English
Related papers

Related papers: Scaling Optimal LR Across Token Horizons

200 papers

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

Large Language Models (LLMs) are pretrained on massive datasets and later instruction-tuned via supervised fine-tuning (SFT) or reinforcement learning (RL). Best practices emphasize large, diverse pretraining data, whereas post-training…

Machine Learning · Computer Science 2026-03-03 Adel Javanmard , Baharan Mirzasoleiman , Vahab Mirrokni

The growing scale of deep learning models has rendered standard hyperparameter (HP) optimization prohibitively expensive. A promising solution is the use of scale-aware hyperparameters, which can enable direct transfer of optimal HPs from…

Machine Learning · Computer Science 2025-12-30 Nikhil Ghosh , Denny Wu , Alberto Bietti

Continual learning (CL) in large language models (LLMs) is an evolving domain that focuses on developing efficient and sustainable training strategies to adapt models to emerging knowledge and achieve robustness in dynamic environments. Our…

Computation and Language · Computer Science 2025-02-13 Çağatay Yıldız , Nishaanth Kanna Ravichandran , Nitin Sharma , Matthias Bethge , Beyza Ermis

Large Language Models (LLMs) must continuously learn and update knowledge to remain effective in dynamic real-world environments. While Low-Rank Adaptation (LoRA) is widely used for such memory updates, existing studies mainly rely on…

Computation and Language · Computer Science 2026-05-29 Ziwen Xu , Haiwen Hong , Linsong Yu , Benglei Cui , Longtao Huang , Hui Xue , Ningyu Zhang

Generalization abilities of well-trained large language models (LLMs) are known to scale predictably as a function of model size. In contrast to the existence of practical scaling laws governing pre-training, the quality of LLMs after…

Machine Learning · Computer Science 2024-12-09 Zifei Xu , Alexander Lan , Wanzin Yazar , Tristan Webb , Sayeh Sharify , Xin Wang

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

Despite the recent popularity of Large Language Models (LLMs) in Machine Translation (MT), their performance in low-resource languages (LRLs) still lags significantly behind Neural Machine Translation (NMT) models. In this work, we explore…

Computation and Language · Computer Science 2024-10-07 Vivek Iyer , Bhavitvya Malik , Pavel Stepachev , Pinzhen Chen , Barry Haddow , Alexandra Birch

The scaling laws have become the de facto guidelines for designing large language models (LLMs), but they were studied under the assumption of unlimited computing resources for both training and inference. As LLMs are increasingly used as…

Modern LLMs scale at test-time, e.g. via repeated sampling, where inference cost grows with model size and the number of samples. This creates a trade-off that pretraining scaling laws, such as Chinchilla, do not address. We present…

We reveal that low-bit quantization favors undertrained large language models (LLMs) by observing that models with larger sizes or fewer training tokens experience less quantization-induced degradation (QiD) when applying low-bit…

Machine Learning · Computer Science 2024-11-28 Xu Ouyang , Tao Ge , Thomas Hartvigsen , Zhisong Zhang , Haitao Mi , Dong Yu

The rapid scaling of Large Language Models (LLMs) has pushed training workloads far beyond the limits of single-node analysis, demanding a deeper understanding of how these models behave across large-scale, multi-GPU systems. In this paper,…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-22 Seokjin Go , Joongun Park , Spandan More , Hanjiang Wu , Irene Wang , Aaron Jezghani , Tushar Krishna , Divya Mahajan

Large Language Models (LLMs) that can continually improve beyond their training budgets are able to solve increasingly difficult problems by adapting at test time, a property we refer to as extrapolation. However, standard reinforcement…

Machine Learning · Computer Science 2026-03-24 Ian Wu , Yuxiao Qu , Amrith Setlur , Aviral Kumar

Modern large language models (LLMs) excel at tasks that require storing and retrieving knowledge, such as factual recall and question answering. Transformers are central to this capability because they can encode information during training…

Machine Learning · Statistics 2026-03-18 Nuri Mert Vural , Alberto Bietti , Mahdi Soltanolkotabi , Denny Wu

As large language models (LLMs) continue to scale in size, the computational overhead has become a major bottleneck for task-specific fine-tuning. While low-rank adaptation (LoRA) effectively curtails this cost by confining the weight…

Machine Learning · Computer Science 2026-05-15 Yilang Zhang , Xiaodong Yang , Yiwei Cai , Georgios B. Giannakis

Does continued scaling of large language models (LLMs) yield diminishing returns? In this work, we show that short-task benchmarks may give an illusion of slowing progress, as even marginal gains in single-step accuracy can compound into…

Artificial Intelligence · Computer Science 2026-03-16 Akshit Sinha , Arvindh Arun , Shashwat Goel , Steffen Staab , Jonas Geiping

Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their scalability raises a critical question: Have we reached the scaling ceiling? This paper addresses this pivotal question by developing a unified theoretical…

Machine Learning · Computer Science 2024-12-24 Charles Luo

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

Due to the advantages of hypergraphs in modeling high-order relationships in complex systems, they have been applied to higher-order clustering, hypergraph neural networks and computer vision. These applications rely heavily on access to…

Social and Information Networks · Computer Science 2025-10-15 Bingqiao Gu , Jiale Zeng , Xingqin Qi , Dong Li

Tokenization is a fundamental component of large language models (LLMs), yet its influence on model scaling and performance is not fully explored. In this paper, we introduce Over-Tokenized Transformers, a novel framework that decouples…

Computation and Language · Computer Science 2025-05-26 Hongzhi Huang , Defa Zhu , Banggu Wu , Yutao Zeng , Ya Wang , Qiyang Min , Xun Zhou