English
Related papers

Related papers: Pushing the Limits of Low-Bit Optimizers: A Focus …

200 papers

Training language models becomes increasingly expensive with scale, prompting numerous attempts to improve optimization efficiency. Despite these efforts, the Adam optimizer remains the most widely used, due to a prevailing view that it is…

Machine Learning · Computer Science 2025-03-03 Rosie Zhao , Depen Morwani , David Brandfonbrener , Nikhil Vyas , Sham Kakade

In this research, we address critical concerns related to the numerical instability observed in 16-bit computations of machine learning models. Such instability, particularly when employing popular optimization algorithms like Adam, often…

Machine Learning · Computer Science 2025-06-18 Juyoung Yun

Despite the popularity of the Adam optimizer in practice, most theoretical analyses study Stochastic Gradient Descent (SGD) as a proxy for Adam, and little is known about how the solutions found by Adam differ. In this paper, we show that…

Machine Learning · Computer Science 2025-11-05 Xinghan Li , Haodong Wen , Kaifeng Lyu

This study combines simulated annealing with delta evaluation to solve the joint stratification and sample allocation problem. In this problem, atomic strata are partitioned into mutually exclusive and collectively exhaustive strata. Each…

Artificial Intelligence · Computer Science 2021-11-23 Mervyn O'Luing , Steven Prestwich , S. Armagan Tarim

State Space Models (SSMs) are emerging as a compelling alternative to Transformers because of their consistent memory usage and high performance. Despite this, scaling up SSMs on cloud services or limited-resource devices is challenging due…

Machine Learning · Computer Science 2025-11-07 Hung-Yueh Chiang , Chi-Chih Chang , Natalia Frumkin , Kai-Chiang Wu , Mohamed S. Abdelfattah , Diana Marculescu

Large language models (LLMs) demand extensive memory capacity during both fine-tuning and inference. To enable memory-efficient fine-tuning, existing methods apply block-wise quantization techniques, such as NF4 and AF4, to the network…

Machine Learning · Computer Science 2025-05-13 Patrick Blumenberg , Thomas Graave , Tim Fingscheidt

To efficiently train large-scale models, low-bit gradient communication compresses full-precision gradients on local GPU nodes into low-precision ones for higher gradient synchronization efficiency among GPU nodes. However, it often…

Machine Learning · Computer Science 2024-12-02 Xingyu Xie , Zhijie Lin , Kim-Chuan Toh , Pan Zhou

The disparity in healthcare personnel expertise and medical resources across different regions of the world is a pressing social issue. Artificial intelligence technology offers new opportunities to alleviate this issue. Segment Anything…

Computer Vision and Pattern Recognition · Computer Science 2024-10-04 Zhikai Li , Jing Zhang , Qingyi Gu

Several analog-to-digital conversion methods for bandlimited signals used in applications, such as Sigma Delta quantization schemes, employ coarse quantization coupled with oversampling. The standard mathematical model for the error accrued…

Information Theory · Computer Science 2010-04-21 Felix Krahmer , Rachel Ward

The design of analog circuits is a cornerstone of integrated circuit (IC) development, requiring the optimization of complex, interconnected sub-structures such as amplifiers, comparators, and buffers. Traditionally, this process relies…

Hardware Architecture · Computer Science 2025-02-06 Karthik Somayaji N. S , Peng Li

The optimization algorithm and its hyperparameters can significantly affect the training speed and resulting model accuracy in machine learning applications. The wish list for an ideal optimizer includes fast and smooth convergence to low…

Machine Learning · Computer Science 2024-02-20 Marco Eckhoff , Markus Reiher

Segment Anything Model (SAM) has gained significant recognition in the field of semantic segmentation due to its versatile capabilities and impressive performance. Despite its success, SAM faces two primary limitations: (1) it relies…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Yuchen Li , Li Zhang , Youwei Liang , Pengtao Xie

We propose Adam-mini, an optimizer that achieves on par or better performance than AdamW with 50% less memory footprint. Adam-mini reduces memory by cutting down the learning rate resources in Adam (i.e., $1/\sqrt{v}$). By investigating the…

Machine Learning · Computer Science 2025-02-25 Yushun Zhang , Congliang Chen , Ziniu Li , Tian Ding , Chenwei Wu , Diederik P. Kingma , Yinyu Ye , Zhi-Quan Luo , Ruoyu Sun

Despite its flexibility to learn diverse inductive biases in machine learning programs, meta learning (i.e., learning to learn) has long been recognized to suffer from poor scalability due to its tremendous compute/memory costs, training…

Machine Learning · Computer Science 2023-10-24 Sang Keun Choe , Sanket Vaibhav Mehta , Hwijeen Ahn , Willie Neiswanger , Pengtao Xie , Emma Strubell , Eric Xing

Multiple Instance Learning (MIL) effectively analyzes whole slide images but faces overfitting due to attention over-concentration. While existing solutions rely on complex architectural modifications or additional processing steps, we…

Computer Vision and Pattern Recognition · Computer Science 2025-07-01 Yunlong Zhang , Honglin Li , Yunxuan Sun , Zhongyi Shui , Jingxiong Li , Chenglu Zhu , Lin Yang

Despite recent progress in optimal hyperparameter transfer under model and dataset scaling, no unifying explanatory principle has been established. For Adam and Scion optimizers, we discover that joint optimal scaling across model and…

Machine Learning · Computer Science 2026-01-28 Oleg Filatov , Jiangtao Wang , Jan Ebert , Stefan Kesselheim

Quantization-aware training (QAT) is an effective method to drastically reduce the memory footprint of LLMs while keeping performance degradation at an acceptable level. However, the optimal choice of quantization format and bit-width…

Machine Learning · Computer Science 2026-02-18 Sohir Maskey , Constantin Eichenberg , Johannes Messner , Douglas Orr

Extremely low-bit quantization is critical for efficiently deploying Large Language Models (LLMs), yet it often leads to severe performance degradation at 2 bits and even at 4 bits (e.g., MXFP4). We present SignRoundV2, a post-training…

Computation and Language · Computer Science 2026-05-19 Wenhua Cheng , Weiwei Zhang , Heng Guo , Haihao Shen , Zaner Ma

Adaptive gradient optimization methods, such as Adam, are prevalent in training deep neural networks across diverse machine learning tasks due to their ability to achieve faster convergence. However, these methods often suffer from…

Machine Learning · Computer Science 2025-02-12 Abulikemu Abuduweili , Changliu Liu

Machine learning algorithms aim to find patterns from observations, which may include some noise, especially in robotics domain. To perform well even with such noise, we expect them to be able to detect outliers and discard them when…

Machine Learning · Computer Science 2020-03-04 Wendyam Eric Lionel Ilboudo , Taisuke Kobayashi , Kenji Sugimoto