Main content start

Student Learning Seminar on Mathematics and Computation

Organizers: Henry Bosch and Shurui Liu

Upcoming Events

May
20
Date1:30 PM
Location
384H
Speaker
Shengtong Zhang (Stanford & Cursor)

Starting from first principles, I will derive (a variant of) the GRPO algorithm, one of the most widely used algorithms for post-training large language models. Then I will sketch how this algorithm is implemented at scale. Finally, I will briefly describe an important open problem known as…

May
27
Date1:30 PM
Location
384H
Speaker
Fred Rajasekaran (Stanford)

TBA: RL/MCTS, AlphaZero

Jun
03
Date1:30 PM
Location
384H
Speaker
Sheng Zha (Amazon)

TBA: Mathematical Questions in Pretraining

Jun
10
Date1:30 PM
Location
384H
Speaker
Taylor Mitchell (ETH Zurich)

My first productive experience using large language models occurred in October 2024. At the time, we were thinking about the hot spots conjecture, and a very lucky prompt gave us a key insight that helped us establish an interesting result on the extremal failure of this conjecture. I will…

Past Events

May
13
Date1:30 PM
Location
384H
Speaker
Selim Amar (Stanford)

In this talk, I will attempt to survey the recent applications of neural networks to PDEs with a focus on two approaches. I will start by introducing physics-informed neural networks and how they have been applied to discovering unstable singular solutions to fluid equations. Then, I will finish…

May
06
Date1:15 PM
Location
384H
Speaker
Otis Chodosh (Stanford)

I will describe some potential (but thus far largely unsuccessful) applications of ML techniques to proof discovery in geometric analysis.

Apr
29
Date1:00 PM
Location
384H
Speaker
Henry Bosch (Stanford)

Machine learning is usually presented as function approximation: in supervised learning, one aims to recover an unknown map from inputs to outputs, and results such as universal approximation theorems and generalization bounds explain why neural networks can, in principle, learn rich function…

Apr
22
Date1:00 PM
Location
384H

We will meet to discuss organizational matters (topic of interest, etc.)