I am an assistant professor in the Electrical and Computer Engineering Department at Iowa State University.

I am also a recipient of the Black and Veatch Faculty Fellowship.

I am interested broadly in problems related to data processing and machine learning. My research focuses on developing fast and robust algorithms for diverse problems in data sensing and inference.

Prior to joining ISU, I was a post-doctoral associate in the Theory of Computation (TOC) group at MIT where I worked with Piotr Indyk. I received my Ph.D. at Rice University under the supervision of Rich Baraniuk.

[CV]   [Google Scholar]  


August 2018

Received an NSF ATD Grant for our project on efficient algorithms for non-Euclidean regression (Eric Weber, Fritz Keinert, and Steve Sapp).

July 2018

Our group presented multiple papers at ICML 2018 and affiliated workshops.

June 2018

Received an NSF CCF Grant for our project on estimation from phaseless observations (along with PI Namrata Vaswani).

June 2018

Invited talk on sparse coding and autoencoder learning at MMLS 2018.

June 2018

New papers on autoencoder learning and distributed deep learning posted on ArXiv.

May 2018

New paper on provable dictionary learning from incomplete samples accepted to ICML 2018.

May 2018

We are organizing the 3rd Midwest Big Data Summer School on May 14-17. More details here.

May 2018

I have been named a senior member of the IEEE.

April 2018

Conference travel! Gave a talk on provable learning of shallow networks at AISTATS. Our group also presented multiple papers at ICASSP.

March 2018

Two new papers on low-rank matrix estimation and solving random quadratic equations accepted to ISIT 2018.

January 2018

I am honored to be named a recipient of the NSF CAREER Award.

January 2018

Three new papers on Fourier ptychography, phase retrieval, and learning with GANs accepted to ICASSP 2018.

December 2017

New paper on provable neural network learning accepted to AISTATS 2018.

December 2017

Our group presented multiple papers at NIPS 2017 and affiliated workshops.

December 2017

New preprints on low-rank matrix estimation, phase retrieval, and sparse coding available on ArXiv.

November 2017

New paper on provable double-sparse coding accepted to AAAI 2018.

September 2017

I am a recipient of the Black and Veatch Faculty Fellowship for 2017-2020.

September 2017

Two papers on phase retrieval and distributed deep learning accepted to NIPS 2017.

August 2017

Spotlight and poster presented at KDD MLG in Halifax, NS.

August 2017

Invited talk on fast machine learning at the Alan Turing Institute in London.

July 2017

Invited talk on structured phase retrieval at the Annual International Linear Algebra Symposium (ILAS) meeting.

July 2017

New papers on parallel matrix completion and signal unmixing to appear in IEEE GlobalSIP in November.

July 2017

New monograph on basics of data analytics and machine learning; this is a compiled version of my lecture notes from the Spring '17 edition of 525X.

July 2017

New papers on graph sketching and HDR imaging to appear in Asilomar in November.

June 2017

Mohammadreza received a best poster award at MMLS '17 for presenting this paper. Congratulations!!

May 2017

Invited talk on matrix recovery at SIAM Optimization Conference.

May 2017

New papers on phase retrieval and matrix recovery posted on arXiv.

April 2017

New paper on fast algorithms for signal demixing accepted to IEEE TSP.

April 2017

We are organizing the 2nd Midwest Big Data Summer School on July 10-14. More details here. Register quickly!

March 2017

Invited talks on signal recovery from periodic features given at ITA and ICASSP.

January 2017

New paper on graph-based outage identification accepted to IEEE PESGM 2017.

December 2016

NVIDIA Corporation kindly donated a Titan X Pascal to our group as part of their GPU Grant Program.

December 2016

New paper on recovery from sinusoidal features accepted at ICASSP 2017.

November 2016

GPUFish, a new parallel computing toolbox for very large-scale matrix completion problems, is now public. Attendant paper here.

October 2016

I am a recipient of the 2016 Warren Boast Undergraduate Teaching Award.

September 2016

I am part of a team of transportation engineers and data scientists that got awarded an NSF PFI:BIC grant for a project focussing on traffic incident management. Thanks to Anuj Sharma (CCEE Department and INTRANS) for leading the team!

August 2016

More new papers on signal demixing from nonlinear observations.

April 2016

I am a recipient of the NSF CRII Award. Thanks NSF!!

some recent publications
For a full list, click here.

Towards Provable Learning of Polynomial Neural Networks using Low-Rank Matrix Estimation
with Mohammadreza Soltani.
AISTATS, April 2018.
A Provable Approach for Double-Sparse Coding
with Thanh Nguyen and Raymond Wong.
AAAI, February 2018.
Fast, Sample-Efficient Algorithms for Structured Phase Retrieval
with Gauri Jagatap.
NIPS, December 2017.
Collaborative Deep Learning over Fixed-Topology Networks
with Zhanhong Jiang, Aditya Balu, and Soumik Sarkar.
NIPS, December 2017.
Fast Algorithms for Learning Latent Variables in Graphical Models
with Mohammadreza Soltani.
KDD MLG, August 2017.
Stable Recovery of Sparse Vectors from Random Sinusoidal Feature Maps
with Mohammadreza Soltani.
ICASSP, March 2017.
Fast Recovery from a Union of Subspaces
with Piotr Indyk and Ludwig Schmidt.
Neural Information Processing Systems (NIPS), December 2016.
Data-Driven Prognostics of a Li-Ion Rechargeable Battery Using Bilinear Kernel Regression
with Charles Hubbard, John Bavslik, and Chao Hu.
Proc. Annual Conference of the Prognostics and Health Management (PHM) Society, October 2016.
Fast Algorithms for Demixing Sparse Signals from Nonlinear Observations
with Mohammadreza Soltani.
Preprint, August 2016.
NuMax: A Convex Approach for Learning Near-Isometric Linear Embeddings
with Aswin Sankaranarayanan, Wotao Yin, and Richard Baraniuk.
IEEE Trans. Signal Processing, November 2015.
Fast Algorithms for Structured Sparsity
with Piotr Indyk and Ludwig Schmidt.
Bulletin of the European Association of Theoretical Computer Science, October 2015.
Approximation Algorithms for Model-Based Compressive Sensing
with Piotr Indyk and Ludwig Schmidt.
IEEE Trans. Information Theory, September 2015.
A Nearly Linear-Time Framework for Graph-Structured Sparsity
with Piotr Indyk and Ludwig Schmidt.
In Proc. Int. Conf. Machine Learning (ICML), July 2015.

For detailed descriptions, click here.