Picture for Zaid Harchaoui

Zaid Harchaoui

Modified Gauss-Newton Algorithms under Noise

May 18, 2023
Krishna Pillutla, Vincent Roulet, Sham Kakade, Zaid Harchaoui

* IEEE SSP 2023

Access Paper or Ask Questions

Confidence Sets under Generalized Self-Concordance

Dec 31, 2022
Lang Liu, Zaid Harchaoui

Figure 1 for Confidence Sets under Generalized Self-Concordance

Figure 2 for Confidence Sets under Generalized Self-Concordance

Figure 3 for Confidence Sets under Generalized Self-Concordance

Figure 4 for Confidence Sets under Generalized Self-Concordance

Access Paper or Ask Questions

Stochastic optimization on matrices and a graphon McKean-Vlasov limit

Oct 02, 2022
Zaid Harchaoui, Sewoong Oh, Soumik Pal, Raghav Somani, Raghavendra Tripathi

* 35 pages

Access Paper or Ask Questions

Iterative Linear Quadratic Optimization for Nonlinear Control: Differentiable Programming Algorithmic Templates

Jul 13, 2022
Vincent Roulet, Siddhartha Srinivasa, Maryam Fazel, Zaid Harchaoui

Figure 1 for Iterative Linear Quadratic Optimization for Nonlinear Control: Differentiable Programming Algorithmic Templates

Figure 2 for Iterative Linear Quadratic Optimization for Nonlinear Control: Differentiable Programming Algorithmic Templates

Figure 3 for Iterative Linear Quadratic Optimization for Nonlinear Control: Differentiable Programming Algorithmic Templates

Figure 4 for Iterative Linear Quadratic Optimization for Nonlinear Control: Differentiable Programming Algorithmic Templates

* This is a companion report to the arXiv report "Complexity Bounds of Iterative Linear Quadratic Optimization Algorithms for Discrete Time Nonlinear Control" by the same authors

Access Paper or Ask Questions

Orthogonal Statistical Learning with Self-Concordant Loss

Apr 30, 2022
Lang Liu, Carlos Cinelli, Zaid Harchaoui

Figure 1 for Orthogonal Statistical Learning with Self-Concordant Loss

Figure 2 for Orthogonal Statistical Learning with Self-Concordant Loss

Figure 3 for Orthogonal Statistical Learning with Self-Concordant Loss

Access Paper or Ask Questions