English
Related papers

Related papers: Decentralized Riemannian natural gradient methods …

200 papers

Using second-order optimization methods for training deep neural networks (DNNs) has attracted many researchers. A recently proposed method, Eigenvalue-corrected Kronecker Factorization (EKFAC) (George et al., 2018), proposes an…

Machine Learning · Computer Science 2020-11-30 Kai-Xin Gao , Xiao-Lei Liu , Zheng-Hai Huang , Min Wang , Shuangling Wang , Zidong Wang , Dachuan Xu , Fan Yu

This work addresses the decentralized optimization problem where a group of agents with coupled private objective functions work together to exactly optimize the summation of local interests. Upon modeling the decentralized problem as an…

Optimization and Control · Mathematics 2020-03-18 Changxin Liu , Huiping Li , Yang Shi

Natural-gradient methods markedly accelerate the training of Physics-Informed Neural Networks (PINNs), yet their Gauss--Newton update must be solved in the parameter space, incurring a prohibitive $O(n^3)$ time complexity, where $n$ is the…

Machine Learning · Computer Science 2025-10-09 Anas Jnini , Flavio Vella

This paper considers decentralized consensus optimization problems where nodes of a network have access to different summands of a global objective function. Nodes cooperate to minimize the global objective by exchanging information with…

Optimization and Control · Mathematics 2016-09-21 Aryan Mokhtari , Wei Shi , Qing Ling , Alejandro Ribeiro

In this paper, we propose new structured second-order methods and structured adaptive-gradient methods obtained by performing natural-gradient descent on structured parameter spaces. Natural-gradient descent is an attractive approach to…

Machine Learning · Statistics 2022-02-22 Wu Lin , Frank Nielsen , Mohammad Emtiyaz Khan , Mark Schmidt

The indicator matrix plays an important role in machine learning, but optimizing it is an NP-hard problem. We propose a new relaxation of the indicator matrix and prove that this relaxation forms a manifold, which we call the Relaxed…

Machine Learning · Computer Science 2025-04-14 Jinghui Yuan , Fangyuan Xie , Feiping Nie , Xuelong Li

We study decentralized smooth optimization problems over compact submanifolds. Recasting it as a composite optimization problem, we propose a decentralized Douglas-Rachford splitting algorithm, DDRS. When the proximal operator of the local…

Optimization and Control · Mathematics 2023-11-29 Kangkang Deng , Jiang Hu , Hongxia Wang

We consider Riemannian optimization problems with inequality and equality constraints and analyze a class of Riemannian interior point methods for solving them. The algorithm of interest consists of outer and inner iterations. We show that,…

Optimization and Control · Mathematics 2026-05-12 Mitsuaki Obara , Takayuki Okuno , Akiko Takeda

As a second-order method, the Natural Gradient Descent (NGD) has the ability to accelerate training of neural networks. However, due to the prohibitive computational and memory costs of computing and inverting the Fisher Information Matrix…

The Dijkstra algorithm is a classic path planning method, which operates in a discrete graph space to determine the shortest path from a specified source point to a target node or all other nodes based on non-negative edge weights. Numerous…

Robotics · Computer Science 2025-06-30 Yu Zhang , Xiao-Song Yang

Optimization algorithms that leverage gradient covariance information, such as variants of natural gradient descent (Amari, 1998), offer the prospect of yielding more effective descent directions. For models with many parameters, the…

Machine Learning · Computer Science 2021-07-27 Thomas George , César Laurent , Xavier Bouthillier , Nicolas Ballas , Pascal Vincent

The energy preserving discrete gradient methods are generalized to finite-dimensional Riemannian manifolds by definition of a discrete approximation to the Riemannian gradient, a retraction, and a coordinate center function. The resulting…

Numerical Analysis · Mathematics 2018-05-22 Elena Celledoni , Sølve Eidnes , Brynjulf Owren , Torbjørn Ringholm

This paper investigates the problems large-scale distributed composite convex optimization, with motivations from a broad range of applications, including multi-agent systems, federated learning, smart grids, wireless sensor networks,…

Optimization and Control · Mathematics 2025-12-16 Maoran Wang , Xingju Cai , Yongxin Chen

Optimization with orthogonality constraints frequently arises in various fields such as machine learning. Riemannian optimization offers a powerful framework for solving these problems by equipping the constraint set with a Riemannian…

Optimization and Control · Mathematics 2025-05-20 Andi Han , Pierre-Louis Poirion , Akiko Takeda

We study decentralized online Riemannian optimization over manifolds with possibly positive curvature, going beyond the Hadamard manifold setting. Decentralized optimization techniques rely on a consensus step that is well understood in…

Optimization and Control · Mathematics 2025-09-10 Emre Sahinoglu , Shahin Shahrampour

Regularization is a widely recognized technique in mathematical optimization. It can be used to smooth out objective functions, refine the feasible solution set, or prevent overfitting in machine learning models. Due to its simplicity and…

Optimization and Control · Mathematics 2024-12-31 Filip Nikolovski , Irena Stojkovska , Katerina Hadzi-Velkova Saneva , Zoran Hadzi-Velkov

We present a first-order method for solving constrained optimization problems. The method is derived from our previous work, a modified search direction method inspired by singular value decomposition. In this work, we simplify its…

Optimization and Control · Mathematics 2023-02-24 Long Chen , Kai-Uwe Bletzinger , Nicolas R. Gauger , Yinyu Ye

The Wasserstein distance has become increasingly important in machine learning and deep learning. Despite its popularity, the Wasserstein distance is hard to approximate because of the curse of dimensionality. A recently proposed approach…

Machine Learning · Computer Science 2021-09-29 Minhui Huang , Shiqian Ma , Lifeng Lai

We present Re-weighted Gradient Descent (RGD), a novel optimization technique that improves the performance of deep neural networks through dynamic sample re-weighting. Leveraging insights from distributionally robust optimization (DRO)…

Machine Learning · Computer Science 2024-10-15 Ramnath Kumar , Kushal Majmundar , Dheeraj Nagaraj , Arun Sai Suggala

This paper presents a randomized algorithm for computing the near-optimal low-rank dynamic mode decomposition (DMD). Randomized algorithms are emerging techniques to compute low-rank matrix approximations at a fraction of the cost of…

Numerical Analysis · Mathematics 2019-11-28 N. Benjamin Erichson , Lionel Mathelin , Steven L. Brunton , J. Nathan Kutz