English
Related papers

Related papers: SOAP: Improving and Stabilizing Shampoo using Adam

200 papers

Machine learning has achieved remarkable success over the past couple of decades, often attributed to a combination of algorithmic innovations and the availability of high-quality data available at scale. However, a third critical component…

Distributed adaptive stochastic gradient methods have been widely used for large-scale nonconvex optimization, such as training deep learning models. However, their communication complexity on finding $\varepsilon$-stationary points has…

Machine Learning · Computer Science 2023-08-25 Congliang Chen , Li Shen , Wei Liu , Zhi-Quan Luo

Fine-tuning large language models (LLMs) often faces GPU memory bottlenecks: the backward pass of first-order optimizers like Adam increases memory usage to more than 10 times the inference level (e.g., 633 GB for OPT-30B). Zeroth-order…

Machine Learning · Computer Science 2025-07-01 Sizhe Dang , Yangyang Guo , Yanjun Zhao , Haishan Ye , Xiaodong Zheng , Guang Dai , Ivor Tsang

Diffusion policies have recently emerged as a powerful class of visuomotor controllers for robot manipulation, offering stable training and expressive multi-modal action modeling. However, existing approaches typically treat action…

Robotics · Computer Science 2025-10-01 Zezeng Li , Rui Yang , Ruochen Chen , ZhongXuan Luo , Liming Chen

The success of the Adam optimizer on a wide array of architectures has made it the default in settings where stochastic gradient descent (SGD) performs poorly. However, our theoretical understanding of this discrepancy is lagging,…

Machine Learning · Computer Science 2023-04-28 Frederik Kunstner , Jacques Chen , Jonathan Wilder Lavington , Mark Schmidt

Data-driven methods are emerging as efficient alternatives to traditional numerical forecasting, offering fast inference and lower computational cost. Yet, for complex systems, long-term accuracy often deteriorates due to error…

Machine Learning · Computer Science 2025-09-03 Hao Zhou , Sibo Cheng

Large language models (LLMs) have revolutionized natural language processing by solving a wide range of tasks simply guided by a prompt. Yet their performance is highly sensitive to prompt formulation. While automatic prompt optimization…

Computation and Language · Computer Science 2025-06-18 Tom Zehle , Moritz Schlager , Timo Heiß , Matthias Feurer

In practical applications, machine learning algorithms are often needed to learn classifiers that optimize domain specific performance measures. Previously, the research has focused on learning the needed classifier in isolation, yet…

Machine Learning · Computer Science 2015-03-17 Nan Li , Ivor W. Tsang , Zhi-Hua Zhou

Generative AI can now synthesize strikingly realistic images from text, yet output quality remains highly sensitive to how prompts are phrased. Direct Preference Optimization (DPO) offers a lightweight, off-policy alternative to RL for…

Computation and Language · Computer Science 2025-07-30 Anas Mohamed , Azal Ahmad Khan , Xinran Wang , Ahmad Faraz Khan , Shuwen Ge , Saman Bahzad Khan , Ayaan Ahmad , Ali Anwar

The Segment Anything Model (SAM) has garnered significant attention for its versatile segmentation abilities and intuitive prompt-based interface. However, its application in medical imaging presents challenges, requiring either substantial…

Computer Vision and Pattern Recognition · Computer Science 2024-03-28 Zhiheng Cheng , Qingyue Wei , Hongru Zhu , Yan Wang , Liangqiong Qu , Wei Shao , Yuyin Zhou

Many problems in control theory can be formulated as semidefinite programs (SDPs). For large-scale SDPs, it is important to exploit the inherent sparsity to improve the scalability. This paper develops efficient first-order methods to solve…

Optimization and Control · Mathematics 2020-01-13 Yang Zheng , Giovanni Fantuzzi , Antonis Papachristodoulou , Paul Goulart , Andrew Wynn

In this paper, we present a comprehensive study on the convergence properties of Adam-family methods for nonsmooth optimization, especially in the training of nonsmooth neural networks. We introduce a novel two-timescale framework that…

Optimization and Control · Mathematics 2024-02-20 Nachuan Xiao , Xiaoyin Hu , Xin Liu , Kim-Chuan Toh

A unified framework for first-order optimization algorithms fornonconvex unconstrained optimization is proposed that uses adaptivelypreconditioned gradients and includes popular methods such as full anddiagonal AdaGrad, AdaNorm, as well as…

Machine Learning · Computer Science 2026-05-04 S. Gratton , Ph. L. Toint

Targeting solutions over `flat' regions of the loss landscape, sharpness-aware minimization (SAM) has emerged as a powerful tool to improve generalizability of deep neural network based learning. While several SAM variants have been…

Machine Learning · Computer Science 2025-01-14 Yilang Zhang , Bingcong Li , Georgios B. Giannakis

As machine learning permeates more industries and models become more expensive and time consuming to train, the need for efficient automated hyperparameter optimization (HPO) has never been more pressing. Multi-step planning based…

Machine Learning · Computer Science 2022-11-18 Lucio M. Dery , Abram L. Friesen , Nando De Freitas , Marc'Aurelio Ranzato , Yutian Chen

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

Generative recommendation treats next-item prediction as autoregressive item-identifier generation. Specifically, items are encoded as semantic identifiers (SIDs), which are short coarse-to-fine token sequences whose early tokens capture…

Artificial Intelligence · Computer Science 2026-05-19 Zaiyi Zheng , Guanghui Min , Yaochen Zhu , Liang Wu , Liangjie Hong , Chen Chen , Jundong Li

The homogeneous second-order descent method (Zhang et al. 2025, Mathematics of Operations Research) was initially proposed for unconstrained optimisation problems. HSODM shows excellent performance with respect to the global complexity rate…

Optimization and Control · Mathematics 2026-04-08 Yonggang Pei , Yubing Lin , Mauricio Silva Louzeiro , Detong Zhu

Predicting the next activity in an ongoing process is one of the most common classification tasks in the business process management (BPM) domain. It allows businesses to optimize resource allocation, enhance operational efficiency, and…

Artificial Intelligence · Computer Science 2024-03-15 Alon Oved , Segev Shlomov , Sergey Zeltyn , Nir Mashkif , Avi Yaeli

Learning from a sequence of interactions, as soon as observations are perceived and acted upon, without explicitly storing them, holds the promise of simpler, more efficient and adaptive algorithms. For over a decade, however, deep…

Machine Learning · Computer Science 2026-05-11 Florin Gogianu , Adrian Catalin Lutu , Razvan Pascanu
‹ Prev 1 8 9 10 Next ›