Optimal Control Theoretic Neural Optimizer: From Backpropagation to Dynamic Programming

• URL: http://arxiv.org/abs/2510.14168v1
• Date: Wed, 15 Oct 2025 23:39:51 GMT
• Title: Optimal Control Theoretic Neural Optimizer: From Backpropagation to Dynamic Programming
• Authors: Guan-Horng Liu, Tianrong Chen, Evangelos A. Theodorou,
• Abstract summary: This paper focuses on an algorithmic perspective on optimization of deep neural networks (DNNs)<n>Our motivated observation is the striking algorithmic resemblance between the Backpropagation algorithm for computing gradients in DNNs and the optimality conditions for dynamical systems.<n>The resulting physics, termed Optimal Control The Neural-theoretic (OCNOpt) enables rich algorithmic opportunities.
• Score: 29.911180907218053
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Optimization of deep neural networks (DNNs) has been a driving force in the advancement of modern machine learning and artificial intelligence. With DNNs characterized by a prolonged sequence of nonlinear propagation, determining their optimal parameters given an objective naturally fits within the framework of Optimal Control Programming. Such an interpretation of DNNs as dynamical systems has proven crucial in offering a theoretical foundation for principled analysis from numerical equations to physics. In parallel to these theoretical pursuits, this paper focuses on an algorithmic perspective. Our motivated observation is the striking algorithmic resemblance between the Backpropagation algorithm for computing gradients in DNNs and the optimality conditions for dynamical systems, expressed through another backward process known as dynamic programming. Consolidating this connection, where Backpropagation admits a variational structure, solving an approximate dynamic programming up to the first-order expansion leads to a new class of optimization methods exploring higher-order expansions of the Bellman equation. The resulting optimizer, termed Optimal Control Theoretic Neural Optimizer (OCNOpt), enables rich algorithmic opportunities, including layer-wise feedback policies, game-theoretic applications, and higher-order training of continuous-time models such as Neural ODEs. Extensive experiments demonstrate that OCNOpt improves upon existing methods in robustness and efficiency while maintaining manageable computational complexity, paving new avenues for principled algorithmic design grounded in dynamical systems and optimal control theory.

Related papers

• Deep Unfolding: Recent Developments, Theory, and Design Guidelines [99.63555420898554]
  This article provides a tutorial-style overview of deep unfolding, a framework that transforms optimization algorithms into structured, trainable ML architectures.<n>We review the foundations of optimization for inference and for learning, introduce four representative design paradigms for deep unfolding, and discuss the distinctive training schemes that arise from their iterative nature.
  arXiv  Detail & Related papers  (2025-12-03T13:16:35Z)
• Understanding Inverse Reinforcement Learning under Overparameterization: Non-Asymptotic Analysis and Global Optimality [52.906438147288256]
  We show that our algorithm can identify the globally optimal reward and policy under certain neural network structures.<n>This is the first IRL algorithm with a non-asymptotic convergence guarantee that provably achieves global optimality.
  arXiv  Detail & Related papers  (2025-03-22T21:16:08Z)
• Training Neural ODEs Using Fully Discretized Simultaneous Optimization [2.290491821371513]
  Training Neural Ordinary Differential Equations (Neural ODEs) requires solving differential equations at each epoch, leading to high computational costs.<n>In particular, we employ a collocation-based, fully discretized formulation and use IPOPT-a solver for large-scale nonlinear optimization.<n>Our results show significant potential for (collocation-based) simultaneous Neural ODE training pipelines.
  arXiv  Detail & Related papers  (2025-02-21T18:10:26Z)
• Super Level Sets and Exponential Decay: A Synergistic Approach to Stable Neural Network Training [0.0]
  We develop a dynamic learning rate algorithm that integrates exponential decay and advanced anti-overfitting strategies. We prove that the superlevel sets of the loss function, as influenced by our adaptive learning rate, are always connected.
  arXiv  Detail & Related papers  (2024-09-25T09:27:17Z)
• Efficient and Flexible Neural Network Training through Layer-wise Feedback Propagation [49.44309457870649]
  Layer-wise Feedback feedback (LFP) is a novel training principle for neural network-like predictors.<n>LFP decomposes a reward to individual neurons based on their respective contributions.<n>Our method then implements a greedy reinforcing approach helpful parts of the network and weakening harmful ones.
  arXiv  Detail & Related papers  (2023-08-23T10:48:28Z)
• Neural Combinatorial Optimization: a New Player in the Field [69.23334811890919]
  This paper presents a critical analysis on the incorporation of algorithms based on neural networks into the classical optimization framework. A comprehensive study is carried out to analyse the fundamental aspects of such algorithms, including performance, transferability, computational cost and to larger-sized instances.
  arXiv  Detail & Related papers  (2022-05-03T07:54:56Z)
• Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms [71.62575565990502]
  We prove that the generalization error of an optimization algorithm can be bounded on the complexity' of the fractal structure that underlies its generalization measure. We further specialize our results to specific problems (e.g., linear/logistic regression, one hidden/layered neural networks) and algorithms.
  arXiv  Detail & Related papers  (2021-06-09T08:05:36Z)
• Iterative Surrogate Model Optimization (ISMO): An active learning algorithm for PDE constrained optimization with deep neural networks [14.380314061763508]
  We present a novel active learning algorithm, termed as iterative surrogate model optimization (ISMO) This algorithm is based on deep neural networks and its key feature is the iterative selection of training data through a feedback loop between deep neural networks and any underlying standard optimization algorithm.
  arXiv  Detail & Related papers  (2020-08-13T07:31:07Z)
• A Differential Game Theoretic Neural Optimizer for Training Residual Networks [29.82841891919951]
  We propose a generalized Differential Dynamic Programming (DDP) neural architecture that accepts both residual connections and convolution layers. The resulting optimal control representation admits a gameoretic perspective, in which training residual networks can be interpreted as cooperative trajectory optimization on state-augmented systems.
  arXiv  Detail & Related papers  (2020-07-17T10:19:17Z)
• Iterative Algorithm Induced Deep-Unfolding Neural Networks: Precoding Design for Multiuser MIMO Systems [59.804810122136345]
  We propose a framework for deep-unfolding, where a general form of iterative algorithm induced deep-unfolding neural network (IAIDNN) is developed. An efficient IAIDNN based on the structure of the classic weighted minimum mean-square error (WMMSE) iterative algorithm is developed. We show that the proposed IAIDNN efficiently achieves the performance of the iterative WMMSE algorithm with reduced computational complexity.
  arXiv  Detail & Related papers  (2020-06-15T02:57:57Z)
• Dynamic Hierarchical Mimicking Towards Consistent Optimization Objectives [73.15276998621582]
  We propose a generic feature learning mechanism to advance CNN training with enhanced generalization ability. Partially inspired by DSN, we fork delicately designed side branches from the intermediate layers of a given neural network. Experiments on both category and instance recognition tasks demonstrate the substantial improvements of our proposed method.
  arXiv  Detail & Related papers  (2020-03-24T09:56:13Z)
• DDPNOpt: Differential Dynamic Programming Neural Optimizer [29.82841891919951]
  We show that most widely-used algorithms for trainings can be linked to the Differential Dynamic Programming (DDP) In this vein, we propose a new class of DDPOpt, for training feedforward and convolution networks.
  arXiv  Detail & Related papers  (2020-02-20T15:42:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.