1 citations · 1 across the 10 of their papers we have counts for
10 papers
Anytime-Feasible Gradient Descent for Constrained Optimization Under Gradient Uncertainty
Sina Sharifi, Jiarui Wang, Mahyar Fazlyab
Constrained optimization is central to many engineering systems in which decisions must satisfy strict safety and operational requirements, especially in real-time settings with li…
Generalized Model Predictive Path Integral Control as Expectation--Maximization
Jiarui Wang, Sina Sharifi, Mahyar Fazlyab
Model Predictive Path Integral (MPPI) control is a powerful sampling-based method for solving stochastic optimal control problems and has enabled real-time control in complex robot…
Model Predictive Path Integral Control as Preconditioned Gradient Descent
Mahyar Fazlyab, Sina Sharifi, Jiarui Wang
Model Predictive Path Integral (MPPI) control is a widely used sampling-based method for trajectory optimization, yet its convergence properties remain only partially understood. T…
Sequential QCQP for Bilevel Optimization with Line Search
Sina Sharifi, Erfan Yazdandoost Hamedani, Mahyar Fazlyab
Bilevel optimization involves a hierarchical structure where one problem is nested within another, leading to complex interdependencies between levels. We propose a single-loop, tu…
Perturbed Gradient Descent via Convex Quadratic Approximation for Nonconvex Bilevel Optimization
Nazanin Abolfazli, Sina Sharifi, Mahyar Fazlyab +1
Bilevel optimization is a fundamental tool in hierarchical decision-making and has been widely applied to machine learning tasks such as hyperparameter tuning, meta-learning, and c…
Safe Gradient Flow for Bilevel Optimization
Sina Sharifi, Nazanin Abolfazli, Erfan Yazdandoost Hamedani +1
Bilevel optimization is a key framework in hierarchical decision-making, where one problem is embedded within the constraints of another. In this work, we propose a control-theoret…
Compositional Curvature Bounds for Deep Neural Networks
Taha Entesari, Sina Sharifi, Mahyar Fazlyab
A key challenge that threatens the widespread use of neural networks in safety-critical applications is their vulnerability to adversarial attacks. In this paper, we study the seco…
Provable Bounds on the Hessian of Neural Networks: Derivative-Preserving Reachability Analysis
Sina Sharifi, Mahyar Fazlyab
We propose a novel reachability analysis method tailored for neural networks with smooth activations. Our method relies on constructing an end-to-end first-order Taylor expansion o…
Gradient-Regularized Out-of-Distribution Detection
Sina Sharifi, Taha Entesari, Bardia Safaei +2
One of the challenges for neural networks in real-life applications is the overconfident errors these models make when the data is not from the original training distribution. Addr…
ReachLipBnB: A branch-and-bound method for reachability analysis of neural autonomous systems using Lipschitz bounds
Taha Entesari, Sina Sharifi, Mahyar Fazlyab
We propose a novel Branch-and-Bound method for reachability analysis of neural networks in both open-loop and closed-loop settings. Our idea is to first compute accurate bounds on…