57 citations · 200 across the 66 of their papers we have counts for
8 papers · 1 filter
Safe Reinforcement Learning with Chance-constrained Model Predictive Control
Samuel Pfrommer, Tanmay Gautam, Alec Zhou +1
Real-world reinforcement learning (RL) problems often demand that agents behave safely by obeying a set of designed constraints. We address the challenge of safe RL by coupling a s…
Factorization Approach for Low-complexity Matrix Completion Problems: Exponential Number of Spurious Solutions and Failure of Gradient Methods
Baturalp Yalcin, Haixiang Zhang, Javad Lavaei +1
It is well-known that the Burer-Monteiro (B-M) factorization approach can efficiently solve low-rank matrix optimization problems under the RIP condition. It is natural to ask whet…
Node-Variant Graph Filters in Graph Neural Networks
Fernando Gama, Brendon G. Anderson, Somayeh Sojoudi
Graph neural networks (GNNs) have been successfully employed in a myriad of applications involving graph signals. Theoretical findings establish that GNNs use nonlinear activation…
Practical Convex Formulation of Robust One-hidden-layer Neural Network Training
Yatong Bai, Tanmay Gautam, Yu Gai +1
Recent work has shown that the training of a one-hidden-layer, scalar-output fully-connected ReLU neural network can be reformulated as a finite-dimensional convex program. Unfortu…
Sharp Restricted Isometry Property Bounds for Low-rank Matrix Recovery Problems with Corrupted Measurements
Ziye Ma, Yingjie Bi, Javad Lavaei +1
In this paper, we study a general low-rank matrix recovery problem with linear measurements corrupted by some noise. The objective is to understand under what conditions on the res…
Internally Hankel -positive systems
Christian Grussler, Thiago B. Burghi, Somayeh Sojoudi
The classes of externally Hankel -positive LTI systems and autonomous -positive systems have recently been defined, and their properties and applications began to be explored…
Distributed Linear-Quadratic Control with Graph Neural Networks
Fernando Gama, Somayeh Sojoudi
Controlling network systems has become a problem of paramount importance. In this paper, we consider a distributed linear-quadratic problem and propose the use of graph neural netw…
Towards Optimal Branching of Linear and Semidefinite Relaxations for Neural Network Robustness Certification
Brendon G. Anderson, Ziye Ma, Jingqi Li +1
In this paper, we study certifying the robustness of ReLU neural networks against adversarial input perturbations. To diminish the relaxation error suffered by the popular linear p…