SPADA lab

Signal Processing Algorithm Design and Analysis

SPADA LogoOur lab studies algorithms for statistical signal processing and machine learning with applications in data analysis, computer vision, environmental monitoring, image processing, control systems, power grids, genetic expression data analysis, consumer preference modeling, and computer network analysis. We are interested in algorithmic design using principles from optimization theory, as well as mathematical analysis answering questions regarding algorithmic convergence behavior and performance, required sample complexity, algorithmic robustness. See the projects page for descriptions of some of our research areas and the publications page for our research papers.

You can find Professor Balzano’s mentoring plan here.

For prospective postdocs or students at all levels interested in joining SPADA lab, please read to the end of this page.

SPADA lab May 2026:

SPADA lab 2026
L:R Elvin Tseng, Can Yaras, Nicholas Simafranca, Amir Hedayat, Soo Min Kwon, Linglong Meng, Gavin Kunesh, Laya Pullela, Laura Balzano. Not pictured: Alex Ritchie, Rachel Newton, Jessica Jiang, Matt Asato.

Ph.D. Students

I have the pleasure of working with the following outstanding students and postdocs. Listed is their most recent publication with the SPADA lab.

Rachel Newton | website | (co-advised with Peter Seiler)

1399621 Newton 1 apa 1 date desc 235 https://web.eecs.umich.edu/~girasole/wp-content/plugins/zotpress/
%7B%22status%22%3A%22success%22%2C%22updateneeded%22%3Afalse%2C%22instance%22%3Afalse%2C%22meta%22%3A%7B%22request_last%22%3A0%2C%22request_next%22%3A0%2C%22used_cache%22%3Atrue%7D%2C%22data%22%3A%5B%7B%22key%22%3A%22D3LM67BL%22%2C%22library%22%3A%7B%22id%22%3A1399621%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Newton%20et%20al.%22%2C%22parsedDate%22%3A%222023-12-19%22%2C%22numChildren%22%3A2%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BNewton%2C%20R.%2C%20Du%2C%20Z.%2C%20Seiler%2C%20P.%2C%20%26amp%3B%20Balzano%2C%20L.%20%282023%29.%20Optimality%20of%20POD%20for%20Data-Driven%20LQR%20With%20Low-Rank%20Structures.%20%26lt%3Bi%26gt%3BIEEE%20Control%20Systems%20Letters%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B8%26lt%3B%5C%2Fi%26gt%3B%2C%2085%26%23x2013%3B90.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FLCSYS.2023.3344147%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FLCSYS.2023.3344147%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Optimality%20of%20POD%20for%20Data-Driven%20LQR%20With%20Low-Rank%20Structures%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Rachel%22%2C%22lastName%22%3A%22Newton%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Zhe%22%2C%22lastName%22%3A%22Du%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Peter%22%2C%22lastName%22%3A%22Seiler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Laura%22%2C%22lastName%22%3A%22Balzano%22%7D%5D%2C%22abstractNote%22%3A%22The%20optimal%20state-feedback%20gain%20for%20the%20Linear%20Quadratic%20Regulator%20%28LQR%29%20problem%20is%20computationally%20costly%20to%20compute%20for%20high-order%20systems.%20Reduced-order%20models%20%28ROMs%29%20can%20be%20used%20to%20compute%20feedback%20gains%20with%20reduced%20computational%20cost.%20However%2C%20the%20performance%20of%20this%20common%20practice%20is%20not%20fully%20understood.%20This%20letter%20studies%20this%20practice%20in%20the%20context%20of%20data-driven%20LQR%20problems.%20We%20show%20that%2C%20for%20a%20class%20of%20LQR%20problems%20with%20low-rank%20structures%2C%20the%20controllers%20designed%20via%20their%20ROM%2C%20based%20on%20the%20Proper%20Orthogonal%20Decomposition%20%28POD%29%2C%20are%20indeed%20optimal.%20Experimental%20results%20not%20only%20validate%20our%20theory%20but%20also%20demonstrate%20that%20even%20with%20moderate%20perturbations%20on%20the%20low-rank%20structure%2C%20the%20incurred%20suboptimality%20is%20mild.%22%2C%22date%22%3A%2212%5C%2F19%5C%2F2023%22%2C%22section%22%3A%22%22%2C%22partNumber%22%3A%22%22%2C%22partTitle%22%3A%22%22%2C%22DOI%22%3A%2210.1109%5C%2FLCSYS.2023.3344147%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fieeexplore.ieee.org%5C%2Fabstract%5C%2Fdocument%5C%2F10365496%22%2C%22PMID%22%3A%22%22%2C%22PMCID%22%3A%22%22%2C%22ISSN%22%3A%222475-1456%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%22DZFDBB6V%22%5D%2C%22dateModified%22%3A%222024-12-12T22%3A11%3A12Z%22%7D%7D%5D%7D
Newton, R., Du, Z., Seiler, P., & Balzano, L. (2023). Optimality of POD for Data-Driven LQR With Low-Rank Structures. IEEE Control Systems Letters, 8, 85–90. https://doi.org/10.1109/LCSYS.2023.3344147

Can Yaras | website | (co-advised with Qing Qu)

1399621 Yaras 1 apa 1 date desc 235 https://web.eecs.umich.edu/~girasole/wp-content/plugins/zotpress/
%7B%22status%22%3A%22success%22%2C%22updateneeded%22%3Afalse%2C%22instance%22%3Afalse%2C%22meta%22%3A%7B%22request_last%22%3A0%2C%22request_next%22%3A0%2C%22used_cache%22%3Atrue%7D%2C%22data%22%3A%5B%7B%22key%22%3A%22RP3LQSUZ%22%2C%22library%22%3A%7B%22id%22%3A1399621%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Kwon%20et%20al.%22%2C%22parsedDate%22%3A%222026-06-05%22%2C%22numChildren%22%3A2%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BKwon%2C%20S.%20M.%2C%20Xu%2C%20A.%20S.%2C%20Yaras%2C%20C.%2C%20Song%2C%20D.%2C%20Balzano%2C%20L.%2C%20%26amp%3B%20Qu%2C%20Q.%20%282026%29.%20%26lt%3Bi%26gt%3BThe%20Effect%20of%20Training%20Task%20Diversity%20on%20In-Context%20Learning%20through%20the%20Lens%20of%20Low-Dimensional%20Subspaces%26lt%3B%5C%2Fi%26gt%3B%20%28arXiv%3A2606.06814%29.%20arXiv.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2606.06814%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2606.06814%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22preprint%22%2C%22title%22%3A%22The%20Effect%20of%20Training%20Task%20Diversity%20on%20In-Context%20Learning%20through%20the%20Lens%20of%20Low-Dimensional%20Subspaces%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Soo%20Min%22%2C%22lastName%22%3A%22Kwon%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Alec%20S.%22%2C%22lastName%22%3A%22Xu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Can%22%2C%22lastName%22%3A%22Yaras%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Dogyoon%22%2C%22lastName%22%3A%22Song%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Laura%22%2C%22lastName%22%3A%22Balzano%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Qing%22%2C%22lastName%22%3A%22Qu%22%7D%5D%2C%22abstractNote%22%3A%22The%20transformer%26%23039%3Bs%20emergent%20ability%20to%20perform%20in-context%20learning%20%28ICL%29%20has%20sparked%20a%20wide%20range%20of%20studies%20designed%20to%20understand%20its%20underlying%20mechanisms.%20Existing%20works%20often%20study%20how%20training%20task%20diversity%2C%20defined%20either%20as%20the%20number%20of%20ICL%20training%20task%20vectors%20or%20as%20the%20number%20of%20function%20classes%20from%20which%20the%20task%20vectors%20are%20drawn%2C%20shapes%20both%20the%20learning%20dynamics%20and%20generalization%20capabilities%20of%20ICL.%20While%20both%20definitions%20have%20uncovered%20many%20interesting%20phenomena%2C%20many%20observations%20under%20the%20latter%20definition%20remain%20theoretically%20unexplained.%20This%20paper%20presents%20a%20minimal%20analytical%20model%20under%20which%20these%20phenomena%20provably%20emerge%20from%20the%20properties%20of%20the%20training%20data.%20By%20modeling%20the%20training%20task%20vectors%20as%20a%20mixture%20of%20low-rank%20Gaussians%2C%20we%20show%20how%20training%20task%20diversity%2C%20defined%20by%20the%20number%20of%20non-overlapping%20columns%20between%20subspaces%20that%20parameterize%20the%20covariance%20matrices%2C%20improves%20both%20the%20generalization%20and%20optimization%20trajectory%20of%20ICL%20with%20linear%20attention.%20In%20particular%2C%20we%20show%20that%20our%20model%20can%20explain%20%28i%29%20why%20training%20with%20task%20diversity%20shortens%20the%20ICL%20plateau%20and%20%28ii%29%20why%20ICL%20appears%20to%20achieve%20out-of-distribution%20generalization.%20We%20conclude%20by%20empirically%20demonstrating%20how%20our%20results%20extend%20to%20nonlinear%20transformers%20and%20nonlinear%20function%20classes.%20Overall%2C%20our%20work%20presents%20a%20tractable%20framework%20to%20unify%20existing%20observations.%22%2C%22genre%22%3A%22%22%2C%22repository%22%3A%22arXiv%22%2C%22archiveID%22%3A%22arXiv%3A2606.06814%22%2C%22date%22%3A%222026-06-05%22%2C%22DOI%22%3A%2210.48550%5C%2FarXiv.2606.06814%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2606.06814%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%22J2WEX3C9%22%5D%2C%22dateModified%22%3A%222026-07-10T21%3A39%3A58Z%22%7D%7D%5D%7D
Kwon, S. M., Xu, A. S., Yaras, C., Song, D., Balzano, L., & Qu, Q. (2026). The Effect of Training Task Diversity on In-Context Learning through the Lens of Low-Dimensional Subspaces (arXiv:2606.06814). arXiv. https://doi.org/10.48550/arXiv.2606.06814

Elvin Tseng | website | (Ph.D. student in Statistics)

Laya Pullela | website | (co-advised with Minji Kim)

Jessica Jiang | website | (co-advised with Clay Scott)

Gavin Kunesh | website | (co-advised with Al Hero)

Postdocs

(None currently)

Master’s and Undergraduate Students

Matt Asato
Linglong Meng
Nicholas Simafranca
Roy Wu
Yijue Zhang

Former Ph.D. Students and Postdocs

Alex Ritchie | website | (co-advised with Clay Scott)
Defended June 2026, “Covariate Structure as Weak Supervision in Estimation Problems.”
Next position: TBD.

Soo Min Kwon | website | (co-advised with Qing Qu)
Defended May 2026, “Deep Learning through Low-Dimensional Representations: Theory and Algorithms.”
Next position: Applied Scientist at Microsoft.

Javier Salazar Cavazos | website | (co-advised with Jeff Fessler)
Defended March 2026, “Learning Representations from Noisy Data and Brain Imaging: Subspace Modeling for Heteroscedastic Data and Deep Learning for Functional MRI in Alzheimer’s Disease.”
Next position: Algorithm Engineer at KLA.

Peng Wang | website | (Postdoc co-mentored with Qing Qu)
Next position: Assistant Professor at University of Macau.

Zhe Du | website | (co-advised with Necmiye Ozay)
Defended November 2022, “Learning, Control, and Reduction for Markov Jump Systems”
Next position: Postdoc at UC Riverside.

Kyle Gilman | website
Defended October 2022, “Scalable Algorithms Using Optimization on Orthogonal Matrix Manifolds”
Next positions: Applied AI/ML Senior Associate at Chase Bank. Member of Technical Staff at MIT Lincoln Laboratory.

Davoud Ataee Tarzanagh | website
Next positions: Postdoctoral scholar at University of Pennsylvania. AI Scientist at Samsung.

Haroon Raja | website
Next positions: Postdoctoral scholar at Tufts. AI Research Scientist at Eli Lilly.

Amanda Bower | website | (AIM Ph.D. student co-advised with Martin Strauss)
Defended October 2020, “Dealing with Intransitivity, Non-Convexity, and Algorithmic Bias in Preference Learning”
Next position: Twitter’s ML Ethics, Transparency, and Accountability (META) group.

Ali Soltani-Tehrani | website
Next position: Associate Principal Data Scientist at AstraZeneca.

Dejiao Zhang | website
Defended May 2019, “Extracting Compact Knowledge from Massive Data”
Next positions: Applied research scientist at Amazon Web Services. Senior staff research scientist at Figma.

David Hong | website | (co-advised with Jeff Fessler)
Defended March 2019, “Learning Low-Dimensional Models for Heterogeneous Data”
Next positions: Postdoctoral scholar at Penn – Wharton Statistics Department. Assistant Professor at the University of Delaware.

Greg Ongie | website
Next positions: Postdoctoral scholar at University of Chicago – Statistics and Computer Science Departments. Assistant professor of Mathematics at Marquette University.

John Lipor | website
Defended September 2017, “Sensing Structured Signals with Active and Ensemble Methods”
Next positions: Assistant and then Associate Professor in the Portland State University ECE Department

Former MS lab members:

Yutong Wang 
Rishhabh Naik
Nisarg Trivedi
Geoffrey Fortman
Pengyu Xiao
Saket Dewangan
Jenna King

Former undergraduate researchers:

Ian Steele
Jake Hume
Iman Malik
Austin Xu
Eli Smith
Andrew Gitlin
Bob Malinas
Nora Farouk
William Zhang
Richard Ortman

Prospective students and postdocs:

If you are interested in joining my research lab, either working on a small project, a Ph.D. thesis, or a postdoctoral project, please read this information.

In the SPADA lab, we enjoy working with students and collaborators who have an enthusiastic curiosity for mathematics and algorithms and their applications in machine learning and signal processing. Our work will draw on tools from probability, linear algebra, and functional analysis as well as contemporary mathematics. You must also demonstrate independent thinking, patience, and integrity. For students already at Michigan, both graduate and undergraduate: Please email me with your CV and the types of projects you’d be interested in, and we can set up a time to meet during my office hours. For prospective postdocs: Please email me with your CV and a research statement, and highlight our shared interests and potential collaborative projects. For prospective graduate students: Please start by applying to the ECE Michigan graduate program. Include my name in your research statement along with reasons why you’d be interested in working with me. I am not actively looking for new students in the fall of 2027, however, I am always open to working with truly outstanding students.

Please make your email subject line “Joining the Balzano lab” to show me you have read this. I will do my best to respond as soon as I can. Since I am busy taking care of my current students, it may take several weeks before I find the time, so I encourage your patience. You will appreciate these priorities if you end up at Michigan. If I have not replied in a few months time, you can assume your background was not a good fit for the lab. Best of luck to you in your search for a research mentor.

SPADA lab April 2024:

SPADA Lab members April 2024

SPADA lab September 2022:

SPADA lab members September 2022

SPADA lab January 2021:

SPADA lab April 2019:

SPADA lab December 2017: