Dissertation Defenses

Understanding Word Embedding Stability Across Languages and Applications

Machine Learning for Physiological Time Series: Representing and Controlling Blood Glucose for Diabetes Management

Towards the First Practical Applications of Quantum Computers

Enabling and Improving Centralized Control in Network and Cyber-Physical Systems: An Application-Driven Approach

Election Security is Harder Than You Think

Unsupervised Structural Embedding Methods for Efficient Collective Network Mining

A Parallel Tensor Network Contraction Algorithm and Its Applications in Quantum Computation

Learning to Generate 3D Training Data

Robust Deep Learning in the Open World with Lifelong Learning and Representation Learning

Learning Single-Image 3D from the Internet

Machine Learning in Adversarial Environments

Automatic Designs in Deep Neural Networks

Domain-specific Architectures for Data-intensive Applications

Efficient Belief Propagation for Perception and Manipulation in Clutter

Efficiently Finding Approximately-Optimal Queries for Improving Policies and Guaranteeing Safety

Enhancing System Transparency, Trust, and Privacy with Internet Measurement

Making and Keeping Probabilistic Commitments for Trustworthy Multiagent Coordination

Robust Scene Estimation for Goal-directed Robotic Manipulation in Unstructured Environments

Clarifying Oblique Specifications of Relational Queries

Improving Programming Support for Hardware Accelerators Through Automata Processing Abstractions

Democratizing Self-Service Data Preparation through Program Synthesis for Non-expert Users

Agent-based Models for Analyzing Strategic Adaptations to Government Regulation

Thwarting Advanced Code-reuse Attacks

Using Sensor Redundancy in Vehicles and Smartphones for Driving Security and Safety

Towards Seamless Human-Mobility Interaction

Runtime Systems for Persistent Memories

Enabling Usable and Performant Trusted Execution

Thermal and QoS-Aware Embedded Systems

Estimation of Information Measures and Applications in Machine Learning

Multimodal Character Representation for Visual Story Understanding