# Faculty

Machine Learning Department

Associate Research Professor

I'm interested in multi-agent planning, reinforcement learning, decision-theoretic planning, statistical models of difficult data (e.g. maps, video, text), computational learning theory, and game theory.

Machine Learning and Computer Science Departments

Finmeccanica Associate Professor

I am fundamentally interested in designing efficient algorithms that learn and adapt to changing environments, and that are both theoretically-founded and perform well in the real world. My main focus is on statistical machine learning and inference, and on applications in sensor networks and computer systems.

[Top]

# Graduate Students

Machine Learning Department

Advisor: Geoff Gordon

I am interested in machine learning and optimization applied to problems in computer vision and robotics.

Machine Learning Department

Advisor: Carlos Guestrin

I am interested in structure learning for probabilistic graphical models and using Graphics Processing Units to scale up machine learning methods.

Robotics Institute

Advisor: Carlos Guestrin

I am interested in principled ways to construct probabilistic models that accurately represent reality and at the same time are feasible for exact inference. More specifically, I am working on learning thin junction trees from data.

Computer Science Department

Advisor: Carlos Guestrin

I am interested in statistical machine learning algorithms that are scalable to large real-world data sets, with an emphasis on the Web. I am particularly interested in statistically principled ways for analyzing online news and blogs.

Robotics Institute

Advisor: Carlos Guestrin

I am interested in formalisms and algorithms for effectively addressing large-scale problems in Bayesian inference and machine learning. My research interests include graphical models, convex optimization, distributed algorithms, and their application to computer vision.

Machine Learning Department

Advisor: Carlos Guestrin

My research interests are in statistical machine learning, sensor networks, and designing algorithms that learn and adapt to changing environments.

Computer Science Department

Advisor: Geoff Gordon

I am interested in online decision problems where the environment or the problem changes over time and one must adapt and act accordingly. Currently I am looking at a general framework for such settings using mixed integer linear programs and first-order logic, as well as ideas from online learning and optimization.

Computer Science Department

Advisors: Carlos Guestrin and Guy Blelloch

I am 1st year PhD student (2009). I am currently working on parallel and distributed computing framework for machine learning algorithms.

Machine Learning Department

Advisor: Carlos Guestrin

I am 2nd year PhD student. I am currently working on designing efficient Machine Learning algorithms for Multicore and Cluster platforms.

Machine Learning Department

Advisor: Geoff Gordon

I'm interested in multiagent systems, with an emphasis on planning and learning under uncertainty in multiagent domains.

Computer Science Department

Advisor: Geoff Gordon

Currently I'm a 2nd year PhD student in Computer Science (Machine Learning Department) at Carnegie Mellon, being advised by Geoff Gordon.

Robotics Institute

Advisor: Norman Sadeh

I am a 3rd year PhD student. I am currently working on adaptive trading agents. I am generally interested in problems in game theory, multi-agent learning and control theory.

Robotics Institute

Advisor: Geoff Gordon

I work on efficient models and algorithms for machine learning on temporal data, and on applying these methods to problems in activity monitoring, mobile robotics and other domains.

Computer Science Department

Advisors: Manuel Blum and Carlos Guestrin

Just started my PhD at CMU; I am particularly interested in the ways applied AI can benefit from theoretical CS.

Machine Learning Department

Advisor: Geoff Gordon

I work on models for relational learning. Other areas of research include structure learning and inference in graphical models.

Computer Science Department

Advisor: Carlos Guestrin

I am interested in applying machine learning and optimization techniques to problems in large scale distributed systems such as fault diagnosis/prediction, system performance evaluation/improvement. I also work on planning under uncertainty (POMDPs).

[Top]

# Postdocs

Machine Learning Department

Postdoc

My main interests are in combining theoretical and applied aspects of machine learning and statistics. More specifically, I am interested in problems where the available data sets are small, but the dimension of the solution space is large. My previous work has focused on small sample density estimation with the main application in modeling species habitats. Currently, I am working on decision making under uncertainty in the context of multi-agent learning and planning.

Machine Learning Department

Postdoc

I am interested in bridging machine learning and parallel/distributed computing domains, typically by borrowing ML algorithms, distributing them and applying them to real large scale problems.

Lane Center and Machine Learning Department

Lane Fellow

I currently work on representations of probablistic graphical models using kernel (RKHS) methods. The application of kernel methods to inference in graphical models is fruitful not only in broadening the classes of data on which inference is tractable, but also in generalizing kernel techniques to more complex dependence structures. I am also interested in probabilistic inference on large-scale and distributed problems, and applications of machine learning to network analysis and computational biology.

iLab, Heinz College and Machine Learning Department

Postdoc

My research interests lie in interactive machine learning, structured prediction, information retrieval, and online algorithms. I am primarily interested in designing new methods for analyzing and accessing information, as well as in understanding how information systems can be improved through automated learning and refinement from user interaction.

[Top]

# Project Scientists

Machine Learning Department

Project Scientist

I currently work on representations of probability measures using kernel (RKHS) methods: current applications include nonparametric homogeneity testing (whether two groups of objects have a common distribution), independence testing (whether two observations are related), and conditional dependence testing. My future research interests include probabilistic inference on large-scale problems.

[Top]

# Masters Students

Jan Calliess

Machine Learning Department

Advisor: Geoff Gordon

My research interests are currently focused on multi-agent planning, learning- and game theory. I am a visiting student from University of Karlsruhe (TH), Germany.

[Top]

# Staff

Machine Learning Department

Research Programmer

I'm working with Geoff on some projects involving multi-agent planning, some game theory, scientific visualization, and so on.

[Top]

# Undergraduate

[Top]

# Alumni

University of Alberta

PhD student

Advisor: Carlos Guestrin

I work on creating probabilistic models that can be used to accurately estimate signal quality in wireless networks including building-wide and city-wide deployments of wireless access points.

Stanford University

Postdoctoral Fellow

My research interests lie in designing computationally efficient probabilistic reasoning and learning algorithms which allow computers to deal with the uncertainty and complexity inherent in real world data. My work has specifically focused on probabilistic reasoning and learning with combinatorial data, which arises in myriad applications such as modeling preference rankings over objects, tracking multiple moving objects, reconstructing the temporal ordering of events from multiple imperfect accounts and more.

California Institute of Technology

Assistant Professor, Computer Science Department

My research is in Active Sensing, using tools from decision theory, machine learning and sensor networks to reason about spatio-temporal phenomena. I work on efficient algorithms with theoretical guarantees, and apply them to problems such as traffic prediction, building automation, activity recognition and environmental monitoring.

Jeremy Maitin-Shepard

UC Berkeley

PhD Student

Working with Carlos Guestrin and Jonathan Huang

I am a undergraduate senior interested in approximate inference in principled probabilistic models for tracking and activity recognition.

Research

My primary interests are in Artificial Intelligence, particularly in planning and machine learning in the face of uncertainty and in adversarial environments.

University of Washington

Postdoc

Advisor: Joe Hellerstein and Carlos Guestrin

My research interests are in the area of database systems and my advisor is Joe Hellerstein. I am also co-advised by professor Carlos Guestrin at CMU I am currently working on query optimization in sensor networks, and I am specifically interested in power-efficient routing.

Robotics Institute

Postdoc

My general research interests lie in Artificial Intelligence and Robotics. More specifically, they currently cover planning in deterministic and probabilistic domains and machine learning. So far, my research has been mainly motivated by the problem of fast and intelligent decision making by autonomous robotic systems in real-world environments. I do get easily motivated, however, by other interesting problems in AI.

McGill University

Computer Science Department

My research is motivated by the desire to build intelligent autonomous systems meant for human interaction. My objectives are two-fold. First, I aim to develop broadly applicable probabilistic representations and algorithms that can address the problem of planning and control under uncertainty. Second, I am committed to designing and implementing real-world intelligent systems that operate based on these techniques.

Research

Since finishing up my work at CMU in Oct. 2004 I've been thoroughly enjoying my newfound free time on weekends learning rock climbing and Chinese.