Sandesh Adhikary
About Me
I'm a PhD student at the Paul G. Allen School of Computer Science at the University of Washington , advised by Professor Byron Boots.
My research has been centered around a variety of machine learning methods and applications, the common thread across which has been to identify and utilize geometric structure when it exists. I have worked on understanding and applying quantum-inspired probabilistic models for sequential data. Recently, I worked on incorporating geometric information about data spaces into sampling algorithms. Currently, I am working on designing metric-informed reinforcement learning algorithms that exploit geometric structure in MDPs to improve generalization and transfer.
Publications
In Review
BeigeMaps: Behavioral Eigenmaps for Reinforcement Learning from Images
Adhikary, S., Li. A, & Boots, B. (2024). BeigeMaps: Behavioral Eigenmaps for Reinforcement Learning from Images. In Review at the International Conference on Machine Learning (ICML)
Sampling over Riemannian Manifolds using Kernel Herding
Adhikary, S. & Boots, B. (2022). Sampling over Riemannian Manifolds using Kernel Herding. IEEE International Conference on Robotics and Automation (ICRA)
* denotes equal contribution
Quantum Tensor Networks, Stochastic Processes, and Weighted Automata
Adhikary, S.*, Srinivasan, S.*, Miller, J., Rabusseau, G. and Boots, B., (2021). Quantum Tensor Networks, Stochastic Processes, and Weighted Automata. In International Conference on Artificial Intelligence and Statistics (AISTATS)
* denotes equal contribution
Expressiveness and Learning of Hidden Quantum Markov Models
Adhikary, S.*, Srinivasan, S.*, Gordon, G., & Boots, B. (2020). Expressiveness and Learning of Hidden Quantum Markov Models. In International Conference on Artificial Intelligence and Statistics (AISTATS)
Refereed Workshops and Extended Abstracts
Modular Policy Composition with Policy Centroids
Extended AbstractAdhikary, S. & Boots, B. (2022). Modular Policy Composition with Policy Centroids. Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM)
Towards a Trace-Preserving Tensor Network Representation of Quantum Channels
Srinivasan, S., Adhikary S., Miller, J., Pokharel, B., Rabusseau, G. and Boots, B., (2021). Towards a Trace-Preserving Tensor Network Representation of Quantum Channels. Second Workshop on Quantum Tensor Networks in Machine Learning at NeurIPS.
Sampling over Riemannian Manifolds with Kernel Herding Winner of best workshop paper award!
Adhikary, S., Thompson, J., and Boots, B., (2021). Sampling over Riemannian Manifolds with Kernel Herding. Robotics: Science and Systems (R:SS 2021) Workshop on Geometry and Topology in Robotics