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 …
Cancer is a disease resulting from genomic mutations that occur during an individual's lifetime and cause the uncontrolled growth of a collection of cells into …
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 …
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 …
Hot environments pose a risk of heat illness for many professions especially when heavy workloads or protective clothing are necessary. Modern wearable sensors may be …
In order to intuitively and efficiently collaborate with humans, robots must learn to complete tasks specified using natural language. Natural language instructions can have many …
Apps provide valuable utility and customizability to a range of user devices, but installation of third-party apps also presents significant security risks. Many app systems …
The current paradigm in health tracking research, as performed in fields such as public health, social sciences, and research initiatives like mHealth, is to find …
The analysis of the statistical properties of data is a core goal in computer science. The challenges encountered in this task have evolved through time …
Generally intelligent agents must learn and plan in complex environments, with sensors and actuators that support various behaviors and tasks. This complexity hinders decision making, …
A natural language parser recovers the latent grammatical structures of sentences. In many natural language processing (NLP) applications, parsing is applied to sentences first and …
Neural networks continually surprise us. Many of these surprises are cases of impressive generalization. Others, however, are embarrassing failures. For example, large language models can …
We develop a family of algorithms for statistical inference in models of high dimensional continuous random variables. Our approach builds on existing variational methods, which …