Game Theory in Machine Learning, part 1 - Costantinos Daskalakis - MLSS 2020, Tübingen
Table of Contents (powered by https://videoken.com)
0:00:00 Game Theory in Machine Learning, part 1 - Costantinos Daskalakis - MLSS 2020, Tübingen
0:01:20 Game Theory and Machine Learning
0:02:52 State
0:03:39 Future of A/: learning strategic reasoning
0:04:34 Example 1: Platform Design
0:06:16 Example 2: Recommender Systems
0:07:05 Example 3: Humanoid vs Spider
0:08:37 A dictum
0:11:42 Our focus: min-max optimization
0:13:46 Generative Adversarial Networks (GAN
0:20:50 Training Oscillations: Handwritten Digits
0:21:44 Training Oscillations: even for Gaussian data/bilinear objectives!
0:26:32 Training Oscillations: persistence for variants of Online Gradient Descent
0:27:12 What gives?
0:27:58 Menu
0:34:39 The Min-Max Theorem
0:43:51 Min-Max and No-Regret Learning
0:48:34 [Code Walkthrough]
0:57:19 Training Oscillations
0:59:07 Menu
1:00:22 Gradient Descent w/ Negative Momentum
1:04:04 Negative Momentum: why might it help?
1:07:04 Training Oscillations
1:11:19 Negative Momentum: convergence
1:12:03 Negative Momentum: why might it help?
1:18:54 Negative Momentum: constrained case
1:25:41 Menu
1:27:18 constrained case
1:27:23 Remark 1: Beyond "Last-Iterate"
1:29:39 Remark 3: GAN learning
1:31:48 Thanks!
1:39:16 MLSS 2020 Team
Видео Game Theory in Machine Learning, part 1 - Costantinos Daskalakis - MLSS 2020, Tübingen канала virtual mlss2020
0:00:00 Game Theory in Machine Learning, part 1 - Costantinos Daskalakis - MLSS 2020, Tübingen
0:01:20 Game Theory and Machine Learning
0:02:52 State
0:03:39 Future of A/: learning strategic reasoning
0:04:34 Example 1: Platform Design
0:06:16 Example 2: Recommender Systems
0:07:05 Example 3: Humanoid vs Spider
0:08:37 A dictum
0:11:42 Our focus: min-max optimization
0:13:46 Generative Adversarial Networks (GAN
0:20:50 Training Oscillations: Handwritten Digits
0:21:44 Training Oscillations: even for Gaussian data/bilinear objectives!
0:26:32 Training Oscillations: persistence for variants of Online Gradient Descent
0:27:12 What gives?
0:27:58 Menu
0:34:39 The Min-Max Theorem
0:43:51 Min-Max and No-Regret Learning
0:48:34 [Code Walkthrough]
0:57:19 Training Oscillations
0:59:07 Menu
1:00:22 Gradient Descent w/ Negative Momentum
1:04:04 Negative Momentum: why might it help?
1:07:04 Training Oscillations
1:11:19 Negative Momentum: convergence
1:12:03 Negative Momentum: why might it help?
1:18:54 Negative Momentum: constrained case
1:25:41 Menu
1:27:18 constrained case
1:27:23 Remark 1: Beyond "Last-Iterate"
1:29:39 Remark 3: GAN learning
1:31:48 Thanks!
1:39:16 MLSS 2020 Team
Видео Game Theory in Machine Learning, part 1 - Costantinos Daskalakis - MLSS 2020, Tübingen канала virtual mlss2020
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
![Vlog 05 Constantinos, Francis, and Marco](https://i.ytimg.com/vi/kMZKKrzbu3k/default.jpg)
![Deep Reinforcement Learning, part 2 - Doina Precup - MLSS 2020, Tübingen](https://i.ytimg.com/vi/pN3hfZ6WaE0/default.jpg)
![Bayesian Inference, part 2 - Shakir Mohamed - MLSS 2020, Tübingen](https://i.ytimg.com/vi/DItJbz2OH5U/default.jpg)
![Vlog 09 Shakir, Doina, Michael, and Maria](https://i.ytimg.com/vi/FjdGOQSCMx4/default.jpg)
![Vlog 04 Francis, Marco, and Moritz](https://i.ytimg.com/vi/hySWy2P6akc/default.jpg)
![Deep Learning, part 2 - Yoshua Bengio - MLSS 2020, Tübingen](https://i.ytimg.com/vi/PDPdIDihPvc/default.jpg)
![Vlog 03 Constantinos and Sonia](https://i.ytimg.com/vi/l6M6zTPjeXI/default.jpg)
![Optimal Transport, part 1 - Marco Cuturi - MLSS 2020, Tübingen](https://i.ytimg.com/vi/jgrkhZ8ovVc/default.jpg)
![Meta Learning, part 2 - Yee Whye Teh - MLSS 2020, Tübingen](https://i.ytimg.com/vi/WCREWkWGd6s/default.jpg)
![Vlog 08 Mihaela & Arthur](https://i.ytimg.com/vi/vLPkdL3h-MA/default.jpg)
![Vlog 10 Shakir, Maria, and Michael](https://i.ytimg.com/vi/azWxO52jKew/default.jpg)
![Vlog 02 Stefan Bernhard Nicolo](https://i.ytimg.com/vi/V1sR7BLRXVY/default.jpg)
![Optimization, part 2 - Francis Bach - MLSS 2020, Tübingen](https://i.ytimg.com/vi/hg2h53bU5ic/default.jpg)
![Vlog 07 Arthur, Mihaela, Yee Whye, and Yoshua](https://i.ytimg.com/vi/9w3iqRgW04c/default.jpg)
![Fairness, part 2 - Moritz Hardt - MLSS 2020, Tübingen](https://i.ytimg.com/vi/9oNVFQ9llPc/default.jpg)
![1st Week Recap Video -- MLSS 2020](https://i.ytimg.com/vi/P85YCGtRmxQ/default.jpg)
![Deep Reinforcement Learning, part 1 - Doina Precup - MLSS 2020, Tübingen](https://i.ytimg.com/vi/hoHXV4Ujavg/default.jpg)
![MLSS2020 Talent Show](https://i.ytimg.com/vi/XNTw7pUKcdY/default.jpg)
![Vlog 01 Bernhard, Nicolo, & Stefan](https://i.ytimg.com/vi/f8qs126YOeM/default.jpg)
![Vlog 06 Yoshua & Yee Whye](https://i.ytimg.com/vi/zDedjNnTBw4/default.jpg)
![Game Theory in Machine Learning, part 2 - Costantinos Daskalakis - MLSS 2020, Tübingen](https://i.ytimg.com/vi/yNsrHLpjkvo/default.jpg)