Galen Reeves

Research Interests

Information theory, high-dimensional statistical inference, statistical signal processing, compressed sensing, machine learning

Bio

Galen Reeves joined the faculty at Duke University in Fall 2013, and is currently an Associate Professor with a joint appointment in the Department of Electrical Computer Engineering and the Department of Statistical Science. He completed his PhD in Electrical Engineering and Computer Sciences at the University of California, Berkeley in 2011, and he was a postdoctoral associate in the Departments of Statistics at Stanford University from 2011 to 2013. His research interests include information theory and high-dimensional statistics. He received the NSF CAREER award in 2017.

Education

• Ph.D. University of California, Berkeley, 2011

Positions

• Associate Professor in the Department of Electrical and Computer Engineering
• Associate Professor of Statistical Science

Courses Taught

• STA 891: Topics for Preliminary Exam Preparation in Statistical Science
• STA 741: Compressed Sensing and Related Topics
• STA 711: Probability and Measure Theory
• STA 563: Information Theory
• STA 493: Research Independent Study
• STA 432: Theory and Methods of Statistical Learning and Inference
• MATH 343: Theory and Methods of Statistical Learning and Inference
• ECE 741: Compressed Sensing and Related Topics
• ECE 587: Information Theory
• ECE 586D: Vector Space Methods with Applications

Publications

• Reeves G, Pfister HD. Reed-Muller Codes on BMS Channels Achieve Vanishing Bit-Error Probability for all Rates Below Capacity. IEEE Transactions on Information Theory. 2024 Feb 1;70(2):920–49.
• Rossetti R, Nazer B, Reeves G. Linear Operator Approximate Message Passing: Power Method with Partial and Stochastic Updates. In: IEEE International Symposium on Information Theory - Proceedings. 2024. p. 741–6.
• Reeves G, Pfister HD. Achieving Capacity on Non-Binary Channels with Generalized Reed-Muller Codes. In: IEEE International Symposium on Information Theory - Proceedings. 2023. p. 2057–62.
• Van Den Boom W, Reeves G, Dunson DB. Erratum: Approximating posteriors with high-dimensional nuisance parameters via integrated rotated Gaussian approximation (Biometrika (2021) 108 (269-282) DOI: 10.1093/biomet/asaa068). Biometrika. 2022 Mar 1;109(1):275.
• Behne JK, Reeves G. Fundamental limits for rank-one matrix estimation with groupwise heteroskedasticity. In: Proceedings of Machine Learning Research. 2022. p. 8650–72.
• Goldfeld Z, Greenewald K, Nuradha T, Reeves G. k-Sliced Mutual Information: A Quantitative Study of Scalability with Dimension. In: Advances in Neural Information Processing Systems. 2022.
• Kipnis A, Reeves G. Gaussian Approximation of Quantization Error for Estimation from Compressed Data. IEEE Transactions on Information Theory. 2021 Aug 1;67(8):5562–79.
• VAN DEN Boom W, Reeves G, Dunson DB. Approximating posteriors with high-dimensional nuisance parameters via integrated rotated Gaussian approximation. Biometrika. 2021 Jun;108(2):269–82.
• Zhang Y, Cheng X, Reeves G. Convergence of Gaussian-smoothed optimal transport distance with sub-gamma distributions and dependent samples. In: Proceedings of Machine Learning Research. 2021. p. 2422–30.
• Goldt S, Loureiro B, Reeves G, Krzakala F, Mézard M, Zdeborová L. The Gaussian equivalence of generative models for learning with shallow neural networks. In: Proceedings of Machine Learning Research. 2021. p. 426–71.
• Reeves G, Pfister HD. Understanding Phase Transitions via Mutual Information and MMSE. In: Information-Theoretic Methods in Data Science. 2021. p. 197–228.
• Reeves G. A Two-Moment Inequality with Applications to Rényi Entropy and Mutual Information. Entropy (Basel, Switzerland). 2020 Nov;22(11):E1244.
• Reeves G. Information-theoretic limits for the matrix tensor product. IEEE Journal on Selected Areas in Information Theory. 2020 Nov 1;1(3):777–98.
• Barbier J, Reeves G. Information-theoretic limits of a multiview low-rank symmetric spiked matrix model. In: IEEE International Symposium on Information Theory - Proceedings. 2020. p. 2771–6.
• Reeves G, Xu J, Zadik I. The all-or-nothing phenomenon in sparse linear regression. Mathematical Statistics and Learning. 2020 Jan 1;3(3–4):259–313.
• Mathews H, Mayya V, Volfovsky A, Reeves G. Gaussian Mixture Models for Stochastic Block Models with Non-Vanishing Noise. 2019 IEEE 8th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2019 - Proceedings. 2019 Dec 1;699–703.
• Reeves G, Xu J, Zadik I. All-or-Nothing Phenomena: From Single-Letter to High Dimensions. In: 2019 IEEE 8th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2019 - Proceedings. 2019. p. 654–8.
• Mayya V, Reeves G. Mutual Information in Community Detection with Covariate Information and Correlated Networks. In: 2019 57th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2019. 2019. p. 602–7.
• Reeves G, Mayya V, Volfovsky A. The Geometry of Community Detection via the MMSE Matrix. IEEE International Symposium on Information Theory - Proceedings. 2019 Jul 1;2019-July:400–4.
• Kipnis A, Reeves G. Gaussian Approximation of Quantization Error for Estimation from Compressed Data. In: IEEE International Symposium on Information Theory - Proceedings. 2019. p. 2029–33.
• Reeves G, Pfister HD. The Replica-Symmetric Prediction for Random Linear Estimation With Gaussian Matrices Is Exact. IEEE Transactions on Information Theory. 2019 Apr 1;65(4):2252–83.
• Reeves G, Xu J, Zadik I. The All-or-Nothing Phenomenon in Sparse Linear Regression. In: Proceedings of Machine Learning Research. 2019. p. 2652–63.
• Bertran M, Martinez N, Papadaki A, Qiu Q, Rodrigues M, Reeves G, et al. Adversarially learned representations for information obfuscation and inference. In: 36th International Conference on Machine Learning, ICML 2019. 2019. p. 960–74.
• Kipnis A, Reeves G, Eldar YC. Single Letter Formulas for Quantized Compressed Sensing with Gaussian Codebooks. In: IEEE International Symposium on Information Theory - Proceedings. 2018. p. 71–5.
• Reeves G, Pfister HD, Dytso A. Mutual Information as a Function of Matrix SNR for Linear Gaussian Channels. In: IEEE International Symposium on Information Theory - Proceedings. 2018. p. 1754–8.
• Reeves G. Two-moment inequalities for Rényi entropy and mutual information. In: IEEE International Symposium on Information Theory - Proceedings. 2017. p. 664–8.
• Reeves G. Conditional central limit theorems for Gaussian projections. In: IEEE International Symposium on Information Theory - Proceedings. 2017. p. 3045–9.
• Kipnis A, Reeves G, Eldar YC, Goldsmith AJ. Compressed sensing under optimal quantization. In: IEEE International Symposium on Information Theory - Proceedings. 2017. p. 2148–52.
• Mainsah BO, Reeves G, Collins LM, Throckmorton CS. Optimizing the stimulus presentation paradigm design for the P300-based brain-computer interface using performance prediction. Journal of neural engineering. 2017 Aug;14(4):046025.
• Reeves G. Additivity of information in multilayer networks via additive Gaussian noise transforms. In: 55th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2017. 2017. p. 1064–70.
• Mainsah BO, Collins LM, Reeves G, Throckmorton CS. A performance-based approach to designing the stimulus presentation paradigm for the P300-based BCI by exploiting coding theory. In: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2017. p. 3026–30.
• Mayya V, Mainsah B, Reeves G. Modeling the P300-based brain-computer interface as a channel with memory. In: 54th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2016. 2017. p. 23–30.
• Renna F, Wang L, Yuan X, Yang J, Reeves G, Calderbank R, et al. Classification and Reconstruction of High-Dimensional Signals from Low-Dimensional Features in the Presence of Side Information. In: IEEE Transactions on Information Theory. 2016. p. 6459–92.
• Reeves G, Pfister HD. The replica-symmetric prediction for compressed sensing with Gaussian matrices is exact. In: IEEE International Symposium on Information Theory - Proceedings. 2016. p. 665–9.
• Llull P, Reeves G, Carin L, Brady DJ. Performance assessment of image translation-engineered point spread functions. In: Optics InfoBase Conference Papers. 2016.
• Renna F, Wang L, Yuan X, Yang J, Reeves G, Calderbank R, et al. Classification and reconstruction of compressed GMM signals with side information. In: IEEE International Symposium on Information Theory - Proceedings. 2015. p. 994–8.
• Van Den Boom W, Dunson D, Reeves G. Quantifying uncertainty in variable selection with arbitrary matrices. In: 2015 IEEE 6th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2015. 2015. p. 385–8.
• Reeves G. The fundamental limits of stable recovery in compressed sensing. IEEE International Symposium on Information Theory - Proceedings. 2014 Jan 1;3017–21.
• Reeves G. Beyond sparsity: Universally stable compressed sensing when the number of 'free' values is less than the number of observations. 2013 5th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2013. 2013 Dec 1;17–20.
• Reeves G, Gastpar MC. Approximate sparsity pattern recovery: Information-theoretic lower bounds. IEEE Transactions on Information Theory. 2013 May 23;59(6):3451–65.
• Reeves G, Donoho D. The minimax noise sensitivity in compressed sensing. IEEE International Symposium on Information Theory - Proceedings. 2013 Jan 1;116–20.
• Donoho D, Reeves G. Achieving Bayes MMSE performance in the sparse signal + Gaussian white noise model when the noise level is unknown. IEEE International Symposium on Information Theory - Proceedings. 2013 Jan 1;101–5.
• Reeves G, Gastpar M. Compressed sensing phase transitions: Rigorous bounds versus replica predictions. 2012 46th Annual Conference on Information Sciences and Systems, CISS 2012. 2012 Nov 12;
• Donoho D, Reeves G. The sensitivity of compressed sensing performance to relaxation of sparsity. IEEE International Symposium on Information Theory - Proceedings. 2012 Oct 22;2211–5.
• Reeves G, Gastpar M. The sampling rate-distortion tradeoff for sparsity pattern recovery in compressed sensing. IEEE Transactions on Information Theory. 2012 May 1;58(5):3065–92.
• Reeves G, Goela N, Milosavljevic N, Gastpar M. A compressed sensing wire-tap channel. 2011 IEEE Information Theory Workshop, ITW 2011. 2011 Dec 21;548–52.
• Reeves G, Gastpar M. On the role of diversity in sparsity estimation. IEEE International Symposium on Information Theory - Proceedings. 2011 Oct 26;119–23.
• Reeves G, Gastpar M. "Compressed" compressed sensing. IEEE International Symposium on Information Theory - Proceedings. 2010 Aug 23;1548–52.
• Reeves G, Gastpar M. A note on optimal support recovery in compressed sensing. Conference Record - Asilomar Conference on Signals, Systems and Computers. 2009 Dec 1;1576–80.
• Reeves G, Liu J, Nath S, Zhao F. Managing massive time series streams with multi-scale compressed trickles. Proceedings of the VLDB Endowment. 2009 Jan 1;2(1):97–108.
• Reeves G, Gastpar M. Sampling bounds for sparse support recovery in the presence of noise. IEEE International Symposium on Information Theory - Proceedings. 2008 Sep 29;2187–91.
• Reeves G, Gastpar M. Differences between observation and sampling error in sparse signal reconstruction. IEEE Workshop on Statistical Signal Processing Proceedings. 2007 Dec 1;690–4.
• Mayya V, Mainsah B. Information Theoretic Analysis of the Impact of Refractory Effects on the P300 Speller. In.

In The News

• Meet the Newly Tenured Faculty of 2021 (Sep 21, 2021 | Office of Faculty Advancement)