Summer Graduate School

Popular visualization of the MNIST dataset

Learning theory is a rich field at the intersection of statistics, probability, computer science, and optimization. Over the last decades the statistical learning approach has been successfully applied to many problems of great interest, such as bioinformatics, computer vision, speech processing, robotics, and information retrieval. These impressive successes relied crucially on the mathematical foundation of statistical learning.

Recently, deep neural networks have demonstrated stunning empirical results across many applications like vision, natural language processing, and reinforcement learning. The field is now booming with new mathematical problems, and in particular, the challenge of providing theoretical foundations for deep learning techniques is still largely open. On the other hand, learning theory already has a rich history, with many beautiful connections to various areas of mathematics (e.g., probability theory, high dimensional geometry, game theory). The purpose of the summer school is to introduce graduate students (and advanced undergraduates) to these foundational results, as well as to expose them to the new and exciting modern challenges that arise in deep learning and reinforcement learning.

View all lectures on YouTube

Lectures are available via livestreaming during the scheduled time blocks, and for standard viewing at any time after recording is complete.

To get the most out of the mini-courses in the school, students are encouraged to attend all the lectures and minimize distractions. Please try to avoid the use of laptops, smartphones, tablets, etc. except for note-taking (because the material is highly mathematical, students will probably find it easier to use a pen and notebook).

For eligibility and how to apply, see the Summer Graduate Schools homepage

Suggested Prerequisites:

• Linear Algebra
  (e.g. https://ocw.mit.edu/courses/mathematics/18-06-linear-algebra-spring-2010/).
• Probability
  (e.g. https://ocw.mit.edu/courses/mathematics/18-05-introduction-to-probability-and-statistics-spring-2014/).
• Multivariable calculus
  (e.g. https://ocw.mit.edu/courses/mathematics/18-02sc-multivariable-calculus-fall-2010/).
• Real Analysis
  (e.g. https://ocw.mit.edu/courses/mathematics/18-100c-real-analysis-fall-2012/).

Due to the small number of students supported by MSRI, only one student per institution will be funded by MSRI.

This summer school is brought to you through the funding support of the academic sponsoring institutions of the Mathematical Sciences Research Institute, Berkeley, CA,  Microsoft Research, and the Paul G. Allen School of Computer Science and Engineering at the University of Washington, and in cooperation with the Algorithmic Foundations of Data Science Institute at the University of Washington.