Researchers at MIT's Computer Science & Artificial Intelligence Lab (CSAIL) have open-sourced Multiply-ADDitioN-lESS (MADDNESS), an algorithm that speeds up machine learning using approximate matrix m ...

Can artificial intelligence (AI) create its own algorithms to speed up matrix multiplication, one of machine learning’s most fundamental tasks? Today, in a paper published in Nature, DeepMind ...

The algorithm is able to re-discover older matrix multiplication algorithms and improve upon its own to discover newer and faster algorithms. “AlphaTensor is the first AI system for discovering novel, ...

With Deep Reinforcement Learning, DeepMind has discovered an algorithm no human thought of. It is supposed to significantly accelerate matrix multiplication.

This is a summary of: Fawzi, A. et al.Discovering faster matrix multiplication algorithms with reinforcement learning. Nature 610, 47–53 (2022).. The problem. Algorithms have been used ...

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 ...

A new research paper titled “Discovering faster matrix multiplication algorithms with reinforcement learning” was published by researchers at DeepMind. “Here we report a deep reinforcement learning ...

That and even faster algorithms are mentioned in the video, including David Harvey and Joris van der Hoeven’s O(n log n) algorithm which is only faster for numbers having more than 2^(1729^12) bits.

The new method, called Linear-Complexity Multiplication (L-Mul), comes close to the results of FPM while using the simpler algorithm. But despite that, it’s still able to maintain the high ...