Archive for month: November, 2021
Recent ML Studies
- Regret-Optimal Model-Free Reinforcement Learning for Discounted MDPs with Short Burn-In Time. (arXiv:2305.15546v1 [cs.LG])
- Sliced Optimal Partial Transport. (arXiv:2212.08049v8 [cs.LG] UPDATED)
- DoWG Unleashed: An Efficient Universal Parameter-Free Gradient Descent Method. (arXiv:2305.16284v1 [cs.LG])
- Quality Inference in Federated Learning with Secure Aggregation. (arXiv:2007.06236v4 [cs.LG] UPDATED)
- Near Optimal Adversarial Attack on UCB Bandits. (arXiv:2008.09312v4 [cs.LG] UPDATED)