Dr Armin Eftekhari

Research Interests:

  • Signal Processing
  • Machine Learning
  • Optimization
  • Numerical Analysis

Biography

Armin is currently an Assistant professor at Department of Mathematics and Mathematical Statistics at Umeå University. Armin Eftekhari received his PhD from Colorado School of Mines in 2015. Before joining the Laboratory for Information and Inference Systems at EPFL as a postdoctoral researcher, he was a Research Fellow at the Alan Turing Institute in London and a Peter O’Donnell, Jr. Postdoctoral Fellow at UT Austin.
Armin works with different data models and, as the late statistician George Box once wrote, “all models are wrong, but some are useful.”
Indeed, to make sense of data, we must necessarily impose some structure upon it. For example, we often assume that digital data is collected from band-limited sources. Or, in compressive sensing, we work with sparse signals that have a concise representation in some “dictionary.” Making inferences from (often noisy, incomplete, and high-dimensional) data by imposing appropriate structures has been the main theme of Armin’s research.

Publications with LIONS (most recent)

Computing Second-Order Points Under Equality Constraints: Revisiting Fletcher’s Augmented Lagrangian

F. Goyens; A. Eftekhari; N. Boumal 

Journal Of Optimization Theory And Applications. 2024-04-11. DOI : 10.1007/s10957-024-02421-6.

Subquadratic Overparameterization for Shallow Neural Networks

C. Song; A. Ramezani-Kebrya; T. Pethick; A. Eftekhari; V. Cevher 

2021. 35th Conference on Neural Information Processing Systems (NeurIPS 2021), Sydney, Australia, December 6-14, 2021.

Sparse non-negative super-resolution – simplified and stabilised

A. Eftekhari; J. Tanner; A. Thompson; B. Toader; H. Tyagi 

Applied And Computational Harmonic Analysis. 2021-01-01. Vol. 50, p. 216-280. DOI : 10.1016/j.acha.2019.08.004.

Principal Component Analysis By Optimization Of Symmetric Functions Has No Spurious Local Optima

A. Eftekhari; R. A. Hauser 

Siam Journal On Optimization. 2020-01-01. Vol. 30, num. 1, p. 439-463. DOI : 10.1137/18M1188495.

MOSES: A Streaming Algorithm for Linear Dimensionality Reduction

A. Eftekhari; R. A. Hauser; A. Grammenos 

Ieee Transactions On Pattern Analysis And Machine Intelligence. 2020-11-01. Vol. 42, num. 11, p. 2901-2911. DOI : 10.1109/TPAMI.2019.2919597.

Double-Loop Unadjusted Langevin Algorithm

P. Rolland; A. Eftekhari; A. Kavis; V. Cevher 

2020. 37th International Conference on Machine Learning (ICLM 2020), Virtual, July 12-18, 2020.

Scalable Learning-Based Sampling Optimization For Compressive Dynamic MRI

T. Sanchez; B. Gözcü; R. Van Heeswijk; A. Eftekhari; E. Ilıcak et al. 

2020. International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Barcelona, Spain, May 4-8, 2020. p. 8584-8588. DOI : 10.1109/ICASSP40776.2020.9053345.

An Inexact Augmented Lagrangian Framework for Nonconvex Optimization with Nonlinear Constraints

M. F. Sahin; A. Eftekhari; A. Alacaoglu; F. R. Latorre Gomez; V. Cevher 

2019. NeurIPS 2019 : Thirty-third Conference on Neural Information Processing Systems, Vancouver, Canada, December 8-14, 2019.

Fast and Provable ADMM for Learning with Generative Priors

F. R. Latorre Gomez; A. Eftekhari; V. Cevher 

2019. 33rd Conference on Neural Information Processing Systems (NeurIPS), Vancouver, Canada, December 8-14, 2019.

Sparse Inverse Problems Over Measures: Equivalence Of The Conditional Gradient And Exchange Methods

A. Eftekhari; A. Thompson 

Siam Journal On Optimization. 2019-01-01. Vol. 29, num. 2, p. 1329-1349. DOI : 10.1137/18M1183388.

Streaming Principal Component Analysis From Incomplete Data

A. Eftekhari; G. Ongie; L. Balzano; M. B. Wakin 

Journal Of Machine Learning Research. 2019-01-01. Vol. 20.