paper-with-me

홈 › Papers

Robust Deep Learning as Optimal Control: Insights and Convergence Guarantees

2020-05-01 · L4DC 2020 6 · Jacob H. Seidman, Mahyar Fazlyab, Victor M. Preciado, George J. Pappas

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 mechanism can be formulated as a min-max optimization problem, where the adversary seeks to maximize the loss function using an iterative first-order algorithm while the learner attempts to minimize it. However, finding adversarial examples in this way causes excessive computational overhead during training. By interpreting the min-max problem as an optimal control problem, it has recently been shown that one can exploit the compositional structure of neural networks in the optimization problem to improve the training time significantly. In this paper, we provide the first convergence analysis of this adversarial training algorithm by combining techniques from robust optimal control and inexact oracle methods in optimization. Our analysis sheds light on how the hyperparameters of the algorithm affect the its stability and convergence. We support our insights with experiments on a robust classification problem.

📄 PDF Abstract BibTeX arXiv:2005.00616

Code (0)

등록된 구현이 없습니다.

Tasks

Deep LearningRobust classification

Similar Papers 제목 키워드 기반

Reinforcement Learning for Reachability: Guaranteeing Asymptotic Optimality

2026-05-23 · Amogh Palasamudram, Jakub Svoboda, Suguman Bansal, Krishnendu Chatterjee arxiv

Reinforcement learning (RL) for reachability specifications is fundamental in sequential decision-making, yet theoretical guarantees remain less explored. A recent work achieves asymptotic convergence to optimal policies…

Reinforcement Learning

Convergence Guarantees of Policy Optimization Methods for Markovian Jump Linear Systems

2020-02-10 · Joao Paulo Jansch-Porto, Bin Hu, Geir Dullerud

Recently, policy optimization for control purposes has received renewed attention due to the increasing interest in reinforcement learning. In this paper, we investigate the convergence of policy optimization for quadrat…

Reinforcement Learning

On the Convergence of Jacobian-Free Backpropagation for Optimal Control Problems with Implicit Hamiltonians

2026-01-31 · Eric Gelphman, Deepanshu Verma, Nicole Tianjiao Yang, Stanley Osher 외 arxiv

Optimal feedback control with implicit Hamiltonians poses a fundamental challenge for learning-based value function methods due to the absence of closed-form optimal control laws. Recent work~\cite{gelphman2025end} intro…

Optimally Managing the Impacts of Convergence Tolerance for Distributed Optimal Power Flow

2023-11-14 · Rachel Harris, Mohannad Alkhraijah, Daniel K. Molzahn

The future power grid may rely on distributed optimization to determine the set-points for huge numbers of distributed energy resources. There has been significant work on applying distributed algorithms to optimal power…

Distributed Optimization

Accelerated Learning with Robustness to Adversarial Regressors

2020-05-04 · Joseph E. Gaudio, Anuradha M. Annaswamy, José M. Moreu, Michael A. Bolender 외

High order momentum-based parameter update algorithms have seen widespread applications in training machine learning models. Recently, connections with variational approaches have led to the derivation of new learning al…