Taskar Memorial Lecture 2018: M. Jordan (UC, Berkeley)
On Gradient-Based Optimization: Accelerated, Stochastic and Nonconvex
Abstract:
Many new theoretical challenges have arisen in the area of gradient-based optimization for large-scale statistical data analysis, driven by the needs of applications and the opportunities provided by new hardware and software platforms. I discuss several recent, related results in this area: (1) a new framework for understanding Nesterov acceleration, obtained by taking a continuous-time, Lagrangian/Hamiltonian/symplectic perspective, (2) a discussion of how to escape saddle points efficiently in nonconvex optimization, and (3) the acceleration of Langevin diffusion.
Bio:
Michael I. Jordan is the Pehong Chen Distinguished Professor in the Department of Electrical Engineering and Computer Science and the Department of Statistics at the University of California, Berkeley. His research interests bridge the computational, statistical, cognitive and biological sciences. Prof. Jordan is a member of the National Academy of Sciences, a member of the National Academy of Engineering and a member of the American Academy of Arts and Sciences. He has been named a Neyman Lecturer and a Medallion Lecturer by the Institute of Mathematical Statistics. He received the IJCAI Research Excellence Award in 2016, the David E. Rumelhart Prize in 2015 and the ACM/AAAI Allen Newell Award in 2009.
This video is closed captioned.
Видео Taskar Memorial Lecture 2018: M. Jordan (UC, Berkeley) канала Paul G. Allen School
Abstract:
Many new theoretical challenges have arisen in the area of gradient-based optimization for large-scale statistical data analysis, driven by the needs of applications and the opportunities provided by new hardware and software platforms. I discuss several recent, related results in this area: (1) a new framework for understanding Nesterov acceleration, obtained by taking a continuous-time, Lagrangian/Hamiltonian/symplectic perspective, (2) a discussion of how to escape saddle points efficiently in nonconvex optimization, and (3) the acceleration of Langevin diffusion.
Bio:
Michael I. Jordan is the Pehong Chen Distinguished Professor in the Department of Electrical Engineering and Computer Science and the Department of Statistics at the University of California, Berkeley. His research interests bridge the computational, statistical, cognitive and biological sciences. Prof. Jordan is a member of the National Academy of Sciences, a member of the National Academy of Engineering and a member of the American Academy of Arts and Sciences. He has been named a Neyman Lecturer and a Medallion Lecturer by the Institute of Mathematical Statistics. He received the IJCAI Research Excellence Award in 2016, the David E. Rumelhart Prize in 2015 and the ACM/AAAI Allen Newell Award in 2009.
This video is closed captioned.
Видео Taskar Memorial Lecture 2018: M. Jordan (UC, Berkeley) канала Paul G. Allen School
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
![](https://i.ytimg.com/vi/A958jqJLIIw/default.jpg)
![IST Austria Lecture "Computational thinking, inferential thinking & data science" by Michael Jordan](https://i.ytimg.com/vi/IK2Wccl6q6w/default.jpg)
![Chemical Engineering at UC Berkeley - Reflection](https://i.ytimg.com/vi/QI2ya2kXBog/default.jpg)
![Michael Jordan joins MBZUAI as laureate professor](https://i.ytimg.com/vi/qf0KiGlb_VY/default.jpg)
![Q&A with Christopher Bishop](https://i.ytimg.com/vi/tVKVduB9TUY/default.jpg)
![Perceptual Robot Learning (David Held, CMU)](https://i.ytimg.com/vi/CgknJCHEHHE/default.jpg)
![What is Statistics? (Michael I. Jordan) | AI Podcast Clips](https://i.ytimg.com/vi/AQUAPiHahVY/default.jpg)
![G-Research Lecture with Professor Michael I. Jordan on Artificial Intelligence](https://i.ytimg.com/vi/28TefyYoAm4/default.jpg)
![Distributional Robustness, Learning, and Empirical Likelihood](https://i.ytimg.com/vi/JBrrRFwi-yg/default.jpg)
![I Am Vengeance! I Am The Night! I Am Batman!](https://i.ytimg.com/vi/g7jxcEqE5ic/default.jpg)
![On Langevin Dynamics in Machine Learning - Michael I. Jordan](https://i.ytimg.com/vi/QTnjqdxG99c/default.jpg)
![Allen School Distinguished Lecture: Umesh Vazirani (UC Berkeley)](https://i.ytimg.com/vi/-isB7cKbxH0/default.jpg)
![Allen School Distinguished Lecture: Gabriel H. Loh (AMD)](https://i.ytimg.com/vi/97gPMIbYSNI/default.jpg)
![What It's Like Studying Computer Science | UC Berkeley](https://i.ytimg.com/vi/xQ0SGroZSyg/default.jpg)
![Mike Jordan, "Computational thinking, inferential thinking and Big Data"](https://i.ytimg.com/vi/ZYP8GWXh7lo/default.jpg)
![Allen School Distinguished Lecture: Shafi Goldwasser (UC Berkeley)](https://i.ytimg.com/vi/bqDOzGrXp3Q/default.jpg)
![Everything Michael B. Jordan Does in a Day | Vanity Fair](https://i.ytimg.com/vi/YHZzBrRDquA/default.jpg)
![Bayesian or Frequentist, Which Are You? By Michael I. Jordan (Part 1 of 2)](https://i.ytimg.com/vi/HUAE26lNDuE/default.jpg)
![Certifiable Outlier-Robust Geometric Perception: Robots that See through the Clutter with Confidence](https://i.ytimg.com/vi/AyFWNmyOSXw/default.jpg)
![5 סיבות ללמוד בביה"ס להנדסה ולמדעי המחשב באוניברסיטה העברית](https://i.ytimg.com/vi/wpgzIbFEGhA/default.jpg)