Area of research
Statistics and Probability · Artificial Intelligence
Research interest
Research interests include Statistical Methods and Inference, Sparse and Compressive Sensing Techniques, Stochastic Gradient Optimization Techniques, and Machine Learning and Algorithms.
A precise high-dimensional asymptotic theory for boosting and minimum-ℓ1-norm interpolated classifiers
Training Neural Networks as Learning Data-Adaptive Kernels: Provable Representation and Approximation Benefits
Statistical Inference for the Population Landscape via Moment-Adjusted Stochastic Gradients
Fisher-Rao Metric, Geometry, and Complexity of Neural Networks
DSpace@MIT (Massachusetts Institute of Technology) 2017cited by 36position: first