English
Related papers

Related papers: Scaling Laws for Transfer

200 papers

We theoretically characterize gradient descent dynamics in deep linear networks trained at large width from random initialization and on large quantities of random data. Our theory captures the ``wider is better" effect of…

Machine Learning · Computer Science 2025-06-17 Blake Bordelon , Cengiz Pehlevan

We introduce compression laws for language language models (LLMs). While recent scaling laws have sought to understand how LLMs scale with respect to model size, pre-training data, and computational resources, we focus on understanding how…

Computation and Language · Computer Science 2025-04-08 Ayan Sengupta , Siddhant Chaudhary , Tanmoy Chakraborty

Training large language models (LLMs) is computationally expensive, partly because the loss exhibits slow power-law convergence whose origin remains debatable. Through systematic analysis of toy models and empirical evaluation of LLMs, we…

Machine Learning · Computer Science 2026-02-04 Yizhou Liu , Ziming Liu , Cengiz Pehlevan , Jeff Gore

The performance of machine learning models under distribution shift has been the focus of the community in recent years. Most of current methods have been proposed to improve the robustness to distribution shift from the algorithmic…

Computer Vision and Pattern Recognition · Computer Science 2022-05-26 Ziquan Liu , Yi Xu , Yuanhong Xu , Qi Qian , Hao Li , Rong Jin , Xiangyang Ji , Antoni B. Chan

Transfer learning has emerged as a highly sought-after and actively pursued research area within the statistical community. The core concept of transfer learning involves leveraging insights and information from auxiliary datasets to…

Methodology · Statistics 2024-08-01 Pengfei Li , Tao Yu , Chixiang Chen , Jing Qin

We show that the error of iteratively magnitude-pruned networks empirically follows a scaling law with interpretable coefficients that depend on the architecture and task. We functionally approximate the error of the pruned networks,…

Machine Learning · Computer Science 2021-07-06 Jonathan S. Rosenfeld , Jonathan Frankle , Michael Carbin , Nir Shavit

With the emergence of large-scale pre-trained neural networks, methods to adapt such "foundation" models to data-limited downstream tasks have become a necessity. Fine-tuning, preference optimization, and transfer learning have all been…

Machine Learning · Statistics 2025-07-09 Javan Tahir , Surya Ganguli , Grant M. Rotskoff

When trained on large-scale object classification datasets, certain artificial neural network models begin to approximate core object recognition behaviors and neural response patterns in the primate brain. While recent machine learning…

Machine Learning · Computer Science 2025-11-07 Abdulkadir Gokce , Martin Schrimpf

Scaling laws have played a major role in the modern AI revolution, providing practitioners predictive power over how the model performance will improve with increasing data, compute, and number of model parameters. This has spurred an…

Machine Learning · Computer Science 2026-01-16 Maissam Barkeshli , Alberto Alfarano , Andrey Gromov

Large language models are increasingly deployed across diverse applications. This often includes tasks LLMs have not encountered during training. This implies that enumerating and obtaining the high-quality training data for all tasks is…

Computation and Language · Computer Science 2025-11-11 Shambhavi Krishna , Atharva Naik , Chaitali Agarwal , Sudharshan Govindan , Taesung Lee , Haw-Shiuan Chang

Training large models is both resource-intensive and time-consuming, making it crucial to understand the quantitative relationship between model performance and hyperparameters. In this paper, we present an empirical law that describes how…

Machine Learning · Computer Science 2025-03-18 Kairong Luo , Haodong Wen , Shengding Hu , Zhenbo Sun , Zhiyuan Liu , Maosong Sun , Kaifeng Lyu , Wenguang Chen

Deep neural networks produce state-of-the-art results when trained on a large number of labeled examples but tend to overfit when small amounts of labeled examples are used for training. Creating a large number of labeled examples requires…

Computer Vision and Pattern Recognition · Computer Science 2021-09-13 Attaullah Sahito , Eibe Frank , Bernhard Pfahringer

Precise estimation of downstream performance in large language models (LLMs) prior to training is essential for guiding their development process. Scaling laws analysis utilizes the statistics of a series of significantly smaller sampling…

Computation and Language · Computer Science 2025-04-09 Yangyi Chen , Binxuan Huang , Yifan Gao , Zhengyang Wang , Jingfeng Yang , Heng Ji

We introduce a framework for optimizing domain-specific dataset construction in foundation model training. Specifically, we seek a cost-efficient way to estimate the quality of data sources (e.g. synthetically generated or filtered web…

Neural scaling laws describe how the performance of deep neural networks scales with key factors such as training data size, model complexity, and training time, often following power-law behaviors over multiple orders of magnitude. Despite…

Machine Learning · Statistics 2024-10-14 Roman Worschech , Bernd Rosenow

Neural scaling laws have garnered significant interest due to their ability to predict model performance as a function of increasing parameters, data, and compute. In this work, we propose a simple statistical ansatz based on memorization…

Machine Learning · Statistics 2024-12-10 Noam Levi

Empirically-determined scaling laws have been broadly successful in predicting the evolution of large machine learning models with training data and number of parameters. As a consequence, they have been useful for optimizing the allocation…

Computer Vision and Pattern Recognition · Computer Science 2024-07-26 Katherine L. Mentzer , Andrea Montanari

Scaling has been a major driver of recent advancements in deep learning. Numerous empirical studies have found that scaling laws often follow the power-law and proposed several variants of power-law functions to predict the scaling behavior…

Machine Learning · Computer Science 2025-06-17 Dongwoo Lee , Dong Bok Lee , Steven Adriaensen , Juho Lee , Sung Ju Hwang , Frank Hutter , Seon Joo Kim , Hae Beom Lee

We propose Neural Priming, a technique for adapting large pretrained models to distribution shifts and downstream tasks given few or no labeled examples. Presented with class names or unlabeled test samples, Neural Priming enables the model…

Neural scaling laws -- power-law relationships between loss, model size, and data -- have been extensively documented for language and vision transformers, yet their existence in single-cell genomics remains largely unexplored. We present…

Machine Learning · Computer Science 2026-02-18 Ihor Kendiukhov