Tarun Kathuria

About

Tarun Kathuria is a leading researcher in machine learning, with a primary focus on Bayesian optimization, Gaussian processes, and bandit algorithms—critical tools for tackling expensive, noisy black-box function optimization. His most-cited work, "Batched Gaussian Process Bandit Optimization via Determinantal Point Processes" (2016, 39 citations), introduced a novel framework that leverages determinantal point processes to efficiently select batches of evaluation points, dramatically reducing the number of costly function evaluations required in settings like hyperparameter tuning. This contribution addresses a fundamental bottleneck in machine learning, where training a single model can take days or weeks. Kathuria’s work has been instrumental in advancing the practicality of Bayesian optimization for large-scale problems, enabling faster and more resource-efficient experimentation. His research continues to shape how researchers and practitioners approach optimization in high-stakes, computationally intensive environments, making him a key figure in the ongoing evolution of automated machine learning and adaptive decision-making under uncertainty.

Research Focus

Key Achievements

Top Papers

1. 1
   Batched Gaussian Process Bandit Optimization via Determinantal Point\n Processes

   39 citations · 2016

Key Collaborators

Contact & Links