publications
2026
- Working paperLower Bound on Policy Gradient with Decreasing Stepsizes2026Working paper
2025
- NeurIPSREINFORCE Converges to Optimal Policies with Any Learning RateIn Advances in Neural Information Processing Systems, 2025Equal contribution between S. M. Robertson and T. D. Chu
2023
- IEEE/ACMGraph Transformer for Drug Response PredictionIEEE/ACM Transactions on Computational Biology and Bioinformatics, 2023