English
Related papers

Related papers: Broken Neural Scaling Laws

200 papers

$\textbf{Formal version available at}$ https://cell.com/patterns/fulltext/S2666-3899(23)00200-3 Networks of spiking neurons underpin the extraordinary information-processing capabilities of the brain and have become pillar models in…

Neural and Evolutionary Computing · Computer Science 2023-09-18 Gehua Ma , Rui Yan , Huajin Tang

While scaling laws for large language models (LLMs) during pre-training have been extensively studied, their behavior under reinforcement learning (RL) post-training remains largely unexplored. This paper presents a systematic empirical…

Representation learning that leverages large-scale labelled datasets, is central to recent progress in machine learning. Access to task relevant labels at scale is often scarce or expensive, motivating the need to learn from unlabelled…

Machine Learning · Computer Science 2022-02-14 Arna Ghosh , Arnab Kumar Mondal , Kumar Krishna Agrawal , Blake Richards

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

Existing scaling laws for Large Language Models (LLMs), predominantly monotonic power laws, fail to explain emerging non-monotonic phenomena such as catastrophic overtraining and quantization-induced degradation, where performance…

Machine Learning · Computer Science 2026-05-25 Xu Ouyang , Deyi Liu , Yuhang Cai , Jing Liu , Yuan Yang , Chen Zheng , Thomas Hartvigsen , Yiyuan Ma

Ensembles of deep neural networks are known to achieve state-of-the-art performance in uncertainty estimation and lead to accuracy improvement. In this work, we focus on a classification problem and investigate the behavior of both…

Machine Learning · Computer Science 2021-06-29 Ekaterina Lobacheva , Nadezhda Chirkova , Maxim Kodryan , Dmitry Vetrov

Deep neural networks trained end-to-end to map a measurement of a (noisy) image to a clean image perform excellent for a variety of linear inverse problems. Current methods are only trained on a few hundreds or thousands of images as…

Image and Video Processing · Electrical Eng. & Systems 2023-02-24 Tobit Klug , Reinhard Heckel

In recent years, the expansion of neural network models and training data has driven remarkable progress in deep learning, particularly in computer vision and natural language processing. This advancement is underpinned by the concept of…

Machine Learning · Computer Science 2025-08-06 Yi Ma , Hongyao Tang , Chenjun Xiao , Yaodong Yang , Wei Wei , Jianye Hao , Jiye Liang

Neuro-symbolic learning (NSL) models complex symbolic rule patterns into latent variable distributions by neural networks, which reduces rule search space and generates unseen rules to improve downstream task performance. Centralized NSL…

Artificial Intelligence · Computer Science 2024-05-28 Pengwei Xing , Songtao Lu , Han Yu

This paper investigates the learnability of the nonlinearity property of Boolean functions using neural networks. We train encoder style deep neural networks to learn to predict the nonlinearity of Boolean functions from examples of…

Machine Learning · Computer Science 2025-02-04 Sriram Ranga , Nandish Chattopadhyay , Anupam Chattopadhyay

Scaling laws for large language models (LLMs) have provided useful guidance in training ever larger models for predictable performance gains. Time series forecasting shares a similar sequential structure to language, and is amenable to…

Machine Learning · Computer Science 2025-01-09 Thomas D. P. Edwards , James Alvey , Justin Alsing , Nam H. Nguyen , Benjamin D. Wandelt

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

With the rapid development of Deep Neural Networks (DNNs), various network models that show strong computing power and impressive expressive power are proposed. However, there is no comprehensive informational interpretation of DNNs from…

Machine Learning · Computer Science 2018-02-14 Xiao-Yang Liu

While scaling laws for Large Language Models (LLMs) traditionally focus on proxy metrics like pretraining loss, predicting downstream task performance has been considered unreliable. This paper challenges that view by proposing a direct…

Machine Learning · Computer Science 2025-12-10 Jakub Krajewski , Amitis Shidani , Dan Busbridge , Sam Wiseman , Jason Ramapuram

Scaling laws predict the loss of a target machine learning model by extrapolating from easier-to-train models with fewer parameters or smaller training sets. This provides an efficient way for practitioners and researchers alike to compare…

Machine Learning · Computer Science 2025-06-04 Leshem Choshen , Yang Zhang , Jacob Andreas

Symbolic regression (SR) aims to discover the underlying mathematical expressions that explain observed data. This holds promise for both gaining scientific insight and for producing inherently interpretable and generalizable models for…

Machine Learning · Computer Science 2026-02-05 David Otte , Jörg K. H. Franke , Arbër Zela , Fábio Ferreira , Frank Hutter

Deep learning (DL) creates impactful advances following a virtuous recipe: model architecture search, creating large training data sets, and scaling computation. It is widely believed that growing training sets and models should improve…

Neural scaling laws characterize how model performance improves as the model size scales up. Inspired by empirical observations, we introduce a resource model of neural scaling. A task is usually composite hence can be decomposed into many…

Machine Learning · Computer Science 2024-05-16 Jinyeop Song , Ziming Liu , Max Tegmark , Jeff Gore

We study empirical scaling laws for language model performance on the cross-entropy loss. The loss scales as a power-law with model size, dataset size, and the amount of compute used for training, with some trends spanning more than seven…

The dependency of the generalization error of neural networks on model and dataset size is of critical importance both in practice and for understanding the theory of neural networks. Nevertheless, the functional form of this dependency…

Machine Learning · Computer Science 2019-12-23 Jonathan S. Rosenfeld , Amir Rosenfeld , Yonatan Belinkov , Nir Shavit