セメリスアンドレアス

Themelis Andreas

所属機関・部署：
競争的資金等の研究課題 (2件)：

2021 - 2023 The project is concerned with optimization algorithms for engineering, in compliance with the application challenges: efficiency, limited power of microprocessors, and nonconvexity of the problems. The final goal is to provide efficient open-source multi-purpose software with theoretical guarantees.
2021 - 2021 The main objective of the project is to develop learning-based techniques for devising ad-hoc tuning-free optimization algorithms for convex and nonconvex optimization problems. A novel universal framework will be developed, which will serve as a solid theoretical ground for the development of new learning paradigms to train optimization methods subject to certificates of (speed of) conver-gence and quality of output solution.

論文 (6件)：

Alberto De Marchi, Andreas Themelis. Proximal Gradient Algorithms under Local Lipschitz Gradient Continuity: A Convergence and Robustness Analysis of PANOC. Journal of Optimization Theory and Applications. 2022. 194. 771-794
Hongjia Ou, Andreas Themelis, Tsuyoshi Yuno, Taketoshi Kawabe. Douglas-Peucker piecewise affine approximation of an optimal fuel consumption problem to apply PANOC. 2022 SICE International Symposium on Control Systems (SICE ISCS). 2022. 34-38
Brecht Evens, Puya Latafat, Andreas Themelis, Johan Suykens, Panagiotis Patrinos. Neural network training as an optimal control problem: An augmented Lagrangian approach. 2021 60th IEEE Conference on Decision and Control (CDC). 2022. 5136-5143
Miguel Simoes, Andreas Themelis, Panagiotis Patrinos. Lasry-Lions Envelopes and Nonconvex Optimization: A Homotopy Approach. 2021 29th European Signal Processing Conference (EUSIPCO). 2021. 2089-2093
Pantelis Sopasakis, Andreas Themelis, Johan Suykens, Panagiotis Patrinos. A primal-dual line search method and applications in image processing. 2017 25th European Signal Processing Conference (EUSIPCO). 2017. 1065-1069

MISC (15件)：

Ben Hermans, Andreas Themelis, Panagiotis Patrinos. QPALM: A Proximal Augmented Lagrangian Method for Nonconvex Quadratic Programs. 2020
Andreas Themelis, Lorenzo Stella, Panagiotis Patrinos. Douglas-Rachford splitting and ADMM for nonconvex optimization: Accelerated and Newton-type algorithms. 2020
Andreas Themelis, Ben Hermans, Panagiotis Patrinos. A new envelope function for nonsmooth DC optimization. 2020
Nico Vervliet, Andreas Themelis, Panagiotis Patrinos, Lieven De Lathauwer. A quadratically convergent proximal algorithm for nonnegative tensor decomposition. 2020
Ben Hermans, Andreas Themelis, Panagiotis Patrinos. QPALM: A Newton-type Proximal Augmented Lagrangian Method for Quadratic Programs. 2019

講演・口頭発表等 (9件)：

A universal majorization-minimization framework for the convergence analysis of nonconvex proximal algorithms
(6th International Conference on Continuous Optimization 2019)
Proximal envelopes
(17th IEEE European Control Conference 2018)
A simple and efficient algorithm for Nonlinear MPC
(56th IEEE Conference on Decision and Control 2017)
Accelerated Douglas-Rachford splitting and ADMM for structured nonconvex optimization
(CMO-BIRS Workshop on Splitting Algorithms, Modern Operator Theory and Applications 2017)
Newton-type proximal algorithms for nonconvex optimization
(LCCC focus period on large scale and distributed optimization 2017)

※　J-GLOBALの研究者情報は、researchmapの登録情報に基づき表示しています。登録・更新については、こちらをご覧ください。

セメリス アンドレアス