English
Related papers

Related papers: Accelerating Second-Order Differential Dynamic Pro…

200 papers

Differentially private (stochastic) gradient descent is the workhorse of DP private machine learning in both the convex and non-convex settings. Without privacy constraints, second-order methods, like Newton's method, converge faster than…

Machine Learning · Computer Science 2023-05-23 Arun Ganesh , Mahdi Haghifam , Thomas Steinke , Abhradeep Thakurta

This paper studies the robust optimal control design for uncertain nonlinear systems from a perspective of robust adaptive dynamic programming (robust-ADP). The objective is to fill up a gap in the past literature of ADP where dynamic…

Dynamical Systems · Mathematics 2013-03-12 Yu Jiang , Zhong-Ping Jiang

This paper explores the relationship between numerical integrators and optimal control algorithms. Specifically, the performance of the differential dynamical programming (DDP) algorithm is examined when a variational integrator and a newly…

Optimization and Control · Mathematics 2017-09-13 Gerardo De La Torre , Todd Murphey

Even for the gradient descent (GD) method applied to neural network training, understanding its optimization dynamics, including convergence rate, iterate trajectories, function value oscillations, and especially its implicit acceleration,…

Machine Learning · Computer Science 2026-05-22 Alexander Tyurin

Differential Dynamic Programming (DDP) is one of the indirect methods for solving an optimal control problem. Several extensions to DDP have been proposed to add stagewise state and control constraints, which can mainly be classified as…

Optimization and Control · Mathematics 2024-09-19 Siddharth Prabhu , Srinivas Rangarajan , Mayuresh Kothare

The dynamic mode decomposition (DMD) has become a leading tool for data-driven modeling of dynamical systems, providing a regression framework for fitting linear dynamical models to time-series measurement data. We present a simple…

Numerical Analysis · Mathematics 2017-04-11 Travis Askham , J. Nathan Kutz

Soft robots are well suited for contact-rich tasks due to their compliance, yet this property makes accurate and tractable modeling challenging. Planning motions with dynamically-feasible trajectories requires models that capture arbitrary…

Robotics · Computer Science 2026-03-25 Beibei Liu , Akua K. Dickson , Ran Jing , Andrew P. Sabelhaus

This paper reduces the cost of DNNs training by decreasing the amount of data movement across heterogeneous architectures composed of several GPUs and multicore CPU devices. In particular, this paper proposes an algorithm to dynamically…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-04-07 Sicong Zhuang , Cristiano Malossi , Marc Casas

Stochastic dual dynamic programming (SDDP) is a state-of-the-art method for solving multi-stage stochastic optimization, widely used for modeling real-world process optimization tasks. Unfortunately, SDDP has a worst-case complexity that…

Machine Learning · Computer Science 2021-12-03 Hanjun Dai , Yuan Xue , Zia Syed , Dale Schuurmans , Bo Dai

Differentiable programming is revolutionizing computational science by enabling automatic differentiation (AD) of numerical simulations. While first-order gradients are well-established, second-order derivatives (Hessians) for implicit…

Computational Engineering, Finance, and Science · Computer Science 2025-05-20 Tianju Xue

This paper presents a new formulation for model-free robust optimal regulation of continuous-time nonlinear systems. The proposed reinforcement learning based approach, referred to as incremental adaptive dynamic programming (IADP),…

Systems and Control · Electrical Eng. & Systems 2022-03-25 Cong Li , Yongchao Wang , Fangzhou Liu , Qingchen Liu , Martin Buss

Reactive trajectory optimization for robotics presents formidable challenges, demanding the rapid generation of purposeful robot motion in complex and swiftly changing dynamic environments. While much existing research predominantly…

Robotics · Computer Science 2023-10-04 Apan Dastider , Hao Fang , Mingjie Lin

This paper presents a novel framework for Jacobian computation in motion optimization problems involving multi-link systems, where physical quantities are represented using higher-order time derivatives. In motion optimization of robots and…

Robotics · Computer Science 2026-05-18 Taiki Ishigaki , Ko Ayusawa , Eiichi Yoshida

Nonnegative Tucker decomposition (NTD) is a powerful tool for the extraction of nonnegative parts-based and physically meaningful latent components from high-dimensional tensor data while preserving the natural multilinear structure of…

Machine Learning · Computer Science 2015-09-17 Guoxu Zhou , Andrzej Cichocki , Qibin Zhao , Shengli Xie

Several well-known algorithms in the field of combinatorial optimization can be interpreted in terms of the primal-dual method for solving linear programs. For example, Dijkstra's algorithm, the Ford-Fulkerson algorithm, and the Hungarian…

Optimization and Control · Mathematics 2016-01-19 Randy Cogill

We define a regularized variant of the Dual Dynamic Programming algorithm called REDDP (REgularized Dual Dynamic Programming) to solve nonlinear dynamic programming equations. We extend the algorithm to solve nonlinear stochastic dynamic…

Optimization and Control · Mathematics 2020-05-05 Vincent Guigues , Miguel Lejeune , Wajdi Tekaya

This paper proposes a general incremental policy iteration adaptive dynamic programming (ADP) algorithm for model-free robust optimal control of unknown nonlinear systems. The approach integrates recursive least squares estimation with…

Optimization and Control · Mathematics 2025-09-01 Qingkai Meng , Fenglan Wang , Lin Zhao

Many applications -- including power systems, robotics, and economics -- involve a dynamical system interacting with a stochastic and hard-to-model environment. We adopt a reinforcement learning approach to control such systems.…

Optimization and Control · Mathematics 2025-08-26 Abed AlRahman Al Makdah , Oliver Kosut , Lalitha Sankar , Shaofeng Zou

We present a framework for bi-level trajectory optimization in which a system's dynamics are encoded as the solution to a constrained optimization problem and smooth gradients of this lower-level problem are passed to an upper-level…

Autonomous agents are limited in their ability to observe the world state. Partially observable Markov decision processes (POMDPs) formally model the problem of planning under world state uncertainty, but POMDPs with continuous actions and…

Robotics · Computer Science 2020-07-08 Dicong Qiu , Yibiao Zhao , Chris L. Baker