English
Related papers

Related papers: Scaling Laws for Sparsely-Connected Foundation Mod…

200 papers

Sparse neural networks are highly desirable in deep learning in reducing its complexity. The goal of this paper is to study how choices of regularization parameters influence the sparsity level of learned neural networks. We first derive…

Machine Learning · Computer Science 2024-08-07 Lixin Shen , Rui Wang , Yuesheng Xu , Mingsong Yan

We investigate the dynamics of increasing the number of model parameters versus the number of labeled examples across a wide variety of tasks. Our exploration reveals that while scaling parameters consistently yields performance…

Computation and Language · Computer Science 2021-10-12 Yuval Kirstain , Patrick Lewis , Sebastian Riedel , Omer Levy

Sparse Mixture-of-Experts (SMoE) architectures have gained prominence for their ability to scale neural networks, particularly transformers, without a proportional increase in computational cost. Despite their success, their role in…

Scaling laws are powerful tools to predict the performance of large language models. However, current scaling laws fall short of accounting for inference costs. In this work, we first show that model architecture affects inference latency,…

Machine Learning · Computer Science 2025-06-10 Song Bian , Minghao Yan , Shivaram Venkataraman

The population loss of trained deep neural networks often follows precise power-law scaling relations with either the size of the training dataset or the number of parameters in the network. We propose a theory that explains the origins of…

Machine Learning · Computer Science 2024-06-28 Yasaman Bahri , Ethan Dyer , Jared Kaplan , Jaehoon Lee , Utkarsh Sharma

Training Transformer language models is expensive, as performance typically improves with increasing dataset size and computational budget. Although scaling laws describe this trend at large scale, their implications in controlled,…

While scaling laws provide a reliable methodology for predicting train loss across compute scales for a single data distribution, less is known about how these predictions should change as we change the distribution. In this paper, we…

Machine Learning · Computer Science 2024-11-21 David Brandfonbrener , Nikhil Anand , Nikhil Vyas , Eran Malach , Sham Kakade

As we scale to more massive machine learning models, the frequent synchronization demands inherent in data-parallel approaches create significant slowdowns, posing a critical challenge to further scaling. Recent work develops an approach…

Machine Learning · Computer Science 2025-03-14 Zachary Charles , Gabriel Teston , Lucio Dery , Keith Rush , Nova Fallen , Zachary Garrett , Arthur Szlam , Arthur Douillard

Sparse connectivity is a hallmark of the brain and a desired property of artificial neural networks. It promotes energy efficiency, simplifies training, and enhances the robustness of network function. Thus, a detailed understanding of how…

Disordered Systems and Neural Networks · Physics 2024-09-10 Mirza M. Junaid Baig , Armen Stepanyants

As large language models (LLMs) grow in size, efficient compression techniques like quantization and sparsification are critical. While quantization maintains performance with reduced precision, structured sparsity methods, such as N:M…

Machine Learning · Computer Science 2026-04-21 Egor Maximov , Yulia Kuzkina , Azamat Kanametov , Alexander Prutko , Aleksei Goncharov , Maxim Zhelnin , Egor Shvetsov

The remarkable progress in deep learning in recent years is largely driven by improvements in scale, where bigger models are trained on larger datasets for longer schedules. To predict the benefit of scale empirically, we argue for a more…

Machine Learning · Computer Science 2022-11-02 Ibrahim Alabdulmohsin , Behnam Neyshabur , Xiaohua Zhai

Scaling model sizes to scale performance has worked remarkably well for the current large language models paradigm. The research and empirical findings of various scaling studies led to novel scaling results and laws that guides subsequent…

To date, 2:4 sparsity has stood as the only sparse pattern that can be accelerated using sparse tensor cores on GPUs. In practice, 2:4 sparsity often possesses low actual speedups ($\leq 1.3$) and requires fixed sparse ratios, meaning that…

Machine Learning · Computer Science 2025-06-04 Kang Zhao , Tao Yuan , Han Bao , Zhenfeng Su , Chang Gao , Zhaofeng Sun , Zichen Liang , Liping Jing , Jianfei Chen

We introduce the Sparsity Roofline, a visual performance model for evaluating sparsity in neural networks. The Sparsity Roofline jointly models network accuracy, sparsity, and theoretical inference speedup. Our approach does not require…

Computer Vision and Pattern Recognition · Computer Science 2023-11-08 Cameron Shinn , Collin McCarthy , Saurav Muralidharan , Muhammad Osama , John D. Owens

Finding neural network weights that generalize well from small datasets is difficult. A promising approach is to learn a weight initialization such that a small number of weight changes results in low generalization error. We show that this…

The core of a good model is in its ability to focus only on important information that reflects the basic patterns and consistencies, thus pulling out a clear, noise-free signal from the dataset. This necessitates using a simplified model…

Machine Learning · Computer Science 2024-07-18 Saeed Damadi , Soroush Zolfaghari , Mahdi Rezaie , Jinglai Shen

We rigorously evaluate three state-of-the-art techniques for inducing sparsity in deep neural networks on two large-scale learning tasks: Transformer trained on WMT 2014 English-to-German, and ResNet-50 trained on ImageNet. Across thousands…

Machine Learning · Computer Science 2019-02-27 Trevor Gale , Erich Elsen , Sara Hooker

Recurrent Neural Networks (RNN) are widely used to solve a variety of problems and as the quantity of data and the amount of available compute have increased, so have model sizes. The number of parameters in recent state-of-the-art networks…

Machine Learning · Computer Science 2017-11-08 Sharan Narang , Erich Elsen , Gregory Diamos , Shubho Sengupta

Given large datasets and sufficient compute, is it beneficial to design neural architectures for the structure and symmetries of each problem? Or is it more efficient to learn them from data? We study empirically how equivariant and…

Machine Learning · Computer Science 2025-07-29 Johann Brehmer , Sönke Behrends , Pim de Haan , Taco Cohen

Training large-scale models under given resources requires careful design of parallelism strategies. In particular, the efficiency notion of critical batch size (CBS), concerning the compromise between time and compute, marks the threshold…

Machine Learning · Computer Science 2025-04-22 Hanlin Zhang , Depen Morwani , Nikhil Vyas , Jingfeng Wu , Difan Zou , Udaya Ghai , Dean Foster , Sham Kakade