Discovering faster matrix multiplication algorithms with reinforcement learning

Alhussein Fawzi (), Matej Balog, Aja Huang, Thomas Hubert, Bernardino Romera-Paredes, Mohammadamin Barekatain, Alexander Novikov, Francisco J. R. Ruiz, Julian Schrittwieser, Grzegorz Swirszcz, David Silver, Demis Hassabis and Pushmeet Kohli
Additional contact information
Alhussein Fawzi: DeepMind
Matej Balog: DeepMind
Aja Huang: DeepMind
Thomas Hubert: DeepMind
Bernardino Romera-Paredes: DeepMind
Mohammadamin Barekatain: DeepMind
Alexander Novikov: DeepMind
Francisco J. R. Ruiz: DeepMind
Julian Schrittwieser: DeepMind
Grzegorz Swirszcz: DeepMind
David Silver: DeepMind
Demis Hassabis: DeepMind
Pushmeet Kohli: DeepMind

Nature, 2022, vol. 610, issue 7930, 47-53

Abstract: Abstract Improving the efficiency of algorithms for fundamental computations can have a widespread impact, as it can affect the overall speed of a large amount of computations. Matrix multiplication is one such primitive task, occurring in many systems—from neural networks to scientific computing routines. The automatic discovery of algorithms using machine learning offers the prospect of reaching beyond human intuition and outperforming the current best human-designed algorithms. However, automating the algorithm discovery procedure is intricate, as the space of possible algorithms is enormous. Here we report a deep reinforcement learning approach based on AlphaZero1 for discovering efficient and provably correct algorithms for the multiplication of arbitrary matrices. Our agent, AlphaTensor, is trained to play a single-player game where the objective is finding tensor decompositions within a finite factor space. 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, to our knowledge, since its discovery 50 years ago2. We further showcase the flexibility of AlphaTensor through different use-cases: algorithms with state-of-the-art complexity for structured matrix multiplication and improved practical efficiency by optimizing matrix multiplication for runtime on specific hardware. Our results highlight AlphaTensor’s ability to accelerate the process of algorithmic discovery on a range of problems, and to optimize for different criteria.

Date: 2022
References: Add references at CitEc
Citations: View citations in EconPapers (5)

Downloads: (external link)
https://www.nature.com/articles/s41586-022-05172-4 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:nature:v:610:y:2022:i:7930:d:10.1038_s41586-022-05172-4

Ordering information: This journal article can be ordered from
https://www.nature.com/

DOI: 10.1038/s41586-022-05172-4

Access Statistics for this article

Nature is currently edited by Magdalena Skipper

More articles in Nature from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().