Optimization group meeting (Spring 2020)

Time: 13:00 - 16:00 on Wednesdays

Location: Amos Eaton Hall 402

Participants

Regular participants: Profs. Rongjie Lai, John Mitchell, and Yangyang Xu's group members.

For others: anyone is welcome to join us if you are interested in the topic to be presented.

Schedules

• March 04

  • Yonggui Yan, Multi-Agent Reinforcement Learning via Double Averaging Primal-Dual Optimization

• Feb. 26

  • Gabe Mancino-Ball, Accelerated Distributed Gradient Descent

• Feb. 19

  • Colin Sutcher-Shepard, Differential privacy and deep learning

• Feb. 12

  • Yonggui Yan, Equivalence between policy gradients and soft Q-learning

• Feb. 05

  • Gabe Mancino-Ball, Asynchronous Decentralized Consensus Optimization

• Jan. 29

  • Yonggui Yan, Combining policy gradient and Q-learning

• Jan. 22

  • Yonggui Yan, policy gradient in reinforcement learning

• Jan. 15

  • Gabe Mancino-Ball, A decentralized primal-dual method for constrained minimization of a strongly convex function

• Jan. 08 (at AE411)

  • Yuejiao Sun, LASG: Lazily Aggregated Stochastic Gradients for Communication-Efficient Distributed Learning

Previous meetings

• Fall 2019

• Spring 2019