Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟯𝟭𝟴 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗠𝗜𝗧 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵𝗲𝗿𝘀 𝗢𝗽𝗲𝗻-𝗦𝗼𝘂𝗿𝗰𝗲𝗱 ‘𝗠𝗔𝗗𝗗𝗡𝗘𝗦𝗦’: An AI Algorithm That Speeds Up Machine Learning Using Approximate Matrix Multiplication (AMM) Follow me for a similar post: 🇮🇳 Ashish Patel ------------------------------------------------------------------- 𝗜𝗻𝘁𝗲𝗿𝗲𝘀𝘁𝗶𝗻𝗴 𝗙𝗮𝗰𝘁𝘀 : 🔸 Paper: Multiplying Matrices Without Multiplying 🔸 This paper is published in NeuroIPS 2021. 🔸 Earlier this year, researchers from MIT’s Computer Science & Artificial Intelligence Lab (CSAIL) has introduced Multiply-ADDitioN-lESS (MADDNESS). This algorithm does not require multiply-add operations and speeds up ML by employing approximate matrix multiplication (AMM). MADDNESS runs 10x quicker than other approximation algorithms and 100x faster than accurate multiplication. This algorithm is now made open-sourced. ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 Multiplying matrices is among the most fundamental and compute-intensive operations in machine learning. Consequently, there has been significant work on efficiently approximating matrix multiplies. 🔸We introduce a learning-based algorithm for this task that greatly outperforms existing methods. Experiments using hundreds of matrices from diverse domains show that it often runs 100× faster than exact matrix products and 10× faster than current approximate methods. 🔸In the common case that one matrix is known ahead of time, our method also has the interesting property that it requires zero multiply-adds. 🔸These results suggest that a mixture of hashing, averaging, and byte shuffling−the core operations of our method−could be a more promising building block for machine learning than the sparsified, factorized, and/or scalar quantized matrix products that have recently been the focus of substantial research and hardware investment. ------------------------------------------------------------------- #computervision #artificialintelligence #innovation -------------------------------------------------------------------