[vc_row][vc_column][vc_column_text]
Thesis
- Theory and methods for problems arising in robust stability, optimization and quantization
In the pipeline …
- Why Random Reshuffling Beats Stochastic Gradient Descent (with Asu Ozdaglar and Pablo Parrilo), Submitted.
-
Global Convergence Rate of Proximal Incremental Aggregated Gradient Methods, (with D. Vanli and A. Ozdaglar), In Revision, 2017.
- On the convergence rate of the incremental gradient and Newton method (with A. Ozdaglar and P. Parrilo), Submitted.
- Surpassing Gradient Descent Provably: A Cyclic Incremental Method with Linear Convergence Rate (with A. Mokthari and A. Ribiero), Submitted, 2016.
Published Journals
- Convergence rate of incremental aggregated gradient algorithms (with Asu Ozdaglar and Pablo Parrilo), SIAM Journal on Optimization, 2017.
- Approximating the real structured stability radius with Frobenius-bounded perturbations via spectral value sets (with N. Guglielmi, T. Mitchell and M. Overton), SIAM Journal on Matrix Analysis and Applications. Slides
- A new globally convergent incremental Newton method (with Asu Ozdaglar and Pablo Parrilo), Math. Programming, 2015.
- Polynomial Root Radius Optimization with Affine Constraints (with Julie Eaton, Sara Grundel and Michael Overton), Math. Programming, 2015.
- Fast approximation of the H-infinity norm via Optimization over Spectral Value Sets (with Nicola Guglielmi and Michael L. Overton), Siam Journal on Matrix Analysis and Applications, 2013.
- Some regularity results for the pseudospectral abscissa and pseudospectral radius of a matrix (with M.L. Overton), Siam Journal on Optimization, 2013.
- Explicit Solutions for Root Optimization of a Polynomial Family With One Affine Constraint (with V.D. Blondel, A. Megretski and M.L. Overton), IEEE Transactions on Automatic Control, 2012.
- On Nesterov’s Nonsmooth Chebyschev-Rosenbrock Functions (with M.L. Overton), Journal of Nonlinear Analysis: Theory, Methods, Applications, Special Issue: Variational Analysis and Its Applications, Invited paper, 2011.
Conferences
- When Cyclic Coordinate Descent Outperforms Randomized Coordinate Descent (with A. Ozdaglar, P. Parrilo and N. D. Vanli), NIPS, Accepted with Spotlight invitation, 2017.
- Avoiding Communication in Proximal Methods for Convex Optimization Problems, (with Saeed Soori, Aditya Devarakonda, James Demmel and Maryam Mehri Dehnavi), Submitted to IEEE IPDPS Conference, 2017.
- Decentralized Computation of Effective Resistances and Acceleration of Consensus Algorithms (with N.S. Aybat), IEEE GlobalSIP Conference, 2017.
- A Double Incremental Aggregated Gradient Method with Linear Convergence Rate for Large-scale Optimization (with A. Mokthari and A. Ribiero), 42nd IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017.
- A Simple Proof for the Iteration Complexity of the Proximal Gradient Algorithm (with D. Vanli and A. Ozdaglar), NIPS Optimization Workshop, 2016.
- Polynomial Stabilization with Bounds on the Controller Coefficients, 8th IFAC Symposium on Robust Control Design (ROCOND), 2015.
- Explicit Solutions for Root Optimization of a Polynomial Family (with V.D. Blondel, A. Megretski and M.L. Overton), Proceedings of the 49th IEEE Conference on Decision and Control (CDC 2010).
[/vc_column_text][/vc_column][/vc_row][vc_row][vc_column][vc_column_text]Please also my Google Scholar page for a (recent) list of publications.[/vc_column_text][/vc_column][/vc_row]