research
publications by categories in reversed chronological order. generated by jekyll-scholar.
I’ve had the privilege of working on various research projects in reinforcement learning, theoretical computer science, and applied machine learning. See a list of publications below, or check out my Google Scholar for a more up-to-date list.
2023
- Loss of plasticity in continual deep reinforcement learningarXiv preprint arXiv:2303.07507 2023
- Beyond Implicit Bias: The Insignificance of SGD Noise in Online LearningarXiv preprint arXiv:2306.08590 2023
- Policy Gradient Methods in the Presence of Symmetries and State AbstractionsarXiv preprint arXiv:2305.05666 2023
2022
- Continuous MDP Homomorphisms and Homomorphic Policy Gradient2022
- Lower bound methods for sign-rank and their limitationsIn Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques (APPROX/RANDOM 2022) 2022
- Boolean functions with small approximate spectral norm2022
- Leaf multiplicity in a Bienaymé-Galton-Watson treeDiscrete Mathematics & Theoretical Computer Science 2022
2021
- On the peel number and the leaf-height of Galton–Watson treesCombinatorics, Probability and Computing 2021
- Arithmetic subsequences in a random ordering of an additive setINTEGERS 2021
- Bridging the gap between supervised classification and unsupervised topic modelling for social-media assisted crisis managementarXiv preprint arXiv:2103.11835 2021
2020
- Using deep learning and social network analysis to understand and manage extreme floodingJournal of Contingencies and Crisis Management 2020
- A Study of Policy Gradient on a Class of Exactly Solvable ModelsarXiv preprint arXiv:2011.01859 2020