English
Related papers

Related papers: Practical and Fast Momentum-Based Power Methods

200 papers

We introduce EfficientTDMPC, a sample-efficient model-based reinforcement learning method for continuous control built on the TD-MPC family of algorithms. Central to this family is a planner that aims to find an action sequence that…

Machine Learning · Computer Science 2026-05-20 Thomas Evers , Cristian Meo , Wendelin Bohmer , Justin Dauwels , Yaniv Oren

This paper proposes a novel method for solving and tracing power flow solutions with changes of a loading parameter. Different from the conventional continuation power flow method, which repeatedly solves static AC power flow equations, the…

Dynamical Systems · Mathematics 2022-03-10 Yang Liu , Kai Sun , Jiaojiao Dong

Power packets are proposed as a transmission unit that can deliver power and information simultaneously. They are transferred using the store-and-forward method of power routers. A system that achieves power supply/demand in this manner is…

Systems and Control · Electrical Eng. & Systems 2020-11-03 Seongcheol Baek , Hiroyasu Ando , Takashi Hikihara

We present a dynamic algorithm for maintaining $(1+\epsilon)$-approximate maximum eigenvector and eigenvalue of a positive semi-definite matrix $A$ undergoing \emph{decreasing} updates, i.e., updates which may only decrease eigenvalues.…

Data Structures and Algorithms · Computer Science 2025-01-07 Deeksha Adil , Thatchaphol Saranurak

This paper proposes a gradient descent based optimization method that relies on automatic differentiation for the computation of gradients. The method uses tools and techniques originally developed in the field of artificial neural networks…

Systems and Control · Electrical Eng. & Systems 2023-09-29 Georg Kordowich , Johann Jaeger

In this paper, we introduce an accelerated distributed stochastic gradient method with momentum for solving the distributed optimization problem, where a group of $n$ agents collaboratively minimize the average of the local objective…

Optimization and Control · Mathematics 2025-03-27 Kun Huang , Shi Pu , Angelia Nedić

Within the current sphere of deep learning research, despite the extensive application of optimization algorithms such as Stochastic Gradient Descent (SGD) and Adaptive Moment Estimation (Adam), there remains a pronounced inadequacy in…

Machine Learning · Computer Science 2025-10-30 Zhifeng Wang , Longlong Li , Chunyan Zeng

We present a unified method, based on convex optimization, for managing the power produced and consumed by a network of devices over time. We start with the simple setting of optimizing power flows in a static network, and then proceed to…

Optimization and Control · Mathematics 2019-03-18 Nicholas Moehle , Enzo Busseti , Stephen Boyd , Matt Wytock

A key motivation in the development of Distributed Model Predictive Control (DMPC) is to accelerate centralized Model Predictive Control (MPC) for large-scale systems. DMPC has the prospect of scaling well by parallelizing computations…

Optimization and Control · Mathematics 2025-04-16 Gösta Stomberg , Maurice Raetsch , Alexander Engelmann , Timm Faulwasser

A streaming algorithm to compute the spectral proper orthogonal decomposition (SPOD) of stationary random processes is presented. As new data becomes available, an incremental update of the truncated eigenbasis of the estimated…

Fluid Dynamics · Physics 2019-01-14 Oliver T. Schmidt , Aaron Towne

The development of machine learning is promoting the search for fast and stable minimization algorithms. To this end, we suggest a change in the current gradient descent methods that should speed up the motion in flat regions and slow it…

Machine Learning · Computer Science 2019-06-13 Marco Baiesi

In this paper, we introduce an actor-critic algorithm called Deep Value Model Predictive Control (DMPC), which combines model-based trajectory optimization with value function estimation. The DMPC actor is a Model Predictive Control (MPC)…

Machine Learning · Computer Science 2019-10-09 Farbod Farshidian , David Hoeller , Marco Hutter

Emerging distributed applications recently boosted the development of decentralized machine learning, especially in IoT and edge computing fields. In real-world scenarios, the common problems of non-convexity and data heterogeneity result…

Machine Learning · Computer Science 2023-03-02 Haizhou Du , Chengdong Ni

Momentum methods are now used pervasively within the machine learning community for training non-convex models such as deep neural networks. Empirically, they out perform traditional stochastic gradient descent (SGD) approaches. In this…

Machine Learning · Computer Science 2021-06-02 Aaron Defazio

In this work, we study how to implement a distributed algorithm for the power method in a parallel manner. As the existing distributed power method is usually sequentially updating the eigenvectors, it exhibits two obvious disadvantages: 1)…

Information Theory · Computer Science 2021-08-16 Jiaying Li , Sissi Xiaoxiao Wu , Qiang Li , Anna Scaglione

While time series momentum is a well-studied phenomenon in finance, common strategies require the explicit definition of both a trend estimator and a position sizing rule. In this paper, we introduce Deep Momentum Networks -- a hybrid…

Machine Learning · Statistics 2020-09-29 Bryan Lim , Stefan Zohren , Stephen Roberts

We present a stochastic variance-reduced heavy ball power iteration algorithm for solving PCA and provide a convergence analysis for it. The algorithm is an extension of heavy ball power iteration, incorporating a step size so that progress…

Optimization and Control · Mathematics 2019-01-25 Cheolmin Kim , Diego Klabjan

The continuous dynamical system approach to deep learning is explored in order to devise alternative frameworks for training algorithms. Training is recast as a control problem and this allows us to formulate necessary optimality conditions…

Machine Learning · Computer Science 2018-06-05 Qianxiao Li , Long Chen , Cheng Tai , Weinan E

Multimodal learning has attracted increasing attention due to its practicality. However, it often suffers from insufficient optimization, where the multimodal model underperforms even compared to its unimodal counterparts. Existing methods…

Computer Vision and Pattern Recognition · Computer Science 2026-04-08 Shicai Wei , Chunbo Luo , Qiang Zhu , Yang Luo

Instrumental variable analysis is a powerful tool for estimating causal effects when randomization or full control of confounders is not possible. The application of standard methods such as 2SLS, GMM, and more recent variants are…

Machine Learning · Statistics 2020-06-08 Andrew Bennett , Nathan Kallus , Tobias Schnabel