English
Related papers

Related papers: Scaling Laws for Transfer

200 papers

While task-specific finetuning of pretrained networks has led to significant empirical advances in NLP, the large size of networks makes finetuning difficult to deploy in multi-task, memory-constrained settings. We propose diff pruning as a…

Computation and Language · Computer Science 2021-06-10 Demi Guo , Alexander M. Rush , Yoon Kim

Despite the fact that experimental neural scaling laws have substantially guided empirical progress in large-scale machine learning, no existing theory can quantitatively predict the exponents of these important laws for any modern LLM…

Machine Learning · Computer Science 2026-02-13 Francesco Cagnetta , Allan Raventós , Surya Ganguli , Matthieu Wyart

Scale has been a major driving force in improving machine learning performance, and understanding scaling laws is essential for strategic planning for a sustainable model quality performance growth, long-term resource planning and…

Information Retrieval · Computer Science 2022-08-19 Newsha Ardalani , Carole-Jean Wu , Zeliang Chen , Bhargav Bhushanam , Adnan Aziz

We demonstrate the emergence of scaling laws in the benchmark top versus QCD jet classification problem in collider physics. Six distinct physically-motivated classifiers exhibit power-law scaling of the binary cross-entropy test loss as a…

High Energy Physics - Phenomenology · Physics 2023-12-06 Joshua Batson , Yonatan Kahn

Modern deep convolutional networks (CNNs) are often criticized for not generalizing under distributional shifts. However, several recent breakthroughs in transfer learning suggest that these networks can cope with severe distribution shifts…

Large Language Models (LLMs) represent a promising frontier for recommender systems, yet their development has been impeded by the absence of predictable scaling laws, which are crucial for guiding research and optimizing resource…

Information Retrieval · Computer Science 2026-02-16 Benyu Zhang , Qiang Zhang , Jianpeng Cheng , Hong-You Chen , Qifei Wang , Wei Sun , Shen Li , Jia Li , Jiahao Wu , Xiangjun Fan , Hong Yan

Data duplication during pretraining can degrade generalization and lead to memorization, motivating aggressive deduplication pipelines. However, at web scale, it is unclear what constitutes a ``duplicate'': beyond surface-form matches,…

Machine Learning · Computer Science 2026-03-10 Joshua Kazdan , Noam Levi , Rylan Schaeffer , Jessica Chudnovsky , Abhay Puri , Bo He , Mehmet Donmez , Sanmi Koyejo , David Donoho

Transfer learning from huge natural image datasets, fine-tuning of deep neural networks and the use of the corresponding pre-trained networks have become de facto the core of art analysis applications. Nevertheless, the effects of transfer…

Computer Vision and Pattern Recognition · Computer Science 2020-11-25 Nicolas Gonthier , Yann Gousseau , Saïd Ladjal

In this work, we provide a sharp theory of scaling laws for two-layer neural networks trained on a class of hierarchical multi-index targets, in a genuinely representation-limited regime. We derive exact information-theoretic scaling laws…

Machine Learning · Statistics 2026-02-06 Leonardo Defilippis , Florent Krzakala , Bruno Loureiro , Antoine Maillard

Transfer learning refers to the process of adapting a model trained on a source task to a target task. While kernel methods are conceptually and computationally simple machine learning models that are competitive on a variety of tasks, it…

Machine Learning · Computer Science 2022-11-02 Adityanarayanan Radhakrishnan , Max Ruiz Luyten , Neha Prasad , Caroline Uhler

The growing use of Machine Learning has produced significant advances in many fields. For image-based tasks, however, the use of deep learning remains challenging in small datasets. In this article, we review, evaluate and compare the…

Machine Learning · Computer Science 2021-06-09 Miguel Romero , Yannet Interian , Timothy Solberg , Gilmer Valdes

Pre-training language models (LMs) on large-scale unlabeled text data makes the model much easier to achieve exceptional downstream performance than their counterparts directly trained on the downstream tasks. In this work, we study what…

Computation and Language · Computer Science 2022-02-21 Cheng-Han Chiang , Hung-yi Lee

Power-law scaling, a central concept in critical phenomena, is found to be useful in deep learning, where optimized test errors on handwritten digit examples converge as a power-law to zero with database size. For rapid decision making with…

Machine Learning · Computer Science 2022-11-17 Yuval Meir , Shira Sardi , Shiri Hodassman , Karin Kisos , Itamar Ben-Noam , Amir Goldental , Ido Kanter

Large, pre-trained models are problematic to use in resource constrained applications. Fortunately, task-aware structured pruning methods offer a solution. These approaches reduce model size by dropping structural units like layers and…

Computation and Language · Computer Science 2023-11-14 Lucio Dery , David Grangier , Awni Hannun

We propose an approach to estimate the number of samples required for a model to reach a target performance. We find that the power law, the de facto principle to estimate model performance, leads to large error when using a small dataset…

Neural scaling laws have driven the field's ever-expanding exponential growth in parameters, data and compute. While scaling behaviors for pretraining losses and discriminative benchmarks are well established, generative benchmarks such as…

Machine Learning · Computer Science 2026-02-03 Rylan Schaeffer , Noam Levi , Brando Miranda , Sanmi Koyejo

Current theoretical results on optimization trajectories of neural networks trained by gradient descent typically have the form of rigorous but potentially loose bounds on the loss values. In the present work we take a different approach…

Machine Learning · Computer Science 2021-05-04 Maksim Velikanov , Dmitry Yarotsky

The scientific scale-up of large language models (LLMs) necessitates a comprehensive understanding of their scaling properties. However, the existing literature on the scaling properties only yields an incomplete answer: optimization loss…

Computation and Language · Computer Science 2024-04-18 Shengding Hu , Xin Liu , Xu Han , Xinrong Zhang , Chaoqun He , Weilin Zhao , Yankai Lin , Ning Ding , Zebin Ou , Guoyang Zeng , Zhiyuan Liu , Maosong Sun

In practice, it is very demanding and sometimes impossible to collect datasets of tagged data large enough to successfully train a machine learning model, and one possible solution to this problem is transfer learning. This study aims to…

Machine Learning · Computer Science 2022-01-13 Erik Otović , Marko Njirjak , Dario Jozinović , Goran Mauša , Alberto Michelini , Ivan Štajduhar

In this paper we present a technique to train neural network models on small amounts of data. Current methods for training neural networks on small amounts of rich data typically rely on strategies such as fine-tuning a pre-trained neural…

Machine Learning · Computer Science 2016-11-08 Ark Anderson , Kyle Shaffer , Artem Yankov , Court D. Corley , Nathan O. Hodas