UAI 2019 – VIDEOS

All videos are available to watch both here and on the UAI 2019 YouTube Channel.
(Including invited speakers, students lectures, tutorials & presentations)

---

The Conference on Uncertainty in Artificial Intelligence (UAI) is one of the premier international conferences on research related to knowledge representation, learning, and reasoning in the presence of uncertainty. UAI is supported by the Association for Uncertainty in Artificial Intelligence (AUAI).

---

Tutorials:

22/07/19

Tutorial 1: Tractable Probabilistic Models: Representations, Algorithms, Learning, and Applications.
Guy Van den Broeck (UCLA), Nicola Di Mauro (Università degli Studi di Bari “Aldo Moro” ), Antonio Vergari (UCLA)

TPMTutorialUAI19

Tutorial 2: Mixing Graphical Models and Neural Nets Like Chocolate and Peanut Butter.
Matt Johnson (Google Brain)

mattj_tutorial

Tutorial 3: Causal Reinforcement Learning.
Elias Bareinboim (Columbia University)

Tutorial 4: Mathematics of Deep Learning.
Raja Giryes (Tel Aviv University)

Giryes_Theory2019

---

Main Conference:

23/07/19

Invited Speaker (Rina Dechter, UC Irvine): Anytime Probabilistic Reasoning.

Lecture (ID 264): Multi-Class Gaussian Process Classification Made Conjugate: Efficient Inference via Data Augmentation.
Théo Galy-Fajou, Florian Wenzel, Christian Donner, Manfred Opper

Multi-Class-Gaussian-Process-Classification-Made-Conjugate-Efficient-Inference-via-Data-Augmentation

Lecture (ID 356): Generating and Sampling Orbits for Lifted Probabilistic Inference.
Steven Holtzen, Todd Millstein, Guy Van den Broeck

Generating-and-Sampling-Orbits-for-Lifted-Probabilistic-Inference

Lecture (ID 6): Conditional Expectation Propagation.
Zheng Wang, Shandian Zhe

Conditional-Expectation-Propagation

Lecture (ID 221): Belief Propagation: Accurate Marginals or Accurate Partition Function – Where is the Difference?
Christian Knoll, Franz Pernkopf

Belief-Propagation-Accurate-Marginals-or-Accurate-Partition-Function

Lecture (ID 204): Sliced Score Matching: A Scalable Approach to Density and Score Estimation.
Yang Song, Sahaj Garg, Jiaxin Shi, Stefano Ermon

Sliced-Score-Matching-A-Scalable-Approach-to-Density-and-Score-Estimation

Lecture (ID 124): Random Sum-Product Networks: A Simple and Effective Approach to Probabilistic Deep Learning
Robert Peharz, Antonio Vergari, Karl Stelzner, Alejandro Molina, Martin Trapp, Xiaoting Shao, Kristian Kersting, Zoubin Ghahramani

Random-Sum-Product-Networks-A-Simple-and-Effective-Approach-to-Probabilistic-Deep-Learning

Lecture (ID 91): Towards a Better Understanding and Regularization of GAN Training Dynamics
Weili Nie, Ankit Patel

Towards-a-Better-Understanding-and-Regularization-of-GAN-Training-Dynamics

Lecture (ID 159): Neural Dynamics Discovery via Gaussian Process Recurrent Neural Networks
Qi She, Anqi Wu

Neural-Dynamics-Discovery-via-Gaussian-Process-Recurrent-Neural-Networks

Lecture (ID 164): Efficient Neural Network Verification with Exactness Characterization.
Krishnamurthy (Dj) Dvijotham, Robert Stanforth, Sven Gowal, Sven Gowal, Chongli Qin, Soham De, Pushmeet Kohli

Efficient-Neural-Network-Verification-with-Exactness-Characterization

Lecture (ID 253): Sinkhorn AutoEncoders
Giorgio Patrini, Rianne van den Berg, Patrick Forré, Marcello Carioni, Samarth Bhargav, Max Welling, Tim Genewein, Frank Nielsen

Sinkhorn-AutoEncoders

Lecture (ID 244): Learning with Non-Convex Truncated Losses by SGD.
Yi Xu, Shenghuo Zhu, Sen Yang, Chi Zhang, Rong Jin, Tianbao Yang

Learning-with-Non-Convex-Truncated-Losses-by-SGD

Invited Speaker (Suchi Saria, Johns Hopkins University): Safety Challenges with Black-Box Predictors and Novel Learning Approaches for Failure Proofing.

---

Main Conference:

24/07/19

Invited Speaker (Stefanie Jegelka, MIT): Safety Challenges with Black-Box Predictors and Novel Learning Approaches for Failure Proofing.

Lecture (ID 144): General Identifiability with Arbitrary Surrogate Experiments.
Sanghack Lee, Juan D. Correa, Elias Bareinboim

General-Identifiability-with-Arbitrary-Surrogate-Experiments

Lecture (ID 481): On Open-Universe Causal Reasoning.
Duligur Ibeling, Thomas Icard

On-Open-Universe-Causal-Reasoning

Lecture (ID 210): Approximate Causal Abstractions.
Sander Beckers, Frederick Eberhardt, Joseph Y. Halpern

Approximate-Causal-Abstraction

Lecture (ID 205): Beyond Structural Causal Models: Causal Constraints Models.
Tineke Blom, Stephan Bongers, Joris M. Mooij

Beyond-Structural-Causal-Models-Causal-Constraints-Models

Lecture (ID 512): Exclusivity Graph Approach to Instrumental Inequalities.
Davide Poderini, Rafael Chaves, Iris Agresti, Gonzalo Carvacho, Fabio Sciarrino

Exclusivity-graph-approach-to-Instrumental-inequalities

Lecture (ID 222): Finding Minimal d-separators in Linear Time and Applications.
Benito van der Zander, Maciej Liśkiewicz

Finding-minimal-d-separators-in-linear-time-and-applications

Invited Speaker (Emma Brunskill, Stanford University, CS Cornell): Towards Efficient Effective Reinforcement Learning Algorithms That Interact With People.

Lecture (ID 440): Off-Policy Policy Gradient with Stationary Distribution Correction.
Yao Liu, Adith Swaminathan, Alekh Agarwal, Emma Brunskill

Off-Policy-Policy-Gradient-with-State-Distribution-Correction

Lecture (ID 315): Wasserstein Fair Classification.
Ray Jiang, Aldo Pacchiano, Tom Stepleton, Heinrich Jiang, Silvia Chiappa

Wasserstein-Fair-Classification

Lecture (ID 158): A Fast Proximal Point Method for Computing Exact Wasserstein Distance.
Yujia Xie, Xiangfeng Wang, Ruijia Wang, Hongyuan Zha

A-Fast-Proximal-Point-Method-for-Computing-Exact-Wasserstein-Distance

---

Main Conference:

25/07/2019

Invited Speaker (Yee Whey Teh, University of Oxford & Deepmind): A Probabilistic Perspective on Meta and Reinforcement Learning. (Slides)

Lecture (ID 345): Exact Sampling of Directed Acyclic Graphs from Modular Distributions.
Topi Talvitie, Aleksis Vuoksenmaa, Mikko Koivisto

Exact-Sampling-of-Directed-Acyclic-Graphs-from-Modular-Distributions

Lecture (ID 468): Bayesian Optimization with Binary Auxiliary Information.
Yehong Zhang, Zhongxiang Dai, Bryan Kian Hsiang Low

Bayesian-Optimization-with-Binary-Auxiliary-Information

Lecture (ID 176): Perturbed-History Exploration in Stochastic Linear Bandits.
Branislav Kveton, Csaba Szepesvari, Mohammad Ghavamzadeh, Craig Boutilier

Perturbed-History-Exploration-in-Stochastic-Linear-Bandits

Lecture (ID 248): Cascading Linear Submodular Bandits: Accounting for Position Bias and Diversity in Online Learning to Rank.
Gaurush Hiranandani, Harvineet Singh, Prakhar Gupta, Iftikhar Ahamath Burhanuddin, Zheng Wen, Branislav Kveton

Cascading-Linear-Submodular-Bandits-Accounting-for-Position-Bias-and-Diversity-in-Online-Learning-to-Rank

Lecture (ID 267): A Flexible Framework for Multi-Objective Bayesian Optimization using Random Scalarizations.
Biswajit Paria, Kirthevasan Kandasamy, Barnabás Póczos

A-Flexible-Framework-for-Multi-Objective-Bayesian-Optimization-using-Random-Scalarizations

Lecture (ID 407): On the Relationship Between Satisfiability and Markov Decision Processes.
Ricardo Salmon, Pascal Poupart

On-the-Relationship-Between-Satisfiability-and-Markov-Decision-Processes

Lecture (ID 228): A Bayesian Approach to Robust Reinforcement Learning.
Esther Derman, Daniel J. Mankowitz, Timothy A. Mann, Shie Mannor

A-Bayesian-Approach-to-Robust-Reinforcement-Learning

Lecture (ID 191): An Improved Convergence Analysis of Stochastic Variance-Reduced Policy Gradient.
Pan Xu, Felicia Gao, Quanquan Gu

An-Improved-Convergence-Analysis-of-Stochastic-Variance-Reduced-Policy-Gradient

Lecture (ID 441): Co-training for Policy Learning.
Jialin Song, Ravi Lanka, Yisong Yue, Masahiro Ono

Co-training-for-Policy-Learning

Lecture (ID 21): Truly Proximal Policy Optimization.
Yuhui Wang, Hao He, Xiaoyang Tan

Truly-Proximal-Policy-Optimization

Lecture (ID 14): Correlated Learning for Aggregation Systems.
Tanvi Verma, Pradeep Varakantham

Correlated-Learning-for-Aggregation-Systems

Lecture (ID 49): Coordinating Users of Shared Facilities via Data-driven Predictive Assistants and Game Theory.
Philipp Geiger, Michel Besserve, Justus Winkelmann, Claudius Proissl, Bernhard Schoelkopf

Coordinating-Users-of-Shared-Facilities-via-Data-driven-Predictive-Assistants-and-Game-Theory

Lecture (ID 335): Literal or Pedagogic Human? Analyzing Human Model Misspecification in Objective Learning.
Smitha Milli, Anca D. Dragan

Literal-or-Pedagogic-Human-Analyzing-Human-Model-Misspecification-in-Objective-Learning

Lecture (ID 64): Randomized Iterative Algorithms for Fisher Discriminant Analysis.
Agniva Chowdhury, Jiasen Yang, Petros Drineas

Randomized-Iterative-Algorithms-for-Fisher-Discriminant-Analysis

Lecture (ID 28): Countdown Regression: Sharp and Calibrated Survival Predictions
Anand Avati, Tony Duan, Sharon Zhou, Ken Jung, Nigam H. Shah, Andrew Ng

Countdown-Regression-Sharp-and-Calibrated-Survival-Predictions

---

UAI 2019 will be held in Tel Aviv, Israel in July 2019.
EVENT PAGE
AGENDA
ACCEPTED PAPERS
SPEAKERS
TUTORIALS

---

The Association for Uncertainty in Artificial Intelligence is a non-profit organization focused on organizing the annual Conference on Uncertainty in Artificial Intelligence (UAI) and, more generally, on promoting research in pursuit of advances in knowledge representation, learning and reasoning under uncertainty. The most recent UAI conference was the 34th conference, UAI-2018 in Monterey, California, USA. Join our Facebook page or add yourself to the UAI Mailing list to keep updated on announcements and relevant AI news.

Principles and applications developed within the UAI community have been at the forefront of research in Artificial Intelligence. The UAI community and annual meeting have been primary sources of advances in graphical models for representing and reasoning with uncertainty.

Accessing Proceedings
The UAI conference has been held every year since 1985. Hardcopy versions of the proceedings can be purchased through Brightdoc.

Most UAI conference papers are available in electronic form at the online UAI proceedings archive.

• Collections of papers from the first six UAI conferences, 1985-1990, were published as edited books by North-Holland under the title Uncertainty in Artificial Intelligence (1-6).
• Between 1991 and 2003, proceedings were published by Morgan Kaufmann Publishers and were distributed at the conference by Morgan Kaufmann.
• Since 2004, the UAI proceedings have been published by the AUAI Press, the Association for Uncertainty in Artificial Intelligence’s own press.

---

Uncertainty in Artificial Intelligence’s facebook page
https://www.carlton.co.il/
Carlton Tel Aviv’s facebook page
http://www.auai.org/