English
Related papers

Related papers: Optimal Scaling Needs Optimal Norm

200 papers

When training an estimator such as a neural network for tasks like image denoising, it is often preferred to train one estimator and apply it to all noise levels. The de facto training protocol to achieve this goal is to train the estimator…

Machine Learning · Computer Science 2020-07-20 Abhiram Gnansambandam , Stanley H. Chan

Large language models with a huge number of parameters, when trained on near internet-sized number of tokens, have been empirically shown to obey neural scaling laws: specifically, their performance behaves predictably as a power law in…

Machine Learning · Computer Science 2022-11-01 Alexander Maloney , Daniel A. Roberts , James Sully

As neural networks continue to grow in size but datasets might not, it is vital to understand how much performance improvement can be expected: is it more important to scale network size or data volume? Thus, neural network scaling laws,…

Machine Learning · Computer Science 2024-09-10 Akhilan Boopathy , Ila Fiete

Matrix-based optimizers have demonstrated immense potential in training Large Language Models (LLMs), however, designing an ideal optimizer remains a formidable challenge. A superior optimizer must satisfy three core desiderata: efficiency,…

Machine Learning · Computer Science 2026-05-06 Jinghui Yuan , Jiaxuan Zou , Shuo Wang , Yong Liu , Feiping Nie

Setting the learning rate (LR) for a deep learning model is a critical part of successful training. Choosing LRs is often done empirically with trial and error. In this work, we explore a solvable model of optimal LR schedules for a…

Disordered Systems and Neural Networks · Physics 2026-05-11 Blake Bordelon , Francesco Mori

Traditional scaling laws in natural language processing suggest that increasing model size and training data enhances performance. However, recent studies reveal deviations, particularly in large language models, where performance…

Machine Learning · Computer Science 2025-07-16 Zhengyu Chen , Siqi Wang , Teng Xiao , Yudong Wang , Shiqi Chen , Xunliang Cai , Junxian He , Jingang Wang

We study empirical scaling laws for transfer learning between distributions in an unsupervised, fine-tuning setting. When we train increasingly large neural networks from-scratch on a fixed-size dataset, they eventually become data-limited…

Machine Learning · Computer Science 2021-02-03 Danny Hernandez , Jared Kaplan , Tom Henighan , Sam McCandlish

Training large language models (LLMs) relies on adaptive optimizers such as Adam, which introduce extra operations and require significantly more memory to maintain first- and second-order moments than SGD. While recent works such as…

Machine Learning · Computer Science 2026-05-22 Athanasios Glentis , Jiaxiang Li , Andi Han , Mingyi Hong

The success of Large Language Models (LLMs) hinges on the stable training of deep Transformer architectures. A critical design choice is the placement of normalization layers, leading to a fundamental trade-off: the ``PreNorm'' architecture…

Computation and Language · Computer Science 2026-02-02 Chao Wang , Bei Li , Jiaqi Zhang , Xinyu Liu , Yuchun Fan , Linkun Lyu , Xin Chen , Jingang Wang , Tong Xiao , Peng Pei , Xunliang Cai

What scaling limits govern neural network training dynamics when model size and training time grow in tandem? We show that despite the complex interactions between architecture, training algorithms, and data, compute-optimally trained…

Machine Learning · Computer Science 2025-07-08 Shikai Qiu , Lechao Xiao , Andrew Gordon Wilson , Jeffrey Pennington , Atish Agarwala

We introduce two complementary techniques for efficient optimization that reduce memory requirements while accelerating training of large-scale neural networks. The first technique, Subset-Norm step size, generalizes AdaGrad-Norm and…

Machine Learning · Computer Science 2025-05-27 Thien Hang Nguyen , Huy Le Nguyen

Large language models (LLMs) have demonstrated impressive generalization and emergent capabilities, yet their pre-training remains computationally expensive and sensitive to optimization dynamics. While Adam-based optimizers offer fast…

Machine Learning · Computer Science 2025-10-01 Junjie Wang , Pan Zhou , Yiming Dong , Huan Li , Jia Li , Xun Zhou , Qicheng Lao , Cong Fang , Zhouchen Lin

We analyse the learning performance of Distributed Gradient Descent in the context of multi-agent decentralised non-parametric regression with the square loss function when i.i.d. samples are assigned to agents. We show that if agents hold…

Machine Learning · Statistics 2019-11-14 Dominic Richards , Patrick Rebeschini

Large Language Models (LLMs) have advanced rapidly but face significant memory demands. While quantization has shown promise for LLMs, current methods typically require lengthy training to alleviate the performance degradation from…

Artificial Intelligence · Computer Science 2024-05-31 Ke Yi , Yuhui Xu , Heng Chang , Chen Tang , Yuan Meng , Tong Zhang , Jia Li

Stochastic processing networks (SPNs) have broad applications in healthcare, transportation, and communication networks. The control of SPN is to dynamically assign servers in batches under uncertainty to optimize long-run performance. This…

Systems and Control · Electrical Eng. & Systems 2025-10-09 Jim Dai , Manxi Wu , Zhanhao Zhang

The rapid scaling of models has led to prohibitively high training and fine-tuning costs. A major factor accounting for memory consumption is the widespread use of stateful optimizers (e.g., Adam), which maintain auxiliary information of…

Machine Learning · Computer Science 2025-06-10 Cong Xu , Wenbin Liang , Mo Yu , Anan Liu , Ke-Yue Zhang , Shunli Wang , Lizhuang Ma , Jianyong Wang , Jun Wang , Wei Zhang

Neural scaling laws establish a predictable relationship between model performance and data or compute, offering crucial guidance for resource allocation in new domains and tasks. Yet such laws are most needed precisely where they are…

Machine Learning · Computer Science 2026-05-11 Xing Han , Ziyin Liu , Suchi Saria , Paul Pu Liang

Scaling laws in language modeling traditionally quantify training loss as a function of dataset size and model parameters, providing compute-optimal estimates but often neglecting the impact of data quality on model generalization. In this…

Computation and Language · Computer Science 2024-10-07 Ernie Chang , Matteo Paltenghi , Yang Li , Pin-Jie Lin , Changsheng Zhao , Patrick Huber , Zechun Liu , Rastislav Rabatin , Yangyang Shi , Vikas Chandra

Bilevel optimization is a central tool in machine learning for high-dimensional hyperparameter tuning. Its applications are vast; for instance, in imaging it can be used for learning data-adaptive regularizers and optimizing forward…

Optimization and Control · Mathematics 2025-11-11 Mohammad Sadegh Salehi , Subhadip Mukherjee , Lindon Roberts , Matthias J. Ehrhardt

Scaling the amount of data used for supervied fine-tuning(SFT) does not guarantee the proportional gains in model performance, highlighting a critical need to understand what makes training samples effective. This work identifies two…

Artificial Intelligence · Computer Science 2025-10-29 Chengwei Wu , Li Du , Hanyu Zhao , Yiming Ju , Jiapu Wang , Tianyu Chen , Haoyi Zhou