13 citations · 16 across the 6 of their papers we have counts for
8 papers
Verifying performance, stability, and feasibility of inexact non-linear model predictive controllers
Rajiv Sambharya, Sribalaji C. Anand, George Pappas
We introduce a verification framework to numerically analyze inexact model predictive controllers (MPCs) in the constrained non-linear discrete-time setting. Rather than modifying…
Verification of Sequential Convex Programming for Parametric Non-convex Optimization
Rajiv Sambharya, Nikolai Matni, George Pappas
We introduce a verification framework to exactly verify the worst-case performance of sequential convex programming (SCP) algorithms for parametric non-convex optimization. The ver…
Learning Acceleration Algorithms for Fast Parametric Convex Optimization with Certified Robustness
Rajiv Sambharya, Jinho Bok, Nikolai Matni +1
We develop a machine-learning framework to learn hyperparameter sequences for accelerated first-order methods (e.g., the step size and momentum sequences in accelerated gradient de…
Learning Algorithm Hyperparameters for Fast Parametric Convex Optimization
Rajiv Sambharya, Bartolomeo Stellato
We introduce a machine-learning framework to learn the hyperparameter sequence of first-order methods (e.g., the step sizes in gradient descent) to quickly solve parametric convex…
Data-Driven Performance Guarantees for Classical and Learned Optimizers
Rajiv Sambharya, Bartolomeo Stellato
We introduce a data-driven approach to analyze the performance of continuous optimization algorithms using generalization guarantees from statistical learning theory. We study clas…
Learning to Warm-Start Fixed-Point Optimization Algorithms
Rajiv Sambharya, Georgina Hall, Brandon Amos +1
We introduce a machine-learning framework to warm-start fixed-point optimization algorithms. Our architecture consists of a neural network mapping problem parameters to warm starts…
End-to-End Learning to Warm-Start for Real-Time Quadratic Optimization
Rajiv Sambharya, Georgina Hall, Brandon Amos +1
First-order methods are widely used to solve convex quadratic programs (QPs) in real-time applications because of their low per-iteration cost. However, they can suffer from slow c…
Lifted Neural Networks
Armin Askari, Geoffrey Negiar, Rajiv Sambharya +1
We describe a novel family of models of multi- layer feedforward neural networks in which the activation functions are encoded via penalties in the training problem. Our approach i…