Research
Our research focuses on core foundational challenges integrating mathematical tools with real-world objectives to advance the state-of-the-art. We pursue ambitious use-inspired research, targeting frontier perceptual tasks in video, imaging and navigation.
Research Thrusts
-
Advanced Algorithms for Deep Learning
We create fast, provably efficient tools for training neural networks and searching parameter spaces. We develop new theories to rigorously explain successful heuristics.
-
Learning with Dynamic Data
Since datasets are constantly evolving, we research new algorithms and models that can incorporate context and changes at training and test time, including robustness to perturbations.
-
Exploiting Structure in Data
What characteristics of a dataset help with training and inference? We define and uncover rich mathematical structures in datasets to improve downstream modeling and optimization.
-
Optimizing Real-World Objectives
We develop principled methods for automatically satisfying complex constraints and handling interactive feedback from users in real-world situations as is needed for safe robot navigation.
Use Inspired Applications
Key use cases include the integration of mathematical tools to advance breakthroughs in medical imaging, protein engineering, automated theorem proving, and open-source AI. Building on research themes initiated in 2020, we have since refined our focus to emphasize use-inspired research that aligns with our foundational thrusts and fosters multi-institutional collaboration. These efforts target areas where generative AI can drive global impact—enhancing medical care, accelerating vaccine development, expanding access to AI, and advancing mathematical and scientific discovery.
