Reinforcement learning defines the problem facing agents that learn to make good decisions through action and observation alone. To be effective problem solvers, such agents …
Just as an interconnected-computerized world has produced large amounts of data resulting in exciting challenges for machine learning, connected households with robots and smart devices …
I introduce novel concentration-of-measure bounds for the supremum deviation, several variance concepts, and a family of game-theoretic welfare functions. I then apply these bounds to …
Coreference Resolution is a fundamental natural language processing (NLP) problem, as it attempts to resolve which underlying discourse objects refer to one another. Further, it …
This dissertation primarily contributes to the visualization and visual analytics community. It offers findings and methods to expand the visualization design space and to deepen …
Future collaborative robots must be capable of finding objects. As such a fundamental skill, we expect object search to eventually become an off-the-shelf capability for …
In this work, I present an implemented model that can learn interactively from natural language, enabling non-expert human trainers to convey complex tasks to machines …
Combinatorial optimization problems are fundamental in many real-world applications, where the goal is to find the optimal or near-optimal solution to a problem subject to …
In both supervised and reinforcement settings, there exist learning problems that are hard due to having high computational or sample complexity. Researchers have shown, using …
We propose a general-purpose probabilistic framework for scene understanding tasks. We show that several classical scene understanding tasks can be modeled and addressed under a …
In the age of big data, uncertainty in data constantly grows with its volume, variety and velocity. Data is noisy, biased and error-prone. Compounding the …
Educational assessments are crucial for both instructors and education researchers to measure learning, troubleshoot student problems, evaluate pedagogy, and improve education. Unfortunately, creating and administering …
We develop Bayesian nonparametric statistical models of document collections and social networks. Extending classic parametric topic models of documents, and stochastic block models of networks, …
We develop new representations and algorithms for three-dimensional (3D) scene understanding from images and videos. To model cluttered indoor scenes, we introduce object descriptors that …
Neural network models have grown in popularity to be the dominant artificial intelligence paradigm of our time, succeeding across a variety of challenging tasks despite …
