The School of Computer Science at the University of Windsor is pleased to present…  

Colloquium Presentation by Dr. Fawzi: ”Discovering faster matrix multiplication algorithms with deep reinforcement learning” 

Date: Friday January 27, 2023

Time: 11:00am – 12:00pm

Location: Erie Hall, Room 3123

Reminders: 

1. Two-part attendance mandatory (sign-in sheet, QR Code)
2. Arrive 5-10 minutes prior to event starting – LATECOMERS WILL NOT BE ADMITTED. Note that due to demand, if the room has reached capacity, even if you are “early” admission is not guaranteed.
3. Please be respectful of the presenter by NOT knocking on the door for admittance once the door has been closed whether the presentation has begun or not (If the room is at capacity, overflow is not permitted (ie. sitting on floors) as this is a violation of the Fire Safety code).
4. Be respectful of the decision of the advisor/host of the event if you are not given admittance. The School of Computer Science has numerous events occurring in the near future.

 Register for Event Here:  https://winhub.ca/

Abstract:

Improving the efficiency of algorithms for fundamental computational tasks such as matrix multiplication can have widespread impact, as it affects the overall speed of a large amount of computations. The automatic discovery of algorithms using machine learning offers the prospect of reaching beyond human intuition and outperforming the current best human-designed algorithms. In this talk I’ll present AlphaTensor, our reinforcement learning agent based on AlphaZero for discovering efficient and provably correct algorithms for the multiplication of arbitrary matrices. AlphaTensor discovered algorithms that outperform the state-of-the-art complexity for many matrix sizes. Particularly relevant is the case of 4 × 4 matrices in a finite field, where AlphaTensor’s algorithm improves on Strassen’s two-level algorithm for the first time since its discovery 50 years ago. I’ll present our problem formulation as a single-player game, the key ingredients that enable tackling such difficult mathematical problems using reinforcement learning, and the flexibility of the AlphaTensor framework.

Keywords: Machine Learning, Algorithmic Discovery, Matrix Multiplication, Tensor Decomposition, Combinatorial Optimization.

Biography:

I am a staff research scientist at Google DeepMind. I obtained my PhD from the signal processing laboratory in EPFL in 2016, and my M.Sc. in Electrical Engineering from EPFL in 2012. I work on AI for Science, and in particular on using Machine Learning to unlock new results in Mathematics and Computer Science.