English
Related papers

Related papers: Neural Scaling Laws for Deep Regression

200 papers

Scaling laws for language models have often focused on finding the optimal model size and token count for training from scratch. However, achieving this optimal balance requires significant compute resources due to the extensive data…

Computation and Language · Computer Science 2025-04-01 Roseval Malaquias Junior , Ramon Pires , Thales Sales Almeida , Kenzo Sakiyama , Roseli A. F. Romero , Rodrigo Nogueira

Deep learning (DL) has transformed applications in a variety of domains, including computer vision, natural language processing, and tabular data analysis. The search for improved DL model accuracy has led practitioners to explore…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-01-10 Kabir Nagrecha

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

Recent advances in large language models (LLMs) have been largely driven by scaling laws for individual models, which predict performance improvements as model parameters and data volume increase. However, the capabilities of any single LLM…

Machine Learning · Computer Science 2026-01-29 Dakuan Lu , Jiaqi Zhang , Cheng Yuan , Jiawei Shao , Xuelong Li

Recent large language models have been trained on vast datasets, but also often on repeated data, either intentionally for the purpose of upweighting higher quality data, or unintentionally because data deduplication is not perfect and the…

Motivated by the remarkable success of Foundation Models (FMs) in language modeling, there has been growing interest in developing FMs for time series prediction, given the transformative power such models hold for science and engineering.…

Machine Learning · Computer Science 2025-11-18 Ramzi Dakhmouche , Hossein Gorji

Empirical power--law scaling has been widely observed across modern deep learning systems, yet its theoretical origins and scope of validity remain incompletely understood. The Generalized Resolution--Shell Dynamics (GRSD) framework models…

Machine Learning · Computer Science 2026-01-14 Yizhou Zhang

Despite recent advancements of large language models (LLMs), optimally predicting the model size for LLM pretraining or allocating optimal resources still remains a challenge. Several efforts have addressed the challenge by proposing…

Machine Learning · Computer Science 2026-02-11 Md Arafat Hossain , Xingfu Wu , Valerie Taylor , Ali Jannesari

We find that the cross-entropy loss curves of neural language models empirically adhere to a scaling law with learning rate (LR) annealing over training steps: $$L(s) = L_0 + A\cdot S_1^{-\alpha} - C\cdot S_2,$$ where $L(s)$ is the…

Computation and Language · Computer Science 2024-10-28 Howe Tissue , Venus Wang , Lu Wang

Molecular generative models, often employing GPT-style language modeling on molecular string representations, have shown promising capabilities when scaled to large datasets and model sizes. However, it remains unclear and subject to debate…

Machine Learning · Computer Science 2026-02-02 Dong Xu , Qihua Pan , Sisi Yuan , Jianqiang Li , Zexuan Zhu , Junkai Ji

Pretrained large language models (LLMs) are surprisingly effective at performing zero-shot tasks, including time-series forecasting. However, understanding the mechanisms behind such capabilities remains highly challenging due to the…

Machine Learning · Computer Science 2025-07-02 Toni J. B. Liu , Nicolas Boullé , Raphaël Sarfati , Christopher J. Earls

Neural scaling laws are observed in a range of domains, to date with no universal understanding of why they occur. Recent theories suggest that loss power laws arise from Zipf's law, a power law observed in domains like natural language.…

Machine Learning · Computer Science 2025-10-15 Oren Neumann , Claudius Gros

Motivated by the size of cell line drug sensitivity data, researchers have been developing machine learning (ML) models for predicting drug response to advance cancer treatment. As drug sensitivity studies continue generating data, a common…

Scaling laws play a central role in the success of Large Language Models (LLMs), enabling the prediction of model performance relative to compute budgets prior to training. While Transformers have been the dominant architecture, recent…

Machine Learning · Computer Science 2026-02-23 Maximilian Beck , Kajetan Schweighofer , Sebastian Böck , Sebastian Lehner , Sepp Hochreiter

Deep neural networks (DNN) are the state of the art on many engineering problems such as computer vision and audition. A key factor in the success of the DNN is scalability - bigger networks work better. However, the reason for this…

Machine Learning · Computer Science 2015-02-13 Andrew J. R. Simpson

Deep neural networks are highly expressive machine learning models with the ability to interpolate arbitrary datasets. Deep nets are typically optimized via first-order methods and the optimization process crucially depends on the…

Machine Learning · Statistics 2019-11-12 Talha Cihad Gulcu

We perform an average case analysis of the generalization dynamics of large neural networks trained using gradient descent. We study the practically-relevant "high-dimensional" regime where the number of free parameters in the network is on…

Machine Learning · Statistics 2017-10-11 Madhu S. Advani , Andrew M. Saxe

Diffusion noise is a major source of spectral line broadening in liquid state nano-scale nuclear magnetic resonance with shallow nitrogen-vacancy centres, whose main consequence is a limited spectral resolution. This limitation arises by…

In search of many social and economical systems, it is found that node strength distribution as well as degree distribution demonstrate the behavior of power-law with droop-head and heavy-tail. We present a new model for the growth of…

Disordered Systems and Neural Networks · Physics 2007-05-23 Chuan-Ji Fu , Qing Ou , Wen Chen , Bing-Hong Wang , Ying-Di Jin , Yong-Wei Niu , Tao Zhou

It is increasingly common in machine learning to use learned models to label data and then employ such data to train more capable models. The phenomenon of weak-to-strong generalization exemplifies the advantage of this two-stage procedure:…

Machine Learning · Computer Science 2026-05-26 Diyuan Wu , Lehan Chen , Theodor Misiakiewicz , Marco Mondelli
‹ Prev 1 8 9 10 Next ›