English
Related papers

Related papers: A Dynamical Model of Neural Scaling Laws

200 papers

Autonomous neural systems must efficiently process information in a wide range of novel environments, which may have very different statistical properties. We consider the problem of how to optimally distribute receptors along a…

Neurons and Cognition · Quantitative Biology 2017-04-04 Marc W. Howard , Karthik H. Shankar

The computational capabilities of a neural network are widely assumed to be determined by its static architecture. Here we challenge this view by establishing that a fixed neural structure can operate in fundamentally different…

Neural and Evolutionary Computing · Computer Science 2025-09-24 Xia Chen

This work presents a novel means for understanding learning dynamics and scaling relations in neural networks. We show that certain measures on the spectrum of the empirical neural tangent kernel, specifically entropy and trace, yield…

Machine Learning · Computer Science 2024-10-11 Samuel Tovey , Sven Krippendorf , Michael Spannowsky , Konstantin Nikolaou , Christian Holm

Widely observed neural scaling laws, in which error falls off as a power of the training set size, model size, or both, have driven substantial performance improvements in deep learning. However, these improvements through scaling alone…

Machine Learning · Computer Science 2023-04-25 Ben Sorscher , Robert Geirhos , Shashank Shekhar , Surya Ganguli , Ari S. Morcos

When artificial neural networks have demonstrated exceptional practical success in a variety of domains, investigations into their theoretical characteristics, such as their approximation power, statistical properties, and generalization…

Machine Learning · Statistics 2023-10-06 Shijin Gong , Xinyu Zhang

The performance of embodied agents has been shown to improve by increasing model parameters, dataset size, and compute. This has been demonstrated in domains from robotics to video games, when generative learning objectives on offline…

Machine Learning · Computer Science 2024-12-19 Tim Pearce , Tabish Rashid , Dave Bignell , Raluca Georgescu , Sam Devlin , Katja Hofmann

A multiplicative constant scaling factor is often applied to the model output to adjust the dynamics of neural network parameters. This has been used as one of the key interventions in an empirical study of lazy and active behavior.…

Machine Learning · Computer Science 2021-07-05 Ryuichi Kanoh , Mahito Sugiyama

Training a neural network with the gradient descent algorithm gives rise to a discrete-time nonlinear dynamical system. Consequently, behaviors that are typically observed in these systems emerge during training, such as convergence to an…

Machine Learning · Computer Science 2018-10-10 Kamil Nar , S. Shankar Sastry

This paper explores the intricate behavior of deep neural networks (DNNs) through the lens of neuron activation dynamics. We propose a probabilistic framework that can analyze models' neuron activation patterns as a stochastic process,…

Artificial Intelligence · Computer Science 2024-12-25 Yizhou Zhang , Yang Sui

Recently, Large Language Models (LLMs) have been widely adopted in a wide range of tasks, leading to increasing attention towards the research on how scaling LLMs affects their performance. Existing works, termed Scaling Laws, have…

Computation and Language · Computer Science 2025-09-23 Yizhe Xiong , Xiansheng Chen , Xin Ye , Hui Chen , Zijia Lin , Haoran Lian , Zhenpeng Su , Wei Huang , Jianwei Niu , Jungong Han , Guiguang Ding

Data-driven models are revolutionizing weather forecasting. To optimize training efficiency and model performance, this paper analyzes empirical scaling laws within this domain. We investigate the relationship between model performance…

Machine Learning · Computer Science 2026-02-27 Yuejiang Yu , Langwen Huang , Alexandru Calotoiu , Torsten Hoefler

The results of training a neural network are heavily dependent on the architecture chosen; and even a modification of only its size, however small, typically involves restarting the training process. In contrast to this, we begin training…

Machine Learning · Computer Science 2024-02-12 Rupert Mitchell , Robin Menzenbach , Kristian Kersting , Martin Mundt

Deep learning models can exhibit what appears to be a sudden ability to solve a new problem as training time, training data, or model size increases, a phenomenon known as emergence. In this paper, we present a framework where each new…

Machine Learning · Computer Science 2025-04-30 Yoonsoo Nam , Nayara Fonseca , Seok Hyeong Lee , Chris Mingard , Ard A. Louis

Large language model pre-training has become increasingly expensive, with most practitioners relying on scaling laws to allocate compute budgets for model size and training tokens, commonly referred to as Compute-Optimal or Chinchilla…

Machine Learning · Computer Science 2024-05-03 Zhen Guo

Continual Pre-training (CPT) serves as a fundamental approach for adapting foundation models to domain-specific applications. Scaling laws for pre-training define a power-law relationship between dataset size and the test loss of an LLM.…

Machine Learning · Computer Science 2025-12-29 Lei Liu , Hao Zhu , Yue Shen , Zhixuan Chu , Jian Wang , Jinjie Gu , Kui Ren

Training compute is increasingly outpacing the availability of high-quality data. This shifts the central challenge from optimal compute allocation to extracting maximum value from limited data. The widely adopted Chinchilla scaling law…

Machine Learning · Computer Science 2026-05-05 Justin Lovelace , Christian Belardi , Srivatsa Kundurthy , Shriya Sudhakar , Kilian Q. Weinberger

We present an empirical study in the geometric task of learning interatomic potentials, which shows equivariance matters even more at larger scales; we show a clear power-law scaling behaviour with respect to data, parameters and compute…

Machine Learning · Computer Science 2026-05-06 Khang Ngo , Siamak Ravanbakhsh

Scaling laws have been used to describe how large language model (LLM) performance scales with model size, training data size, or amount of computational resources. Motivated by the fact that neural quantum states (NQS) has increasingly…

Machine Learning · Computer Science 2025-09-17 Oliver Knitter , Dan Zhao , Stefan Leichenauer , Shravan Veerapaneni

Learning rules -- prescriptions for updating model parameters to improve performance -- are typically assumed rather than derived. Why do some learning rules work better than others, and under what assumptions can a given rule be considered…

Machine Learning · Computer Science 2025-11-03 John J. Vastola , Samuel J. Gershman , Kanaka Rajan

In contrast to conventional artificial neural networks, which are structurally static, we present two approaches for evolving small networks into larger ones during training. The first method employs an auxiliary weight that directly…

Machine Learning · Computer Science 2025-07-29 Anil Radhakrishnan , John F. Lindner , Scott T. Miller , Sudeshna Sinha , William L. Ditto
‹ Prev 1 4 5 6 7 8 10 Next ›