Výsledky vyhledávání

Report

CATS: Contextually-Aware Thresholding for Sparsity in Large Language Models

Autor: Lee, Donghyun, Lee, Je-Yong, Zhang, Genghan, Tiwari, Mo, Mirhoseini, Azalia

Large Language Models (LLMs) have dramatically advanced AI applications, yet their deployment remains challenging due to their immense inference costs. Recent studies ameliorate the computational costs of LLMs by increasing their activation sparsity

Externí odkaz: http://arxiv.org/abs/2404.08763

Zobrazit plný text záznamu

Report

Faster Maximum Inner Product Search in High Dimensions

Autor: Tiwari, Mo, Kang, Ryan, Lee, Je-Yong, Lee, Donghyun, Piech, Chris, Thrun, Sebastian, Shomorony, Ilan, Zhang, Martin Jinye

Maximum Inner Product Search (MIPS) is a ubiquitous task in machine learning applications such as recommendation systems. Given a query vector and $n$ atom vectors in $d$-dimensional space, the goal of MIPS is to find the atom that has the highest in

Externí odkaz: http://arxiv.org/abs/2212.07551

Zobrazit plný text záznamu

Report

MABSplit: Faster Forest Training Using Multi-Armed Bandits

Autor: Tiwari, Mo, Kang, Ryan, Lee, Je-Yong, Thrun, Sebastian, Piech, Chris, Shomorony, Ilan, Zhang, Martin Jinye

Random forests are some of the most widely used machine learning models today, especially in domains that necessitate interpretability. We present an algorithm that accelerates the training of random forests and other popular tree-based learning meth

Externí odkaz: http://arxiv.org/abs/2212.07473

Zobrazit plný text záznamu