English
Related papers

Related papers: Intriguing Properties of Quantization at Scale

200 papers

Quantization neural networks (QNNs) are very attractive to the industry because their extremely cheap calculation and storage overhead, but their performance is still worse than that of networks with full-precision parameters. Most of…

Computer Vision and Pattern Recognition · Computer Science 2020-02-13 Chuanjian Liu , Kai Han , Yunhe Wang , Hanting Chen , Qi Tian , Chunjing Xu

Emergent behavior that appears at a given level of organization may be characterized as arising from an organizationally lower level in such a way that it transcends a mere increase in the behavioral degree of complexity. It is therefore to…

General Physics · Physics 2013-07-22 Gerald E. Marsh

Neural networks appear to have mysterious generalization properties when using parameter counting as a proxy for complexity. Indeed, neural networks often have many more parameters than there are data points, yet still provide good…

Machine Learning · Computer Science 2020-05-26 Wesley J. Maddox , Gregory Benton , Andrew Gordon Wilson

While post-training quantization is widely adopted for efficient deployment of large language models, the mechanisms underlying quantization robustness remain unclear. We conduct a comprehensive analysis of quantization degradation across…

Machine Learning · Computer Science 2026-02-02 Albert Catalan-Tatjer , Niccolò Ajroldi , Jonas Geiping

In-context learning (ICL) enables large language models to adapt to new tasks from demonstrations without parameter updates. Despite extensive empirical studies, a principled understanding of ICL emergence at scale remains more elusive. We…

Machine Learning · Computer Science 2025-11-11 Sushant Mehta , Ishan Gupta

Quantization reduces the numerical precision of Transformer computations and is widely used to accelerate inference, yet its effect on expressivity remains poorly characterized. We demonstrate a fine-grained theoretical tradeoff between…

Machine Learning · Computer Science 2026-02-04 Sayak Chakrabarti , Toniann Pitassi , Josh Alman

Increasing the number of parameters in large language models (LLMs) usually improves performance in downstream tasks but raises compute and memory costs, making deployment difficult in resource-limited settings. Quantization techniques,…

Computation and Language · Computer Science 2024-06-07 Renren Jin , Jiangcun Du , Wuwei Huang , Wei Liu , Jian Luan , Bin Wang , Deyi Xiong

Optimisation algorithms are commonly compared on benchmarks to get insight into performance differences. However, it is not clear how closely benchmarks match the properties of real-world problems because these properties are largely…

Neural and Evolutionary Computing · Computer Science 2021-07-15 Koen van der Blom , Timo M. Deist , Vanessa Volz , Mariapia Marchi , Yusuke Nojima , Boris Naujoks , Akira Oyama , Tea Tušar

We explore the possibility of putting constraints on quintessence models with large-scale structure observations. In particular we compute the linear and second order growth rate of the fluctuations in different flavors of quintessence…

Astrophysics · Physics 2009-11-06 K. Benabed , F. Bernardeau

Increasing model size has unlocked a dazzling array of capabilities in modern language models. At the same time, even frontier models remain vulnerable to jailbreaks and prompt injections, despite concerted efforts to make them robust. As…

Machine Learning · Computer Science 2025-06-06 Nikolaus Howe , Ian McKenzie , Oskar Hollinsworth , Michał Zajac , Tom Tseng , Aaron Tucker , Pierre-Luc Bacon , Adam Gleave

Quantization reduces computation costs of neural networks but suffers from performance degeneration. Is this accuracy drop due to the reduced capacity, or inefficient training during the quantization procedure? After looking into the…

Computer Vision and Pattern Recognition · Computer Science 2019-12-24 Qing Jin , Linjie Yang , Zhenyu Liao

Training large language models (LLMs) from scratch is an expensive endeavor, particularly as world knowledge continually evolves. To maintain relevance and accuracy of LLMs, model editing has emerged as a pivotal research area. While these…

Computation and Language · Computer Science 2024-09-30 Tsung-Hsuan Pan , Chung-Chi Chen , Hen-Hsen Huang , Hsin-Hsi Chen

Demonstrating quantum advantage in machine learning tasks requires navigating a complex landscape of proposed models and algorithms. To bring clarity to this search, we introduce a framework that connects the structure of parametrized…

Quantum Physics · Physics 2025-12-23 Sergi Masot-Llima , Elies Gil-Fuster , Carlos Bravo-Prieto , Jens Eisert , Tommaso Guaita

The fine-structure constant alpha approximately 1/137 is traditionally regarded as a fundamental dimensionless parameter. I argue instead that alpha is a scaled quantity that arises only where the structural scales contributed by classical…

History and Philosophy of Physics · Physics 2025-12-09 Harry Sticker

Outlier detection algorithms typically assign an outlier score to each observation in a dataset, indicating the degree to which an observation is an outlier. However, these scores are often not comparable across algorithms and can be…

Machine Learning · Computer Science 2024-10-31 Philipp Röchner , Henrique O. Marques , Ricardo J. G. B. Campello , Arthur Zimek , Franz Rothlauf

The surprising ability of Large Language Models (LLMs) to perform well on complex reasoning with only few-shot chain-of-thought prompts is believed to emerge only in very large-scale models (100+ billion parameters). We show that such…

Computation and Language · Computer Science 2023-01-31 Yao Fu , Hao Peng , Litu Ou , Ashish Sabharwal , Tushar Khot

Large language models (LLMs) demand substantial computational and memory resources, creating deployment challenges. Quantization-aware training (QAT) addresses these challenges by reducing model precision while maintaining performance.…

Machine Learning · Computer Science 2025-05-21 Mengzhao Chen , Chaoyi Zhang , Jing Liu , Yutao Zeng , Zeyue Xue , Zhiheng Liu , Yunshui Li , Jin Ma , Jie Huang , Xun Zhou , Ping Luo

We analyze characteristics' joint predictive information through the lens of out-of-sample power utility functions. Linking weights to characteristics to form optimal portfolios suffers from estimation error which we mitigate by maximizing…

General Finance · Quantitative Finance 2024-02-05 Christopher G. Lamoureux , Huacheng Zhang

Emergence is a fascinating property of large language models and neural networks more broadly: as models scale and train for longer, they sometimes develop new abilities in sudden ways. Despite initial studies, we still lack a comprehensive…

Machine Learning · Computer Science 2025-12-11 Nicolas Zucchet , Francesco d'Angelo , Andrew K. Lampinen , Stephanie C. Y. Chan

Weight-perturbation evolution strategies (ES) can fine-tune billion-parameter language models with surprisingly small populations (e.g., $N\!\approx\!30$), contradicting classical zeroth-order curse-of-dimensionality intuition. We also…

Machine Learning · Computer Science 2026-02-03 Qiyao Liang , Jinyeop Song , Yizhou Liu , Jeff Gore , Ila Fiete , Risto Miikkulainen , Xin Qiu
‹ Prev 1 3 4 5 6 7 10 Next ›