English
Related papers

Related papers: Rethinking Language Model Scaling under Transferab…

200 papers

We study compute efficiency of LLM training when using different parameterizations, i.e., rules for adjusting model and optimizer hyperparameters (HPs) as model size changes. Some parameterizations fail to transfer optimal base HPs (such as…

Machine Learning · Computer Science 2026-01-21 Nolan Dey , Bin Claire Zhang , Lorenzo Noci , Mufan Li , Blake Bordelon , Shane Bergsma , Cengiz Pehlevan , Boris Hanin , Joel Hestness

Recent studies have found that model performance has a smooth power-law relationship, or scaling laws, with training data and model size, for a wide range of problems. These scaling laws allow one to choose nearly optimal data and model…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-29 Yile Gu , Prashanth Gurunath Shivakumar , Jari Kolehmainen , Ankur Gandhe , Ariya Rastrow , Ivan Bulyko

Despite their remarkable achievement, gigantic transformers encounter significant drawbacks, including exorbitant computational and memory footprints during training, as well as severe collapse evidenced by a high degree of parameter…

Machine Learning · Computer Science 2023-03-06 Tianlong Chen , Zhenyu Zhang , Ajay Jaiswal , Shiwei Liu , Zhangyang Wang

The scaling of the optimal AdamW weight decay hyperparameter with model and dataset size is critical as we seek to build larger models, but is poorly understood. We show that weights learned by AdamW can be understood as an exponential…

Machine Learning · Computer Science 2025-06-03 Xi Wang , Laurence Aitchison

The Mixture of Experts (MoE) for language models has been proven effective in augmenting the capacity of models by dynamically routing each input token to a specific subset of experts for processing. Despite the success, most existing…

Machine Learning · Computer Science 2024-07-26 Hao Zhao , Zihan Qiu , Huijia Wu , Zili Wang , Zhaofeng He , Jie Fu

We introduce a machine-learning framework to learn the hyperparameter sequence of first-order methods (e.g., the step sizes in gradient descent) to quickly solve parametric convex optimization problems. Our computational architecture…

Optimization and Control · Mathematics 2024-12-23 Rajiv Sambharya , Bartolomeo Stellato

As language models scale up, it becomes increasingly expensive to verify research ideas because conclusions on small models do not trivially transfer to large ones. A possible solution is to establish a generic system that accurately…

Computation and Language · Computer Science 2024-04-09 Yiqun Yao , Siqi fan , Xiusheng Huang , Xuezhi Fang , Xiang Li , Ziyi Ni , Xin Jiang , Xuying Meng , Peng Han , Shuo Shang , Kang Liu , Aixin Sun , Yequan Wang

Neural scaling laws have driven the field's ever-expanding exponential growth in parameters, data and compute. While scaling behaviors for pretraining losses and discriminative benchmarks are well established, generative benchmarks such as…

Machine Learning · Computer Science 2026-02-03 Rylan Schaeffer , Noam Levi , Brando Miranda , Sanmi Koyejo

Recent advances in large language models (LLMs) highlight a strong connection between intelligence and compression. Learned image compression, a fundamental task in modern data compression, has made significant progress in recent years.…

Computer Vision and Pattern Recognition · Computer Science 2025-08-13 Yuqi Li , Haotian Zhang , Li Li , Dong Liu , Feng Wu

Low-Rank Adaptation (LoRA) is a standard tool for parameter-efficient finetuning of large models. While it induces a small memory footprint, its training dynamics can be surprisingly complex as they depend on several hyperparameters such as…

Machine Learning · Computer Science 2026-02-09 Nan Chen , Soledad Villar , Soufiane Hayou

Large language models typically employ vocabularies of over 100k tokens, which creates a major computational bottleneck at the final linear projection layer when performing speculative decoding. Current methods for vocabulary pruning depend…

Computation and Language · Computer Science 2026-05-27 Zhiyang Chen , Daliang Xu , Yinyuan Zhang , Chenghua Wang , Mengwei Xu , Yun Ma

The exponential growth in Large Language Model (LLM) parameters has transformed model training into an increasingly resource-intensive endeavor. With the stagnation of Moore's Law and the widening disparity between computation throughput…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-04-22 Size Zheng , Xuegui Zheng , Li-wen Chang , Jidong Zhai

Model merging has emerged as a lightweight paradigm for enhancing Large Language Models (LLMs), yet its underlying mechanisms remain poorly understood. In this work, we analyze late-stage pre-training trajectories and uncover a…

Machine Learning · Computer Science 2026-05-27 Wenjie Zhou , Bohan Wang , Hongtao Zhang , Chenxi Jia , Wei Chen , Xueqi Cheng

Machine-learned interatomic potentials (MILPs) are rapidly gaining interest for molecular modeling, as they provide a balance between quantum-mechanical level descriptions of atomic interactions and reasonable computational efficiency.…

Computational Physics · Physics 2024-08-30 Gustavo R. Pérez-Lemus , Yinan Xu , Yezhi Jin , Pablo F. Zubieta Rico , Juan J. de Pablo

Large language models (LLMs) have shown great success in text modeling tasks across domains. However, natural language exhibits inherent semantic hierarchies and nuanced geometric structure, which current LLMs do not capture completely…

Machine Learning · Computer Science 2025-11-07 Neil He , Rishabh Anand , Hiren Madhu , Ali Maatouk , Smita Krishnaswamy , Leandros Tassiulas , Menglin Yang , Rex Ying

Generative foundation models are increasingly scaled in both width and depth, posing significant challenges for stable feature learning and reliable hyperparameter (HP) transfer across model sizes. While maximal update parameterization…

Machine Learning · Computer Science 2026-05-12 Chenyu Zheng , Rongzhen Wang , Xinyu Zhang , Chongxuan Li

The $\mu$-parameterization ($\mu$P) provides a principled foundation for large language model (LLM) training by prescribing width-independent learning dynamics, which in turn enables predictable scaling behavior and robust hyperparameter…

Machine Learning · Computer Science 2026-01-08 John Zhao

Hyperparameter optimization is an important subfield of machine learning that focuses on tuning the hyperparameters of a chosen algorithm to achieve peak performance. Recently, there has been a stream of methods that tackle the issue of…

Machine Learning · Computer Science 2023-10-26 Arlind Kadra , Maciej Janowski , Martin Wistuba , Josif Grabocka

Scaling large models requires optimization strategies that ensure rapid convergence grounded in stability. Maximal Update Parametrization ($\boldsymbol{\mu}$P) provides a theoretical safeguard for width-invariant $\Theta(1)$ activation…

Machine Learning · Computer Science 2026-03-06 Tian Xie , Haoming Luo , Haoyu Tang , Yiwen Hu , Jason Klein Liu , Qingnan Ren , Yang Wang , Wayne Xin Zhao , Rui Yan , Bing Su , Chong Luo , Baining Guo

The successful training of deep neural networks requires addressing challenges such as overfitting, numerical instabilities leading to divergence, and increasing variance in the residual stream. A common solution is to apply regularization…

Machine Learning · Computer Science 2025-11-20 Jörg K. H. Franke , Urs Spiegelhalter , Marianna Nezhurina , Jenia Jitsev , Frank Hutter , Michael Hefenbrock