Area of research
Computational Mechanics · Artificial Intelligence
Research interest
Research interests include Sparse and Compressive Sensing Techniques, Stochastic Gradient Optimization Techniques, Control Systems and Identification, and Advanced Bandit Algorithms Research.
AI as an intervention: improving clinical outcomes relies on a causal approach to AI development and validation
Serverless linear algebra
KeystoneML: Optimizing Pipelines for Large-Scale Advanced Analytics
Gradient Descent Only Converges to Minimizers
Conference on Learning Theory 2016cited by 386position: last
Blind Deconvolution Using Convex Programming
Robust efficiency and actuator saturation explain healthy heart rate control and variability
Compressed Sensing Off the Grid
Atomic Norm Denoising With Applications to Line Spectral Estimation
Exact matrix completion via convex optimization
CIF:Small:A Systems Approach to Statistics for N-of-1 Experimental Trials
Collaborative Research: SLES: Bridging offline design and online adaptation in safe learning-enabled systems
CAREER: Efficient Atomic Decompositions of Massive Data Sets
CAREER: Efficient Atomic Decompositions of Massive Data Sets
Denoising, Decomposition, and Deconvolution of Moment Sequences by Convex Optimization