A Systems-Theoretic View on the Convergence of Algorithms under Disturbances
Not on the map. Why?
Abstract (arXiv)
Algorithms increasingly operate within complex physical, social, and engineering systems where they are exposed to disturbances, noise, and interconnections with other dynamical systems. This article extends known convergence guarantees of an algorithm operating in isolation (i.e., without disturbances) and systematically derives stability bounds and convergence rates in the presence of such disturbances. By leveraging converse Lyapunov theorems, we derive key inequalities that quantify the impact of disturbances. We further demonstrate how our result can be utilized to assess the effects of disturbances on algorithmic performance in a wide variety of applications, including communication constraints in distributed learning, sensitivity in machine learning generalization, and intentional noise injection for privacy. This underpins the role of our result as a unifying tool for algorithm analysis in the presence of noise, disturbances, and interconnections with other dynamical systems.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 30 of its 56 references that are in the map. First posted on arXiv 19 Dec 2025.
Builds on
30 of 56 references.
References · 30
- 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
- 2015Train faster, generalize better: Stability of stochastic gradient descentcited by 552
- 2018Sparsified SGD with Memorycited by 376
- 2019FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantizationcited by 356
- 2020Performative Predictioncited by 327
- 2019Rapid Convergence of the Unadjusted Langevin Algorithm: Isoperimetry Sufficescited by 227
- 2019Differentially Private Learning with Adaptive Clippingcited by 220
- 2015A Differential Equation for Modeling Nesterov's Accelerated Gradient Method: Theory and Insightscited by 206
- 2019Private Stochastic Convex Optimization with Optimal Ratescited by 186
- 2022An optimal control perspective on diffusion-based generative modelingcited by 147
- 2018Sampling as optimization in the space of measures: The Langevin dynamics as a composite optimization problemcited by 123
- 2016A Variational Perspective on Accelerated Methods in Optimizationcited by 110
18 more
- 2014Differentially Private Empirical Risk Minimization: Efficient Algorithms and Tight Error Boundscited by 107
- 2014Analysis and Design of Optimization Algorithms via Integral Quadratic Constraintscited by 105
- 2022Privacy of Noisy Stochastic Gradient Descent: More Iterations without More Privacy Losscited by 61
- 2019A Dynamical Systems Perspective on Nesterov Accelerationcited by 33
- 2024Provable Benefit of Annealed Langevin Monte Carlo for Non-log-concave Samplingcited by 23
- 2015A General Analysis of the Convergence of ADMMcited by 22
- 2018Beyond Convexity -- Contraction and Global Convergence of Gradient Descentcited by 17
- 2023Orthogonal Directions Constrained Gradient Method: from non-linear equality constraints to Stiefel manifoldcited by 14
- 2021On Constraints in First-Order Optimization: A View from Non-Smooth Dynamical Systemscited by 13
- 2019Event-triggered Learningcited by 9
- 2020Continuous-time Lower Bounds for Gradient-based Algorithmscited by 7
- 2024Towards a Systems Theory of Algorithmscited by 7
- 2025Decision-Dependent Stochastic Optimization: The Role of Distribution Dynamicscited by 6
- 2023Accelerated First-Order Optimization under Nonlinear Constraintscited by 5
- 2023A Dynamical Systems Perspective on Discrete Optimizationcited by 3
- 2024Primal Methods for Variational Inequality Problems with Functional Constraintscited by 3
- 2024Distributed Event-Based Learning via ADMMcited by 3
- 2024Controlling Participation in Federated Learning with Feedbackcited by 1
Built on by
Not cited yet.