English
Related papers

Related papers: Tokens-per-Parameter Coverage Is Critical for Robu…

200 papers

In recent years, the state-of-the-art in deep learning has been dominated by very large models that have been pre-trained on vast amounts of data. The paradigm is very simple: investing more computational resources (optimally) leads to…

Machine Learning · Computer Science 2024-05-24 Sotiris Anagnostidis , Gregor Bachmann , Imanol Schlag , Thomas Hofmann

Training Large Language Models (LLMs) at ultra-low precision is critically impeded by instability rooted in the conflict between discrete quantization constraints and the intrinsic heavy-tailed spectral nature of linguistic data. By…

Machine Learning · Computer Science 2026-02-03 Junlin Huang , Wenyi Fang , Zhenheng Tang , Yuxin Wang , Xueze Kang , Yang Zheng , Bo Li , Xiaowen Chu

Kaplan et al. and Hoffmann et al. developed influential scaling laws for the optimal model size as a function of the compute budget, but these laws yield substantially different predictions. We explain the discrepancy by reproducing the…

Machine Learning · Computer Science 2025-01-22 Tomer Porian , Mitchell Wortsman , Jenia Jitsev , Ludwig Schmidt , Yair Carmon

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

Many machine learning models based on neural networks exhibit scaling laws: their performance scales as power laws with respect to the sizes of the model and training data set. We use large-N field theory methods to solve a model recently…

High Energy Physics - Theory · Physics 2024-05-31 Zhengkang Zhang

Scaling law builds the relationship between training computation and validation loss, enabling researchers to effectively predict the loss trending of models across different levels of computation. However, a gap still remains between…

Computation and Language · Computer Science 2025-06-17 Qiming Ge , Shuhao Xing , Songyang Gao , Yunhua Zhou , Yicheng Zou , Songyang Zhang , Zhi Chen , Hang Yan , Qi Zhang , Qipeng Guo , Kai Chen

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

The scaling law, a cornerstone of Large Language Model (LLM) development, predicts improvements in model performance with increasing computational resources. Yet, while empirically validated, its theoretical underpinnings remain poorly…

Machine Learning · Computer Science 2026-02-03 Chiwun Yang

Scaling laws for neural networks, in which the loss decays as a power-law in the number of parameters, data, and compute, depend fundamentally on the spectral structure of the data covariance, with power-law eigenvalue decay appearing…

Machine Learning · Statistics 2026-03-17 Elliot Paquette , Ke Liang Xiao , Yizhe Zhu

In order to build a large scale quantum computer, one must be able to correct errors extremely fast. We design a fast decoding algorithm for topological codes to correct for Pauli errors and erasure and combination of both errors and…

Quantum Physics · Physics 2021-12-08 Nicolas Delfosse , Naomi H. Nickerson

Neural scaling laws (NSL) refer to the phenomenon where model performance improves with scale. Sharma & Kaplan analyzed NSL using approximation theory and predict that MSE losses decay as $N^{-\alpha}$, $\alpha=4/d$, where $N$ is the number…

Machine Learning · Computer Science 2024-02-05 Ziming Liu , Max Tegmark

Traditional scaling laws in natural language processing suggest that increasing model size and training data enhances performance. However, recent studies reveal deviations, particularly in large language models, where performance…

Machine Learning · Computer Science 2025-07-16 Zhengyu Chen , Siqi Wang , Teng Xiao , Yudong Wang , Shiqi Chen , Xunliang Cai , Junxian He , Jingang Wang

Neural network-based emulators for the inference of stellar parameters and elemental abundances represent an increasingly popular methodology in modern spectroscopic surveys. However, these approaches are often constrained by their…

Instrumentation and Methods for Astrophysics · Physics 2025-06-10 Tomasz Różański , Yuan-Sen Ting

Efficient LLM pre-training requires well-tuned hyperparameters (HPs), including learning rate $\eta$ and weight decay $\lambda$. We study scaling laws for HPs: formulas for how to scale HPs as we scale model size N, dataset size D, and…

Machine Learning · Computer Science 2025-11-25 Shane Bergsma , Nolan Dey , Gurpreet Gosal , Gavia Gray , Daria Soboleva , Joel Hestness

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

Scaling laws have emerged as important components of large language model (LLM) training as they can predict performance gains through scale, and provide guidance on important hyper-parameter choices that would otherwise be expensive. LLMs…

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

Understanding how language model performance varies with scale is critical to benchmark and algorithm development. Scaling laws are one approach to building this understanding, but the requirement of training models across many different…

Machine Learning · Computer Science 2024-10-03 Yangjun Ruan , Chris J. Maddison , Tatsunori Hashimoto

Deep learning has recently revealed the existence of scaling laws, demonstrating that model performance follows predictable trends based on dataset and model sizes. Inspired by these findings and fascinating phenomena emerging in the…

Machine Learning · Statistics 2026-02-10 Mattia Rosso , Simone Rossi , Giulio Franzese , Markus Heinonen , Maurizio Filippone

Recent empirical studies show three phenomena with increasing size of language models: compute-optimal size scaling, emergent capabilities, and performance plateauing. We present a simple unified mathematical framework to explain all of…

Information Theory · Computer Science 2024-10-17 Anuj K. Nayak , Lav R. Varshney
‹ Prev 1 3 4 5 6 7 10 Next ›