Vassilis Apidopoulos

Vassilis Apidopoulos

Assistant professor

Research

Publications

See also my Google Scholar profile.

[C3] Taming Stochastic Gradient Descent: Almost Sure Convergence and Saddle-Point Avoidance under (L₀,L₁)-Smoothness
V. Apidopoulos, I. Lytras, and P. Mertikopoulos
Proceedings of the 43rd International Conference on Machine Learning (ICML), 2026.
[J7] Preconditioned primal-dual dynamics in convex optimization: non-ergodic convergence rates
V. Apidopoulos, C. Molinari, J. Peypouquet, and S. Villa
Nonlinear Analysis: Hybrid Systems, 60, 101674, 2026.
[P1] Heavy-ball dynamics with Hessian-driven damping for non-convex optimization under the Łojasiewicz condition
V. Apidopoulos, V. Mavrogeorgou, and T. G. Tsironis
arXiv preprint arXiv:2506.11705, 2025.
[J6] Iterative regularization in classification via hinge loss diagonal descent
V. Apidopoulos, T. Poggio, L. Rosasco, and S. Villa
Inverse Problems, 41(3), 035010, 2025.
[J5] Variance reduction techniques for stochastic proximal point algorithms
C. Traoré, V. Apidopoulos, S. Salzo, and S. Villa
Journal of Optimization Theory and Applications, 203(2), 1910–1939, 2024.
[C2] Regularization properties of dual subgradient flow
V. Apidopoulos, C. Molinari, L. Rosasco, and S. Villa
2023 European Control Conference (ECC), pp. 1–8, 2023.
[J4] Convergence rates for the heavy-ball continuous dynamics for non-convex optimization, under Polyak–Łojasiewicz condition
V. Apidopoulos, N. Ginatta, and S. Villa
Journal of Global Optimization, 84(3), 563–589, 2022.
[J3] Convergence rates of an inertial gradient descent algorithm under growth and flatness conditions
V. Apidopoulos, J.-F. Aujol, C. Dossal, and A. Rondepierre
Mathematical Programming, 187(1), 151–193, 2021.
[J2] Convergence rate of inertial Forward–Backward algorithm beyond Nesterov's rule
V. Apidopoulos, J.-F. Aujol, and C. Dossal
Mathematical Programming, 180(1–2), 137–156, 2020.
[D1] Inertial Gradient-Descent algorithms for convex minimization
V. Apidopoulos
PhD thesis, Université de Bordeaux, 2019.
[J1] The Differential Inclusion Modeling FISTA Algorithm and Optimality of Convergence Rate in the Case b ≤ 3
V. Apidopoulos, J.-F. Aujol, and C. Dossal
SIAM Journal on Optimization, 28(1), 551–574, 2018.
[C1] An ODE-based Modeling of Inertial Forward-Backward Algorithms
V. Apidopoulos, J.-F. Aujol, and C. Dossal
Signal Processing with Adaptive Sparse Structured Representations (SPARS), Lisbon, Portugal, 2017.