| A distributed second-order algorithm you can trust C Dünner, A Lucchi, M Gargiani, A Bian, T Hofmann, M Jaggi International Conference on Machine Learning, 1358-1366, 2018 | 35 | 2018 |
| On the promise of the stochastic generalized Gauss-Newton method for training DNNs M Gargiani, A Zanelli, M Diehl, F Hutter arXiv preprint arXiv:2006.02409, 2020 | 23 | 2020 |
| Data-driven optimal control with a relaxed linear program A Martinelli, M Gargiani, J Lygeros Automatica 2022, 2020 | 19 | 2020 |
| Data-driven optimal control of affine systems: A linear programming perspective A Martinelli, M Gargiani, M Draskovic, J Lygeros IEEE Control Systems Letters, 2022 | 17 | 2022 |
| PAGE-PG: A Simple and Loopless Variance-Reduced Policy Gradient Method with Probabilistic Gradient Estimation M Gargiani, A Zanelli, A Martinelli, T Summers, J Lygeros ICML 2022, 2022 | 16 | 2022 |
| Probabilistic Rollouts for Learning Curve Extrapolation Across Hyperparameter Settings M Gargiani, A Klein, S Falkner, F Hutter ICML 2018 (Workshop on AutoML), 2019 | 12 | 2019 |
| Hyperparameter optimization A Biedenkapp, K Eggensperger, T Elsken, S Falkner, M Feurer, ... Artificial Intelligence 1, 35, 2018 | 8 | 2018 |
| Dynamic Programming Through the Lens of Semismooth Newton-Type Methods M Gargiani, A Zanelli, D Liao-McPherson, T Summers, J Lygeros IEEE Control Systems Letters 6, 2022 | 7 | 2022 |
| Parallel and Flexible Dynamic Programming Via the Mini-Batch Bellman Operator M Gargiani, A Martinelli, MR Martinez, J Lygeros IEEE Transactions on Automatic Control 69 (1), 455-462, 2023 | 4 | 2023 |
| Policy Iteration for Multiplicative Noise Output Feedback Control B Gravell, M Gargiani, J Lygeros, TH Summers CDC 2022, 2022 | 4 | 2022 |
| Hessian-CoCoA: a general parallel and distributed framework for non-strongly convex regularizers M Gargiani ETH Zurich, 2017 | 4 | 2017 |
| Dynamic Programming Through the Lens of Semismooth Newton-Type Methods (Extended Version) M Gargiani, A Zanelli, D Liao Mc-Pherson, T Summers, J Lygeros https://arxiv.org/abs/2203.08678, 2022 | 3 | 2022 |
| Parallel and Flexible Dynamic Programming via the Randomized Mini-Batch Operator M Gargiani, A Martinelli, M R. Martinez, J Lygeros arXiv preprint arXiv:2110.02901, 2021 | 3 | 2021 |
| On the Synthesis of Bellman Inequalities for Data-Driven Optimal Control A Martinelli, M Gargiani, J Lygeros CDC 2021, 2021 | 3 | 2021 |
| Convergence Analysis of Homotopy-SGD for Non-Convex Optimization M Gargiani, A Zanelli, Q Tran-Dinh, M Diehl, F Hutter arXiv preprint arXiv:2011.10298, 2020 | 3 | 2020 |
| Transferring Optimality Across Data Distributions via Homotopy Methods M Gargiani, A Zanelli, Q Tran-Dinh, M Diehl, F Hutter ICLR 2020, 2020 | 2 | 2020 |
| Inexact GMRES Policy Iteration for Large-Scale Markov Decision Processes M Gargiani, D Liao-McPherson, A Zanelli, J Lygeros | 1 | 2022 |
| madupite: A High-Performance Distributed Solver for Large-Scale Markov Decision Processes M Gargiani, P Pawlowsky, R Sieber, V Hapla, J Lygeros available at https://github.com/madupite/madupite and under review at JOSS, 2024 | | 2024 |
| Inexact Policy Iteration Methods for Large-Scale Markov Decision Processes M Gargiani, R Sieber, E Balta, D Liao-McPherson, J Lygeros https://arxiv.org/abs/2404.06136, 2024 | | 2024 |
| Method, device and computer program for predicting a learning curve M Gargiani, A Klein, F Hutter https://patents.google.com/patent/DE102019207911A1/en, 2023 | | 2023 |
John LygerosProf. of Computation and Control, ETH ZurichVerified email at ethz.ch
