Amit Deshpande
Papers
1
Total Citations
39
H-Index
1
About
Amit Deshpande is a leading researcher in machine learning and optimization, with a core focus on bandit algorithms, Gaussian processes, and determinantal point processes. His most influential work, "Batched Gaussian Process Bandit Optimization via Determinantal Point Processes" (2016, 39 citations), addresses a critical bottleneck in hyper-parameter optimization: the prohibitive cost of evaluating noisy black-box functions, where each evaluation can require days of computation. Deshpande’s key contribution lies in designing a batched selection strategy that leverages determinantal point processes to efficiently explore the parameter space, significantly reducing the number of expensive evaluations needed. This work has been foundational for advancing practical Bayesian optimization in high-stakes settings like automated machine learning and experimental design. Beyond this, his research bridges theoretical rigor with real-world efficiency, earning him recognition for tackling computationally intensive problems. With a citation impact that underscores the relevance of his methods, Deshpande continues to shape how researchers optimize complex systems, making his work essential reading for anyone interested in scaling bandit optimization to resource-constrained tasks.
Research Focus
Key Achievements
Top Papers
- 1