English
Related papers

Related papers: Maximum Principle Based Algorithms for Deep Learni…

200 papers

We establish a variety of results extending the well-known Pontryagin maximum principle of optimal control to discrete-time optimal control problems posed on smooth manifolds. These results are organized around a new theorem on critical and…

Optimization and Control · Mathematics 2017-07-14 Robert Kipka , Rohit Gupta

Based on Pontryagin Maximum Principle (PMP), this paper established a generalized PMP aiming at non-feedback control system with stochastic initial conditions. We proved the conclusion and show its coming back to PMP when the randomness…

Optimization and Control · Mathematics 2015-05-05 Yuanzun Zhao

We build on the dynamical systems approach to deep learning, where deep residual networks are idealized as continuous-time dynamical systems, from the approximation perspective. In particular, we establish general sufficient conditions for…

Machine Learning · Computer Science 2020-06-09 Qianxiao Li , Ting Lin , Zuowei Shen

Given a sequential learning algorithm and a target model, sequential machine teaching aims to find the shortest training sequence to drive the learning algorithm to the target model. We present the first principled way to find such shortest…

Machine Learning · Computer Science 2018-10-17 Laurent Lessard , Xuezhou Zhang , Xiaojin Zhu

Model predictive control offers a powerful framework for managing constrained systems, but its repeated online optimization can become computationally prohibitive. Multiparametric programming addresses this challenge by precomputing optimal…

Optimization and Control · Mathematics 2026-03-19 Lida Lamakani , Efstratios N. Pistikopoulos

Reinforcement learning has traditionally focused on learning state-dependent policies to solve optimal control problems in a closed-loop fashion. In this work, we introduce the paradigm of open-loop reinforcement learning where a fixed…

Machine Learning · Computer Science 2025-04-23 Onno Eberhard , Claire Vernade , Michael Muehlebach

In this paper, we consider reinforcement learning of Markov Decision Processes (MDP) with peak constraints, where an agent chooses a policy to optimize an objective and at the same time satisfy additional constraints. The agent has to take…

Optimization and Control · Mathematics 2019-12-09 Ather Gattami

Recent years have seen considerable progress in the continual training of deep neural networks, predominantly thanks to approaches that add replay or regularization terms to the loss function to approximate the joint loss over all tasks so…

Machine Learning · Computer Science 2024-11-01 Timm Hess , Tinne Tuytelaars , Gido M. van de Ven

We consider the utility maximization problem under convex constraints with regard to theoretical results which allow the formulation of algorithmic solvers which make use of deep learning techniques. In particular for the case of random…

Computational Finance · Quantitative Finance 2022-02-17 Kristof Wiedermann

Stochastic control problems in high dimensions are notoriously difficult to solve due to the curse of dimensionality. An alternative to traditional dynamic programming is Pontryagin's Maximum Principle (PMP), which recasts the problem as a…

Machine Learning · Computer Science 2025-07-03 Qian Qi

Features in machine learning problems are often time-varying and may be related to outputs in an algebraic or dynamical manner. The dynamic nature of these machine learning problems renders current higher order accelerated gradient descent…

Optimization and Control · Mathematics 2019-05-29 Joseph E. Gaudio , Travis E. Gibson , Anuradha M. Annaswamy , Michael A. Bolender

State-space models (SSMs) are effective architectures for sequential modeling, but a rigorous theoretical understanding of their training dynamics is still lacking. In this work, we formulate the training of SSMs as an ensemble optimal…

Optimization and Control · Mathematics 2026-03-17 Ye Feng , Jianfeng Lu

Recent progress in deep learning has been driven by increasingly larger models. However, their computational and energy demands have grown proportionally, creating significant barriers to their deployment and to a wider adoption of deep…

Machine Learning · Computer Science 2025-09-16 Pedro Savarese

The fragility of deep neural networks to adversarially-chosen inputs has motivated the need to revisit deep learning algorithms. Including adversarial examples during training is a popular defense mechanism against adversarial attacks. This…

Optimization and Control · Mathematics 2020-05-05 Jacob H. Seidman , Mahyar Fazlyab , Victor M. Preciado , George J. Pappas

We derive first-order Pontryagin optimality conditions for stochastic optimal control with deterministic controls for systems modeled by rough differential equations (RDE) driven by Gaussian rough paths. This Pontryagin Maximum Principle…

Optimization and Control · Mathematics 2025-10-07 Thomas Lew

Predicting the long-term behavior of chaotic systems remains a formidable challenge due to their extreme sensitivity to initial conditions and the inherent limitations of traditional data-driven modeling approaches. This paper introduces a…

Machine Learning · Computer Science 2024-10-10 Dibyajyoti Chakraborty , Seung Whan Chung , Ashesh Chattopadhyay , Romit Maulik

This paper investigates the relationship between Pontryagin's maximum principle and dynamic programming principle in the context of stochastic optimal control systems governed by stochastic evolution equations with random coefficients in…

Optimization and Control · Mathematics 2025-11-05 Dingqian Gao , Qi Lü

We investigate optimal control problems with $L^0$ constraints, which restrict the measure of the support of the controls. We prove necessary optimality conditions of Pontryagin maximum principle type. Here, a special control perturbation…

Optimization and Control · Mathematics 2022-08-04 Daniel Wachsmuth

We consider a gradient approximation scheme that is based on applying needle shaped inputs. By using ideas known from the classic proof of the Pontryagin Maximum Principle we derive an approximation that reveals that the considered system…

Systems and Control · Computer Science 2016-03-15 Simon Michalowsky , Christian Ebenbauer

This work develops a control-centric framework for a custom 4-DOF rigid-body manipulator by coupling a reduced-order Pontryagin's Maximum Principle (PMP) controller with a physics-informed Gradient Descent stage. The reduced PMP model…

Robotics · Computer Science 2025-12-15 Brock Marcinczyk , Logan E. Beaver