Meeting Calendar for CS 6784 Fall 2023
Date | # | Type | Topic & Materials |
---|---|---|---|
8/21 | 1 | Lecture | Overview & Supervised Learning (slides) |
8/23 | 2 | Lecture | Supervised Learning: Non-discrimination (slides) |
8/28 | 3 | Lecture | Supervised Learning: Least squares (slides) |
8/30 | 4 | Lecture | Online Learning via Online Convex Optimization (slides) |
9/4 | No Meeting: Labor Day | ||
9/6 | 5 | Lecture | Dynamical Systems: Equilibria and Stability (slides) |
9/11 | 6 | Lecture | Dynamical Systems: Nonlinear Stability (slides) |
9/13 | 7 | Lecture | Stochastic Dynamics and Input/Output Models (slides) |
9/18 | 8 | Lecture | State Estimation (slides) |
9/20 | 9 | Lecture | System Identification (slides) |
9/25 | 10 | Guest Lecture | Nonlinear System Identification by Yahya Sattar (slides) |
9/27 | 11 | Lecture | From Prediction to Actions: Bandits (slides) |
10/2 | 12 | Lecture | Contextual Bandits (slides) |
10/4 | 13 | Lecture | Optimal Control and Dynamic Programming (slides) |
10/9 | No Meeting: Fall Break | ||
10/11 | 14 | Lecture | Optimal Linear Control (slides) |
10/16 | 15 | Lecture | Adaptive & Robust Control (slides) |
10/18 | 16 | Lecture | Safe Control (slides) |
10/23 | 17 | Lecture | Receeding Horizon Control (slides) |
10/25 | 18 | Guest Lecture | Online Convex Optimization with Unbounded Memory by Raunak Kumar |
10/30 | 19 | Paper Presentation | [LKKLM21] Liu Leqi, Fatma Kilinc Karzan, Zachary Lipton, and Alan Montgomery. Rebounding bandits for modeling satiation effects. 2021. |
11/1 | 20 | Paper Presentations | [ZMSJ21] Tijana Zrnic, Eric Mazumdar, Shankar Sastry, and Michael Jordan. Who leads and who follows in strategic classification? 2021. [MJR20] Horia Mania, Michael I Jordan, and Benjamin Recht. Active learning for nonlinear system identification with guarantees. 2020. |
11/6 | 21 | Paper Presentations | [AD16] Shipra Agrawal and Nikhil Devanur. Linear contextual bandits with knapsacks. 2016. [JKL+20] Christopher Jung, Sampath Kannan, Changhwa Lee, Mallesh Pai, Aaron Roth, and Rakesh Vohra. Fair prediction with endogenous behavior. 2020. |
11/8 | 22 | Paper Presentations | [FGKM18] Maryam Fazel, Rong Ge, Sham Kakade, and Mehran Mesbahi. Global convergence of policy gradient methods for the linear quadratic regulator. 2018. [ER23] Itay Eilat, Nir Rosenfeld. Performative Recommendation: Diversifying Content via Strategic Incentives. 2023. |
11/13 | 23 | Paper Presentations | [FS20] Dylan Foster and Max Simchowitz. Logarithmic Regret for Adversarial Online Control. 2020. [YLN+23] Fan Yao, Chuanhao Li, Denis Nekipelov, Hongning Wang, Haifeng Xu. How Bad is Top-K Recommendation under Competing Content Creators? 2023. |
11/15 | 24 | Paper Presentations | [HPS16] Moritz Hardt, Eric Price, and Nati Srebro. Equality of opportunity in supervised learning. 2016. [IZY22] Zachary Izzo, James Zou, and Lexing Ying. How to learn when data gradually reacts to your model. 2022. |
11/20 | 25 | Paper Presentations | [LWH+20] Lydia T Liu, Ashia Wilson, Nika Haghtalab, Adam Tauman Kalai, Christian Borgs, and Jennifer Chayes. The Disparate Equilibria of Algorithmic Decision Making when Individuals Invest Rationally 2020. [TMP20] Anastasios Tsiamis, Nikolai Matni, and George Pappas. Sample complexity of kalman filtering for unknown systems. 2020. |
11/22 | No Meeting: Thanksgiving | ||
11/27 | 26 | Paper Presentations | [CMLH23] Xinyi Chen, Edgar Minasyan, Jason D Lee, and Elad Hazan. Regret guarantees for online deep control. 2023. [KTR19] Karl Krauth, Stephen Tu, and Benjamin Recht. Finite-time analysis of approximate policy iteration for the linear quadratic regulator. 2019. |
11/29 | 27 | Paper Presentations | [GHM23] Paula Gradu, Elad Hazan, and Edgar Minasyan. Adaptive regret for control of time-varying dynamics. 2023. [SR19] Tuhin Sarkar and Alexander Rakhlin. Near optimal finite time identification of arbitrary linear dynamical systems. 2019. |
12/4 | 28 | Paper Presentations | [TR19] Stephen Tu and Benjamin Recht. The gap between model-based and model-free methods on the linear quadratic regulator: An asymptotic viewpoint. 2019. [TZTS22] Yi Tian, Kaiqing Zhang, Russ Tedrake, Suvrit Sra. Can Direct Latent Model Learning Solve Linear Quadratic Gaussian Control? 2022. |