Brian Ziebart

Professor

Department of Computer Science

Contact

Building & Room:

3-190H LIB

Address:

801 S. Morgan St., Chicago, IL, 60607

Office Phone:

312.355.1733

Email:

bziebart@uic.edu

About

I am primarily interested in machine learning and its applications to problems in robotics, assistive technologies, and human-computer interaction. I develop and apply new techniques for predicting structured data. I was awarded a Ph.D. in Machine Learning from Carnegie Mellon University in 2010.

Research:

Adversarial prediction: Approximating our training data and optimizing over the exact performance measure to provide greater flexibility for:

Learning under covariate shift (input distribution bias) and active learning;
Cost-sensitive classification and inductive optimization of univariate performance measures;
Learning to optimize for F-measure, discounted cumulative gain, and other multivariate performance measures; and
Structured prediction problems over sequences, trees, graphs, etc.

Inverse optimal control: Using maximum entropy structured prediction techniques to forecast future human behavior for intelligent robotics and vehicle navigation applications.

My research is supported by the following grants:

NSF CAREER (RI)-1652530: Adversarial Machine Learning for Structured Prediction
NSF EAGER (SCH)-1650900: The Virtual Assistant Health Coach: Summarization and Assessment of Goal-Setting Dialogues with Barbara Di Eugenio, Ben Gerber, Bing Liu, and Lisa Sharp
NSF IIS-1526379: Robust Optimization of Loss Functions with Application to Active Learning with Lev Reyzin
NSF III-1514126: Computational tools for extracting individual, dyadic, and network behavior from remotely sensed data with Tanya Berger-Wolf and Meg Crofoot
Future of Life Institute: Towards Safer Inductive Learning
NSF NRI-1227495: Purposeful Prediction: Co-robot Interaction via Understanding Intent and Goals (sub-contract) with Drew Bagnell, Martial Hebert, Anind Dey, Dieter Fox, Josh Tenenbaum

Selected Publications

ARC: Adversarial Robust Cuts for Semi-Supervised and Multi-Label Classification [pdf]

Sima Behpour, Wei Xing, and Brian D. Ziebart

AAAI Conference on Artificial Intelligence, 2018.

ADA: A Game-Theoretic Perspective on Data Augmentation for Object Detection [pdf]

Sima Behpour, Kris M. Kitani, and Brian D. Ziebart

arXiv, 2017.

Adversarial Structured Prediction for Multivariate Measures [pdf]

Hong Wang, Ashkan Rezaei, and Brian D. Ziebart

arXiv, 2017.

Adversarial Surrogate Losses for Ordinal Regression [pdf]

Rizal Fathony, Mohammad Bashiri, and Brian D. Ziebart

Advances in Neural Information Processing Systems (NIPS), 2017.

Goal-Predictive Robotic Teleoperation from Noisy Sensors [pdf]

Chris Schultz, Sanket Gaurav, Mathew Monfort, Lingfei Zhang, and Brian D. Ziebart

International Conference on Robotics and Automation (ICRA), 2017.

Adversarial Multiclass Classification: A Risk Minimization Perspective [pdf]

Rizal Fathony, Anqi Liu, Kaiser Asif, and Brian D. Ziebart

Advances in Neural Information Processing Systems (NIPS), 2016.

Adversarial Inverse Optimal Control for General Imitation Learning Losses and Embodiment Transfer [pdf]

Xiangli Chen, Mathew Monfort, Brian Ziebart, and Peter Carr

Uncertainty in Artificial Intelligence (UAI), 2016.

Adversarial Sequence Tagging [pdf]

Jia Li, Kaiser Asif, Hong Wang, Brian D. Ziebart, and Tanya Berger-Wolf

International Joint Conference on Artificial Intelligence (IJCAI), 2016.

Robust Covariate Shift Regression [pdf]

Xiangli Chen, Mathew Monfort, Anqi Liu, and Brian D. Ziebart

International Conference on Artificial Intelligence and Statistics (AISTATS), 2016.

Adversarial Prediction Games for Multivariate Losses [pdf]

Hong Wang, Wei Xing, Kaiser Asif, and Brian D. Ziebart

Advances in Neural Information Processing Systems (NIPS), 2015.

Softstar: Heuristic-Guided Probabilistic Inference [pdf]

Mathew Monfort, Brenden Lake, Brian Ziebart, Patrick Lucey, and Joshua Tenenbaum

Advances in Neural Information Processing Systems (NIPS), 2015.

Context Retrieval for Web Tables [pdf]

Hong Wang, Anqi Liu, Jing Wang, Brian D. Ziebart, Clement T. Yu, Warren Shen

International Conference on The Theory of Information Retrieval (ICTIR), 2015.

Adversarial Cost-Sensitive Classification [pdf]

Kaiser Asif, Wei Xing, Sima Behpour, Brian D. Ziebart

International Conference on Uncertainty in Artificial Intelligence (UAI),2015.

Graph-Based Inverse Optimal Control for Robot Manipulation[pdf]

Arunkumar Byravan, Mathew Monfort, Brian Ziebart, Byron Boots, Dieter Fox

International Joint Conference on Artificial Intelligence (IJCAI), 2015.

Predictive Inverse Optimal Control for Linear-Quadratic-Gaussian Systems [pdf]

Xiangli Chen and Brian D. Ziebart

International Conference on Artificial Intelligence and Statistics (AISTATS), 2015.

A Sense-Topic Model for Word Sense Induction with Unsupervised Data Enrichment [pdf]

Jing Wang, Mohit Bansal, Kevin Gimpel, Brian D. Ziebart, and Clement T. Yu

Transactions of the Association for Computational Linguistics, 2015.

Shift-Pessimistic Active Learning Using Robust Bias-Aware Prediction [pdf]

Anqi Liu, Lev Reyzin, and Brian D. Ziebart

AAAI Conference on Artificial Intelligence, 2015.

Intent Prediction and Trajectory Forecasting via Predictive Inverse Linear-Quadratic Regulation [pdf]

Mathew Monfort, Anqi Liu, and Brian D. Ziebart

AAAI Conference on Artificial Intelligence, 2015.

Robust Classification Under Sample Selection Bias [pdf]

Anqi Liu and Brian D. Ziebart

Advances in Neural Information Processing Systems (NIPS), 2014.

Spotlight Presentation

Layered Hybrid Inverse Optimal Control for Learning Robot Manipulation from Demonstration [pdf]

Arunkumar Byravan, Mathew Monfort, Brian D. Ziebart, Byron Boots, and Dieter Fox

NIPS Workshop on Autonomous Learning Robots, 2014.

Trajectory Forecasting and Intent Recognition via Predictive Inverse Linear-Quadratic Regulation [pdf]

Mathew Monfort, Anqi Liu and Brian D. Ziebart

IROS Workshop on Assistance and Service Robotics in a Human Environment, 2014.

Robust Structure Estimation of Maximum Causal Entropy Processes [pdf]

Brian D. Ziebart

Annual Allerton Conference on Communication, Control, and Computing, 2013.

TherML: Occupancy Prediction for Thermostat Control [pdf]

Christian Koehler, Brian D. Ziebart, Jennifer Mankoff, and Anind K. Dey

ACM Joint Conference on Pervasive and Ubiquitous Computing,2013.

Discriminative System Identification via the Principle of Maximum Causal Entropy

Xiangli Chen and Brian D. Ziebart

ICML Workshop on Machine Learning For System Identification,2013.

The Principle of Maximum Causal Entropy for Estimating Interacting Processes [pdf]

Brian D. Ziebart, J. Andrew Bagnell, and Anind K. Dey

IEEE Transactions on Information Theory, 2013.

Activity Forecasting [pdf]

Kris M. Kitani, Brian D. Ziebart, J. Andrew Bagnell, and Martial Hebert

European Conference on Computer Vision (ECCV), 2012.

Best Paper Runner-Up

Probabilistic Pointing Target Prediction via Inverse Optimal Control [pdf]

Brian D. Ziebart, Anind K. Dey, and J. Andrew Bagnell

International Conference on Intelligent User Inferfaces (IUI), 2012.

Best Paper Nominee

Identifying Culture and Leveraging Cultural Differences in Negotiations for Negotiation Agents [pdf]

Brian D. Ziebart, Miro Dudik, Geoff Gordon, Katia Sycara, Wendi Adair, Jeanne Brett

Hawaii International Conference on System Science (HICSS), 2012.

Factorized Decision Forecasting via Combining Value-based and Reward-based Estimation [pdf]

Brian D. Ziebart

Allerton Conference on Communication, Control, and Computing (Allerton), 2011.

Process-Conditioned Investing with Incomplete Information using Maximum Causal Entropy [pdf]

Brian D. Ziebart

International Workshop on Bayesian Inference and Maximum Entropy Methods in Science and Engineering (MaxEnt), 2011.

Computational Rationalization: The Inverse Equilibrium Problem[pdf]

Kevin Wuagh, Brian D. Ziebart, and J. Andrew Bagnell

International Conference on Machine Learning (ICML), 2011.

Best Paper Award

Maximum Causal Entropy Correlated Equilibria for Markov Games [pdf]

Brian D. Ziebart, J. Andrew Bagnell, and Anind K. Dey

International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2011.

Learning Patterns of Pick-ups and Drop-offs to Support Busy Family Coordination [pdf]

Scott Davidoff, Brian D. Ziebart, John Zimmerman, and Anind K. Dey

SIG CHI Conference on Human Factors in Computing Systems (CHI), 2011.

Modeling Purposeful Adaptive Behavior with the Principle of Maximum Causal Entropy [pdf]

Brian D. Ziebart

PhD Thesis. Department of Machine Learning, Carnegie Mellon University, December, 2010.

School of Computer Science Distinguished Dissertation Award, Honorable Mention

Modeling Interaction via the Principle of Maximum Causal Entropy [pdf]

Brian D. Ziebart and J. Andrew Bagnell and Anind K. Dey

International Conference on Machine Learning (ICML), 2010.

Best Student Paper Runner-Up

Planning-based Prediction for Pedestrians [pdf]

Brian D. Ziebart, Nathan Ratliff, Garratt Gallagher, Christoph Mertz, Kevin Peterson, J. Andrew Bagnell, Martial Hebert, Anind K. Dey, and Siddhartha Srinivasa

Proc. International Conference on Intelligent Robotics and Systems (IROS), 2009.

Inverse Optimal Heuristic Control for Imitation Learning [pdf]

Nathan Ratliff, Brian Ziebart, Kevin Peterson, J. Andrew Bagnell, Martial Hebert, Anind K. Dey, and Siddhartha Srinivasa

Proc. Aritifical Intelligence and Statistics (AISTATS), 2009.

Human Behavior Modeling with Maximum Entropy Inverse Optimal Control [pdf]

Brian D. Ziebart, Andrew Maas, J. Andrew Bagnell, and Anind K. Dey

AAAI Spring Symposium on Human Behavior Modeling, 2009.

Navigate Like a Cabbie: Probabilistic Reasoning from Observed Context-Aware Behavior [pdf]

Brian D. Ziebart, Andrew Maas, Anind K. Dey, and J. Andrew Bagnell

Proc. International Conference on Ubiquitous Computing (Ubicomp),2008.

Fast Planning for Dynamic Preferences [pdf]

Brian D. Ziebart, Anind K. Dey, and J. Andrew Bagnell