How to beat a Bayesian adversary

DOI10.1017/S0956792525000105MaRDI QIDQ6877260zbMATH OpenFDO

Authors Zihan Ding, Kexin Jin, Jonas Latz, Chenguang Liu

Publication date 8 January 2026

Published in European Journal of Applied Mathematics (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1017/S0956792525000105

zbMATH Keywords

machine learningstochastic differential equationsparticle systemadversarial robustnessMcKean-Vlasov process

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Stochastic programming (90C15) Stochastic particle methods (65C35)

Cites work

• scientific article; zbMATH DE number 7335009 (Why is no real title available?)
• A CLASS OF MARKOV PROCESSES ASSOCIATED WITH NONLINEAR PARABOLIC EQUATIONS
• A Stochastic Approximation Method
• An introduction to stochastic differential equations with reflection
• Analysis of stochastic gradient descent in continuous time
• Convergence error analysis of reflected gradient Langevin dynamics for non-convex constrained optimization
• Exponential ergodicity for singular reflecting McKean-Vlasov SDEs
• Interacting particle Langevin algorithm for maximum marginal likelihood estimation
• Laplace's method revisited: Weak convergence of probability measures
• Large deviations and exit-times for reflected McKean-Vlasov equations with self-stabilising terms and superlinear drifts
• Numerical Optimization
• On approximation of solutions of multidimensional SDE's with reflecting boundary conditions
• On the rate of convergence in Wasserstein distance of the empirical measure
• Optimal Transport
• Subsampling in ensemble Kalman inversion

This page was built for publication: How to beat a Bayesian adversary

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6877260)