Advancing algorithms for machine learning and artificial intelligence
The world has celebrated many accomplishments in AI technologies, but thorny challenges remain. Our work bridges between theory and implementation to improve the accuracy, efficiency, security, and relevance of AI algorithms.
We tackle interesting and challenging problems in machine learning and large-scale data analysis by advancing innovative methods in statistics, algorithms, and computer science. This work is highly interdisciplinary, bringing cutting-edge mathematics to bear on optimizing algorithms and tools at the forefront of scientific research and AI applications.
Our research has examined:
- Random sampling and random projection methods
- Communication-avoiding algorithms
- Locally-biased graph algorithms
- Numerically-intensive machine learning
- Randomized linear algebra
- Convex and non-convex optimization
- Second-order optimization
- Terabyte-scale implementations
- Graph algorithm theory
- Geometric network analysis
- Parallel and distributed computing
- Applications in a wide range of domain areas, including astronomy, genetics, multimedia and social network analysis, and more
Areas of focus:
- Machine Learning (Supervised, Unsupervised, Reinforcement Learning)
- Mathematical Optimization, Operations Research, and Decision Science
- Theoretical Foundations of AI and Machine Learning
