English
Related papers

Related papers: Generalizing Adam to Manifolds for Efficiently Tra…

200 papers

Heavy ball momentum is crucial in accelerating (stochastic) gradient-based optimization algorithms for machine learning. Existing heavy ball momentum is usually weighted by a uniform hyperparameter, which relies on excessive tuning.…

Machine Learning · Computer Science 2021-10-19 Tao Sun , Huaming Ling , Zuoqiang Shi , Dongsheng Li , Bao Wang

Learning representations on Grassmann manifolds is popular in quite a few visual recognition tasks. In order to enable deep learning on Grassmann manifolds, this paper proposes a deep network architecture by generalizing the Euclidean…

Computer Vision and Pattern Recognition · Computer Science 2018-01-30 Zhiwu Huang , Jiqing Wu , Luc Van Gool

For a long period of time, Adam has served as the ubiquitous default choice for training deep neural networks. Recently, many new optimizers have been introduced, out of which Muon has perhaps gained the highest popularity due to its…

Machine Learning · Computer Science 2026-03-03 Sara Dragutinović , Rajesh Ranganath

Manifold learning is a popular and quickly-growing subfield of machine learning based on the assumption that one's observed data lie on a low-dimensional manifold embedded in a higher-dimensional space. This thesis presents a mathematical…

Machine Learning · Computer Science 2020-11-04 Luke Melas-Kyriazi

Although Deep Learning (DL) has achieved success in complex Artificial Intelligence (AI) tasks, it suffers from various notorious problems (e.g., feature redundancy, and vanishing or exploding gradients), since updating parameters in…

Machine Learning · Computer Science 2023-02-17 Yanhong Fei , Xian Wei , Yingjie Liu , Zhengyu Li , Mingsong Chen

The rapid scaling of large language models (LLMs) has made low-precision training essential for reducing memory, improving efficiency, and enabling larger models and datasets. Existing convergence theories for adaptive optimizers, however,…

Machine Learning · Computer Science 2026-03-03 Xuan Tang , Jichu Li , Difan Zou

Randomization is a powerful tool that endows algorithms with remarkable properties. For instance, randomized algorithms excel in adversarial settings, often surpassing the worst-case performance of deterministic algorithms with large…

Machine Learning · Computer Science 2024-08-21 Johannes von Oswald , Seijin Kobayashi , Yassir Akram , Angelika Steger

Stochastic gradient descent (SGD) optimization methods such as the plain vanilla SGD method and the popular Adam optimizer are nowadays the method of choice in the training of artificial neural networks (ANNs). Despite the remarkable…

Optimization and Control · Mathematics 2024-02-09 Arnulf Jentzen , Adrian Riekert

Convolutional neural networks have outperformed humans in image recognition tasks, but they remain vulnerable to attacks from adversarial examples. Since these data are crafted by adding imperceptible noise to normal images, their existence…

Computer Vision and Pattern Recognition · Computer Science 2021-06-10 Heng Yin , Hengwei Zhang , Jindong Wang , Ruiyu Dou

Existing EEG foundation models mainly treat neural signals as generic time series in Euclidean space, ignoring the intrinsic geometric structure of neural dynamics that constrains brain activity to low-dimensional manifolds. This…

Machine Learning · Computer Science 2025-11-24 Yihang Fu , Lifang He , Qingyu Chen

Generative Adversarial Networks (GANs) have demonstrated remarkable advancements in generative modeling; however, their training is often resource-intensive, requiring extensive computational time and hundreds of thousands of epochs. This…

Machine Learning · Computer Science 2024-10-28 Beka Modrekiladze

Orthogonality constrained optimization is widely used in applications from science and engineering. Due to the nonconvex orthogonality constraints, many numerical algorithms often can hardly achieve the global optimality. We aim at…

Optimization and Control · Mathematics 2019-06-18 Honglin Yuan , Xiaoyi Gu , Rongjie Lai , Zaiwen Wen

Deep learning optimizers are often motivated through a mix of convex and approximate second-order theory. We select three such methods -- Adam, Shampoo and Prodigy -- and argue that each method can instead be understood as a squarely…

Machine Learning · Computer Science 2024-12-09 Jeremy Bernstein , Laker Newhouse

The goal of this thesis is to develop the optimisation and generalisation theoretic foundations of learning in artificial neural networks. On optimisation, a new theoretical framework is proposed for deriving architecture-dependent…

Neural and Evolutionary Computing · Computer Science 2022-10-20 Jeremy Bernstein

Deep neural networks have reached human-level performance on many computer vision tasks. However, the objectives used to train these networks enforce only that similar images are embedded at similar locations in the representation space,…

Computer Vision and Pattern Recognition · Computer Science 2023-09-27 Lukas Muttenthaler , Lorenz Linhardt , Jonas Dippel , Robert A. Vandermeulen , Katherine Hermann , Andrew K. Lampinen , Simon Kornblith

Much as replacing hand-designed features with learned functions has revolutionized how we solve perceptual tasks, we believe learned algorithms will transform how we train models. In this work we focus on general-purpose learned optimizers…

Machine Learning · Computer Science 2020-09-24 Luke Metz , Niru Maheswaranathan , C. Daniel Freeman , Ben Poole , Jascha Sohl-Dickstein

In this work, we develop new generalization bounds for neural networks trained on data supported on Riemannian manifolds. Existing generalization theories often rely on complexity measures derived from Euclidean geometry, which fail to…

Machine Learning · Computer Science 2025-07-08 Krisanu Sarkar

Recent methods in geometric deep learning have introduced various neural networks to operate over data that lie on Riemannian manifolds. Such networks are often necessary to learn well over graphs with a hierarchical structure or to learn…

Machine Learning · Statistics 2023-10-17 Isay Katsman , Eric Ming Chen , Sidhanth Holalkere , Anna Asch , Aaron Lou , Ser-Nam Lim , Christopher De Sa

Deep neural network (DNN) generally takes thousands of iterations to optimize via gradient descent and thus has a slow convergence. In addition, softmax, as a decision layer, may ignore the distribution information of the data during…

Machine Learning · Computer Science 2021-06-16 Rui Zhang , Ziheng Jiao , Hongyuan Zhang , Xuelong Li

Adaptive optimization methods such as AdaGrad, RMSprop and Adam have been proposed to achieve a rapid training process with an element-wise scaling term on learning rates. Though prevailing, they are observed to generalize poorly compared…

Machine Learning · Computer Science 2019-04-22 Liangchen Luo , Yuanhao Xiong , Yan Liu , Xu Sun