Παρακολούθηση
Mahyar Fazlyab
Mahyar Fazlyab
Assistant Professor, Johns Hopkins University
Η διεύθυνση ηλεκτρονικού ταχυδρομείου έχει επαληθευτεί στον τομέα jhu.edu - Αρχική σελίδα
Τίτλος
Παρατίθεται από
Παρατίθεται από
Έτος
Efficient and accurate estimation of lipschitz constants for deep neural networks
M Fazlyab, A Robey, H Hassani, M Morari, G Pappas
Advances in neural information processing systems 32, 2019
4162019
Safety verification and robustness analysis of neural networks via quadratic constraints and semidefinite programming
M Fazlyab, M Morari, GJ Pappas
IEEE Transactions on Automatic Control 67 (1), 1-15, 2022
2302022
Prediction-correction interior-point method for time-varying convex optimization
M Fazlyab, S Paternain, VM Preciado, A Ribeiro
IEEE Transactions on Automatic Control 63 (7), 1973-1986, 2017
1422017
Analysis of optimization algorithms via integral quadratic constraints: Nonstrongly convex problems
M Fazlyab, A Ribeiro, M Morari, VM Preciado
SIAM Journal on Optimization 28 (3), 2654-2689, 2018
1172018
Reach-sdp: Reachability analysis of closed-loop systems with neural network controllers via semidefinite programming
H Hu, M Fazlyab, M Morari, GJ Pappas
2020 59th IEEE conference on decision and control (CDC), 5929-5934, 2020
852020
Enforcing robust control guarantees within neural network policies
PL Donti, M Roderick, M Fazlyab, JZ Kolter
International Conference on Learning Representations, 2020
652020
Learning lyapunov functions for hybrid systems
S Chen, M Fazlyab, M Morari, GJ Pappas, VM Preciado
Proceedings of the 24th International Conference on Hybrid Systems …, 2021
632021
Parameter estimation and interval type-2 fuzzy sliding mode control of a z-axis MEMS gyroscope
M Fazlyab, MZ Pedram, H Salarieh, A Alasty
ISA transactions 52 (6), 900-911, 2013
462013
Probabilistic verification and reachability analysis of neural networks via semidefinite programming
M Fazlyab, M Morari, GJ Pappas
2019 IEEE 58th Conference on Decision and Control (CDC), 2726-2731, 2019
452019
Effect of dexamethasone intraligamentary injection on post-endodontic pain in patients with symptomatic irreversible pulpitis: a randomized controlled clinical trial
P Mehrvarzfar, E Esnashari, R Salmanzadeh, M Fazlyab, M Fazlyab
Iranian endodontic journal 11 (4), 261, 2016
422016
Optimal network design for synchronization of coupled oscillators
M Fazlyab, F Dörfler, VM Preciado
Automatica 84, 181-189, 2017
39*2017
Interior point method for dynamic constrained optimization in continuous time
M Fazlyab, S Paternain, VM Preciado, A Ribeiro
2016 American Control Conference (ACC), 5612-5618, 2016
332016
Self-triggered time-varying convex optimization
M Fazlyab, C Nowzari, GJ Pappas, A Ribeiro, VM Preciado
2016 IEEE 55th Conference on Decision and Control (CDC), 3090-3097, 2016
322016
Learning region of attraction for nonlinear systems
S Chen, M Fazlyab, M Morari, GJ Pappas, VM Preciado
2021 60th IEEE Conference on Decision and Control (CDC), 6477-6484, 2021
302021
A variational approach to dual methods for constrained convex optimization
M Fazlyab, A Koppel, VM Preciado, A Ribeiro
2017 American Control Conference (ACC), 5269-5275, 2017
232017
Learning lyapunov functions for piecewise affine systems with neural network controllers
S Chen, M Fazlyab, M Morari, GJ Pappas, VM Preciado
arXiv preprint arXiv:2008.06546, 2020
202020
Certifying incremental quadratic constraints for neural networks via convex optimization
N Hashemi, J Ruths, M Fazlyab
Learning for Dynamics and Control, 842-853, 2021
172021
Robust deep learning as optimal control: Insights and convergence guarantees
JH Seidman, M Fazlyab, VM Preciado, GJ Pappas
Learning for Dynamics and Control, 884-893, 2020
172020
Design of First-Order Optimization Algorithms via Sum-of-Squares Programming
M Fazlyab, M Morari, VM Preciado
2018 IEEE Conference on Decision and Control (CDC), 4445-4452, 2018
152018
Deepsplit: Scalable verification of deep neural networks via operator splitting
S Chen, E Wong, JZ Kolter, M Fazlyab
IEEE Open Journal of Control Systems 1, 126-140, 2022
142022
Δεν είναι δυνατή η εκτέλεση της ενέργειας από το σύστημα αυτή τη στιγμή. Προσπαθήστε ξανά αργότερα.
Άρθρα 1–20