo Ciliberto, Dimitris Stamos, Massimiliano Pontil
Sampling and Inference for Beta Neutral-to-the-Left Models of Sparse Networks
Benjamin Bloem-Reddy, Adam Foster, Emile Mathieu, Yee Whye Teh
Subsampled Stochastic Variance-Reduced Gradient Langevin Dynamics
Difan Zou, Pan Xu, Quanquan Gu
Finite-State Controllers of POMDPs using Parameter Synthesis
Sebastian Junges, Nils Jansen, Ralf Wimmer, Tim Quatmann, Leonore Winterer, Joost-Pieter Katoen, Bernd Becker
Fast Counting in Machine Learning Applications
Subhadeep Karan, Matthew Eichhorn, Blake Hurlburt, Grant Iraci, Jaroslaw Zola
Understanding Measures of Uncertainty for Adversarial Example Detection
Lewis Smith, Yarin Gal
IDK Cascades: Fast Deep Learning by Learning not to Overthink
Xin Wang, Yujia Luo, Daniel Crankshaw, Alexey Tumanov, Fisher Yu, Joseph E. Gonzalez
Differential Analysis of Directed Networks
Min Ren, Dabao Zhang
Sequential Learning under Probabilistic Constraints
Amirhossein Meisami, Henry Lam, Chen Dong, Abhishek Pani
Abstraction Sampling in Graphical Models
Filjor Broka, Rina Dechter, Alexander Ihler, Kalev Kask
Fast Stochastic Quadrature for Approximate Maximum-Likelihood Estimation
Nico Piatkowski, Katharina Morik
A Unified Particle-Optimization Framework for Scalable Bayesian Sampling
Changyou Chen, Ruiyi Zhang, Wenlin Wang, Bai Li, Liqun Chen
An Efficient Quantile Spatial Scan Statistic for Finding Unusual Regions in Continuous Spatial Data with Covariates
Travis Moore, Weng-Keen Wong
Battle of Bandits
Aadirupa Saha, Aditya Gopalan
Fast Kernel Approximations for Latent Force Models and Convolved Multiple-Output Gaussian processes
Cristian Guarnizo, Mauricio Álvarez
Fast Policy Learning through Imitation and Reinforcement
Ching-An Cheng, Xinyan Yan, Nolan Wagener, Byron Boots
Dissociation-Based Oblivious Bounds for Weighted Model Counting
Li Chou, Wolfgang Gatterbauer, Vibhav Gogate
Block-Value Symmetries in Probabilistic Graphical Models
Gagan Madan, Ankit Anand, Mausam, Parag Singla
PAC-Reasoning in Relational Domains
Ondrej Kuzelka, Yuyi Wang, Jesse Davis, Steven Schockaert
Causal Identification under Markov Equivalence
Amin Jaber, Jiji Zhang, Elias Bareinboim
Reforming Generative Autoencoders via Goodness-of-Fit Hypothesis Testing
Aaron Palmer, Dipak Dey, Jinbo Bi
Causal Discovery with Linear Non-Gaussian Models under Measurement Error: Structural Identifiability Results
Kun Zhang, Mingming Gong, Joseph Ramsey, Kayhan Batmanghelich, Peter Spirtes, Clark Glymour
Back to schedule

Poster Session - August 9th - Thursday

Testing for Conditional Mean Independence with Covariates through Martingale Difference Divergence
Ze Jin, Xiaohan Yan, David S. Matteson
Analysis of Thompson Sampling for Graphical Bandits Without the Graphs
Fang Liu, Zizhan Zheng, Ness Shroff
Structured nonlinear variable selection
Magda Gregorova, Alexandros Kalousis, Stephane Marchand-Maillet
Learning Deep Hidden Nonlinear Dynamics from Aggregate Data
Yisen Wang, Bo Dai, Lingkai Kong, Sarah Monazam Erfani, James Bailey, Hongyuan Zha
Revisiting differentially private linear regression: optimal and adaptive prediction & estimation in unbounded domain
Yu-Xiang Wang
Imaginary Kinematics
Sabina Marchetti, Alessandro Antonucci
Frank-Wolfe Optimization for Symmetric-NMF under Simplicial Constraint
Han Zhao, Geoff Gordon
Transferable Meta Learning Across Domains
Bingyi Kang, Jiashi Feng
Nesting Probabilistic Programs
Tom Rainforth
Scalable Algorithms for Learning High-Dimensional Linear Mixed Models
Zilong Tan, Kimberly Roche, Xiang Zhou, Sayan Mukherjee
Constraint-based Causal Discovery for Non-Linear Structural Causal Models with Cycles and Latent Confounders
Patrick Forré, Joris M. Mooij
A unified probabilistic model for learning latent factors and their connectivities from high-dimensional data
Ricardo Pio Monti, Aapo Hyvarinen
Improved Stochastic Trace Estimation using Mutually Unbiased Bases
JK Fitzsimons, MA Osborne, SJ Roberts, JF Fitzsimons
Graph-based Clustering under Differential Privacy
Rafael Pinot, Anne Morvan, Florian Yger, Cedric Gouy-Pailler, Jamal Atif
Causal Learning for Partially Observed Stochastic Dynamical Systems
Søren Wengel Mogensen, Daniel Malinsky, Niels Richard Hansen
Simple and practical algorithms for $\ell_p$-norm low-rank approximation
Anastasios Kyrillidis
Bandits with Side Observations: Bounded vs. Logarithmic Regret
Rémy Degenne, Evrard Garcelon, Vianney Perchet
Unsupervised Learning of Latent Physical Properties Using Perception-Prediction Networks
David Zheng, Vinson Luo, Jiajun Wu, Joshua Tenenbaum
Identification of Personalized Effects Associated With Causal Pathways
Ilya Shpitser, Eli Sherman
Sparse-Matrix Belief Propagation
Reid Bixler, Bert Huang
Meta Reinforcement Learning with Latent Variable Gaussian Processes
Steindor Saemundsson, Katja Hofmann, Marc Peter Deisenroth
Non-Parametric Path Analysis in Structural Causal Models
Junzhe Zhang, Elias Bareinboim
Stochastic Layer-Wise Precision in Deep Neural Networks
Griffin Lacey, Graham W. Taylor, Shawki Areibi
Estimation of Personalized Effects Associated With Causal Pathways
Razieh Nabi, Phyllis Kanki, Ilya Shpitser
Combinatorial Bandits for Incentivizing Agents with Dynamic Preferences
Tanner Fiez, Shreyas Sekar, Liyuan Zheng, Lillian Ratliff
Finite-sample Bounds for Marginal MAP
Qi Lou, Rina Dechter, Alexander Ihler
Acyclic Linear SEMs Obey the Nested Markov Property
Ilya Shpitser, Robin Evans, Thomas S. Richardson
Adaptive Stochastic Dual Coordinate Ascent for Conditional Random Fields
Rémi Le Priol, Alexandre Piché, Simon Lacoste-Julien
Averaging Weights Leads to Wider Optima and Better Generalization
Pavel Izmailov, Dmitrii Podoprikhin, Timur Garipov, Dmitry Vetrov, Andrew Gordon Wilson
Counterfactual Normalization: Proactively Addressing Dataset Shift Using Causal Mechanisms
Adarsh Subbaswamy, Suchi Saria
Probabilistic Collaborative Representation Learning for Personalized Item Recommendation
Aghiles Salah, Hady W. Lauw
Towards Flatter Loss Surface via Nonmonotonic Learning Rate Scheduling
Sihyeon Seong, Yegang Lee, Youngwook Kee, Dongyoon Han, Junmo Kim
A Lagrangian Perspective on Latent Variable Generative Models
Shengjia Zhao, Jiaming Song, Stefano Ermon
Back to schedule






Golden Sponsor



Bronze Sponsor



Startup Sponsor