Mathematics Colloquium
Event details
| Date | 25.09.2025 |
| Hour | 16:00 › 17:00 |
| Speaker | Prof. Philippe Rigollet, MIT |
| Location | |
| Category | Conferences - Seminars |
| Event Language | English |
Title :
A Mathematical Perspective on Transformers
Abstract :
Since their introduction in 2017, Transformers have revolutionized large language models and the broader field of deep learning. Central to this success is the groundbreaking self-attention mechanism. In this presentation, I’ll introduce a mathematical framework that casts this mechanism as a mean-field interacting particle system, revealing a desirable long-time clustering behavior. This perspective leads to a trove of fascinating questions with unexpected connections to Kuramoto oscillators, sphere packing, Wasserstein gradient flows, and slow dynamics.
Please register on the following form : https://forms.gle/M5pYkYZ3uMqTLHqS9
A Mathematical Perspective on Transformers
Abstract :
Since their introduction in 2017, Transformers have revolutionized large language models and the broader field of deep learning. Central to this success is the groundbreaking self-attention mechanism. In this presentation, I’ll introduce a mathematical framework that casts this mechanism as a mean-field interacting particle system, revealing a desirable long-time clustering behavior. This perspective leads to a trove of fascinating questions with unexpected connections to Kuramoto oscillators, sphere packing, Wasserstein gradient flows, and slow dynamics.
Please register on the following form : https://forms.gle/M5pYkYZ3uMqTLHqS9
Practical information
- Informed public
- Invitation required
Organizer
- Institute of Mathematic
Contact
- Pof. Lénaïc Chizat