English
Related papers

Related papers: Riemannian Adaptive Optimization Methods

200 papers

Adam is a widely used stochastic optimization method for deep learning applications. While practitioners prefer Adam because it requires less parameter tuning, its use is problematic from a theoretical point of view since it may not…

Machine Learning · Computer Science 2020-11-25 Mingrui Liu , Wei Zhang , Francesco Orabona , Tianbao Yang

While many Machine Learning methods were developed or transposed on Riemannian manifolds to tackle data with known non Euclidean geometry, Optimal Transport (OT) methods on such spaces have not received much attention. The main OT tool on…

Machine Learning · Computer Science 2024-03-12 Clément Bonet , Lucas Drumetz , Nicolas Courty

We consider the fundamental task of optimising a real-valued function defined in a potentially high-dimensional Euclidean space, such as the loss function in many machine-learning tasks or the logarithm of the probability distribution in…

Machine Learning · Statistics 2024-03-20 Marcelo Hartmann , Bernardo Williams , Hanlin Yu , Mark Girolami , Alessandro Barp , Arto Klami

Adaptive gradient-based optimization methods such as \textsc{Adagrad}, \textsc{Rmsprop}, and \textsc{Adam} are widely used in solving large-scale machine learning problems including deep learning. A number of schemes have been proposed in…

Machine Learning · Computer Science 2019-05-30 Parvin Nazari , Davoud Ataee Tarzanagh , George Michailidis

In recent years, manifold learning has become increasingly popular as a tool for performing non-linear dimensionality reduction. This has led to the development of numerous algorithms of varying degrees of complexity that aim to recover man…

Machine Learning · Statistics 2013-06-03 Dominique Perraul-Joncas , Marina Meila

It was shown recently by Su et al. (2016) that Nesterov's accelerated gradient method for minimizing a smooth convex function $f$ can be thought of as the time discretization of a second-order ODE, and that $f(x(t))$ converges to its…

Optimization and Control · Mathematics 2022-01-19 Valentin Duruisseaux , Melvin Leok

This paper presents a perturbation analysis framework for nonsmooth optimization on connected Riemannian manifolds to bridge the gap between the rapid development of algorithmic approaches and a robust theoretical foundation. Using…

Optimization and Control · Mathematics 2025-10-01 Yuexin Zhou , Chao Ding , Yangjing Zhang

The alternating gradient descent (AGD) is a simple but popular algorithm which has been applied to problems in optimization, machine learning, data ming, and signal processing, etc. The algorithm updates two blocks of variables in an…

Optimization and Control · Mathematics 2018-03-01 Songtao Lu , Mingyi Hong , Zhengdao Wang

Gradient descent (GD) based optimization methods are these days the standard tools to train deep neural networks in artificial intelligence systems. In optimization procedures in deep learning the employed optimizer is often not the…

Optimization and Control · Mathematics 2025-09-24 Steffen Dereich , Robin Graeber , Arnulf Jentzen , Adrian Riekert

We extend the classical primal-dual interior point method from the Euclidean setting to the Riemannian one. Our method, named the Riemannian interior point method, is for solving Riemannian constrained optimization problems. We establish…

Optimization and Control · Mathematics 2024-03-06 Zhijian Lai , Akiko Yoshise

In this work, we propose an optimization algorithm which we call norm-adapted gradient descent. This algorithm is similar to other gradient-based optimization algorithms like Adam or Adagrad in that it adapts the learning rate of stochastic…

Machine Learning · Computer Science 2020-10-14 David Sprunger

We propose the first global accelerated gradient method for Riemannian manifolds. Toward establishing our result we revisit Nesterov's estimate sequence technique and develop an alternative analysis for it that may also be of independent…

Optimization and Control · Mathematics 2020-01-27 Kwangjun Ahn , Suvrit Sra

Representing graphs as sets of node embeddings in certain curved Riemannian manifolds has recently gained momentum in machine learning due to their desirable geometric inductive biases, e.g., hierarchical structures benefit from hyperbolic…

Machine Learning · Computer Science 2020-06-09 Calin Cruceru , Gary Bécigneul , Octavian-Eugen Ganea

This paper proposes a generalized framework with joint normalization which learns lower-dimensional subspaces with maximum discriminative power by making use of the Riemannian geometry. In particular, we model the similarity/dissimilarity…

Computer Vision and Pattern Recognition · Computer Science 2017-11-20 Tianci Liu , Zelin Shi , Yunpeng Liu

In Riemannian optimization, it is well known that the condition number of the Riemannian Hessian at an optimum strongly influences the asymptotic convergence behavior of optimization algorithms. On the manifold of symmetric positive…

Optimization and Control · Mathematics 2026-05-04 Derun Zhou , Keisuke Yano , Mahito Sugiyama

We study a class of nonsmooth stochastic optimization problems on Riemannian manifolds. In this work, we propose MARS-ADMM, the first stochastic Riemannian alternating direction method of multipliers with provable near-optimal complexity…

Optimization and Control · Mathematics 2025-12-30 Jiachen Jin , Kangkang Deng , Hongxia Wang

This paper studies a class of adaptive gradient based momentum algorithms that update the search directions and learning rates simultaneously using past gradients. This class, which we refer to as the "Adam-type", includes the popular…

Machine Learning · Computer Science 2019-03-12 Xiangyi Chen , Sijia Liu , Ruoyu Sun , Mingyi Hong

Stochastic gradient descent (\textsc{Sgd}) methods are the most powerful optimization tools in training machine learning and deep learning models. Moreover, acceleration (a.k.a. momentum) methods and diagonal scaling (a.k.a. adaptive…

Machine Learning · Statistics 2018-10-02 Qi Deng , Yi Cheng , Guanghui Lan

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

Recently, a Riemannian proximal Newton method has been developed for optimizing problems in the form of $\min_{x\in\mathcal{M}} f(x) + \mu \|x\|_1$, where $\mathcal{M}$ is a compact embedded submanifold and $f(x)$ is smooth. Although this…

Optimization and Control · Mathematics 2025-03-25 Wen Huang , Wutao Si