default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDRoman Vershynin
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2024
[j22]March Boedihardjo
, Thomas Strohmer, Roman Vershynin:
Covariance's Loss is Privacy's Gain: Computationally Efficient, Private and Accurate Synthetic Data. Found. Comput. Math. 24(1): 179-226 (2024)- [i36]Girish Kumar, Thomas Strohmer, Roman Vershynin:
An Algorithm for Streaming Differentially Private Data. CoRR abs/2401.14577 (2024) - [i35]Yiyun He, Roman Vershynin, Yizhe Zhu:
Online Differentially Private Synthetic Data Generation. CoRR abs/2402.08012 (2024) - [i34]March Boedihardjo, Thomas Strohmer, Roman Vershynin:
Metric geometry of the privacy-utility tradeoff. CoRR abs/2405.00329 (2024) - [i33]Girish Kumar, Thomas Strohmer, Roman Vershynin:
Differentially Private Synthetic High-dimensional Tabular Stream. CoRR abs/2409.00322 (2024) - 2023
- [j21]Pierre Baldi, Roman Vershynin:
The quarks of attention: Structure and capacity of neural attention building blocks. Artif. Intell. 319: 103901 (2023) - [j20]Yan Shuo Tan, Roman Vershynin:
Online Stochastic Gradient Descent with Arbitrary Initialization Solves Non-smooth, Non-convex Phase Retrieval. J. Mach. Learn. Res. 24: 58:1-58:47 (2023) - [j19]Kathryn Dover, Zixuan Cang, Anna Ma, Qing Nie, Roman Vershynin:
AVIDA: An alternating method for visualizing and integrating data. J. Comput. Sci. 68: 101998 (2023) - [j18]March Boedihardjo, Thomas Strohmer, Roman Vershynin:
Privacy of Synthetic Data: A Statistical Framework. IEEE Trans. Inf. Theory 69(1): 520-527 (2023) - [c12]Yiyun He, Roman Vershynin, Yizhe Zhu:
Algorithmically Effective Differentially Private Synthetic Data. COLT 2023: 3941-3968 - [i32]March Boedihardjo, Thomas Strohmer, Roman Vershynin:
Covariance loss, Szemeredi regularity, and differential privacy. CoRR abs/2301.02705 (2023) - [i31]Yiyun He, Roman Vershynin, Yizhe Zhu:
Algorithmically Effective Differentially Private Synthetic Data. CoRR abs/2302.05552 (2023) - [i30]Yiyun He, Thomas Strohmer, Roman Vershynin, Yizhe Zhu:
Differentially private low-dimensional representation of high-dimensional data. CoRR abs/2305.17148 (2023) - 2022
- [j17]March Boedihardjo, Thomas Strohmer, Roman Vershynin:
Private Sampling: A Noiseless Approach for Generating Differentially Private Synthetic Data. SIAM J. Math. Data Sci. 4(3): 1082-1115 (2022) - [i29]Pierre Baldi, Roman Vershynin:
The Quarks of Attention. CoRR abs/2202.08371 (2022) - [i28]March Boedihardjo, Thomas Strohmer, Roman Vershynin:
Private measures, random walks, and synthetic data. CoRR abs/2204.09167 (2022) - [i27]Kathryn Dover, Zixuan Cang, Anna Ma, Qing Nie, Roman Vershynin:
AVIDA: Alternating method for Visualizing and Integrating Data. CoRR abs/2206.00135 (2022) - 2021
- [j16]Pierre Baldi, Roman Vershynin:
A theory of capacity and sparse neural encoding. Neural Networks 143: 12-27 (2021) - [i26]Pierre Baldi, Roman Vershynin:
A theory of capacity and sparse neural encoding. CoRR abs/2102.10148 (2021) - [i25]March Boedihardjo, Thomas Strohmer, Roman Vershynin:
Covariance's Loss is Privacy's Gain: Computationally Efficient, Private and Accurate Synthetic Data. CoRR abs/2107.05824 (2021) - [i24]March Boedihardjo, Thomas Strohmer, Roman Vershynin:
Privacy of synthetic data: a statistical framework. CoRR abs/2109.01748 (2021) - [i23]March Boedihardjo, Thomas Strohmer, Roman Vershynin:
Private sampling: a noiseless approach for generating differentially private synthetic data. CoRR abs/2109.14839 (2021) - 2020
- [j15]Roman Vershynin:
Memory Capacity of Neural Networks with Threshold and Rectified Linear Unit Activations. SIAM J. Math. Data Sci. 2(4): 1004-1033 (2020) - [i22]Roman Vershynin:
Memory capacity of neural networks with threshold and ReLU activations. CoRR abs/2001.06938 (2020)
2010 – 2019
- 2019
- [j14]Pierre Baldi, Roman Vershynin:
The capacity of feedforward neural networks. Neural Networks 116: 288-311 (2019) - [j13]Pierre Baldi, Roman Vershynin:
Polynomial Threshold Functions, Hyperplane Arrangements, and Random Tensors. SIAM J. Math. Data Sci. 1(4): 699-729 (2019) - [i21]Pierre Baldi, Roman Vershynin:
The capacity of feedforward neural networks. CoRR abs/1901.00434 (2019) - [i20]Yan Shuo Tan, Roman Vershynin:
Online Stochastic Gradient Descent with Arbitrary Initialization Solves Non-smooth, Non-convex Phase Retrieval. CoRR abs/1910.12837 (2019) - 2018
- [j12]Jess Banks, Cristopher Moore, Roman Vershynin, Nicolas Verzelen, Jiaming Xu:
Information-Theoretic Bounds and Phase Transitions in Clustering, Sparse PCA, and Submatrix Localization. IEEE Trans. Inf. Theory 64(7): 4872-4894 (2018) - [c11]Yan Shuo Tan, Roman Vershynin:
Polynomial Time and Sample Complexity for Non-Gaussian Component Analysis: Spectral Methods. COLT 2018: 498-534 - [c10]Pierre Baldi, Roman Vershynin:
On Neuronal Capacity. NeurIPS 2018: 7740-7749 - 2017
- [j11]Can M. Le, Elizaveta Levina, Roman Vershynin:
Concentration and regularization of random graphs. Random Struct. Algorithms 51(3): 538-561 (2017) - [c9]Jess Banks, Cristopher Moore, Roman Vershynin, Nicolas Verzelen, Jiaming Xu:
Information-theoretic bounds and phase transitions in clustering, sparse PCA, and submatrix localization. ISIT 2017: 1137-1141 - [i19]Yan Shuo Tan, Roman Vershynin:
Polynomial Time and Sample Complexity for Non-Gaussian Component Analysis: Spectral Methods. CoRR abs/1704.01041 (2017) - [i18]Yan Shuo Tan, Roman Vershynin:
Phase Retrieval via Randomized Kaczmarz: Theoretical Guarantees. CoRR abs/1706.09993 (2017) - 2016
- [j10]Yaniv Plan, Roman Vershynin:
The Generalized Lasso With Non-Linear Observations. IEEE Trans. Inf. Theory 62(3): 1528-1537 (2016) - [i17]Christopher Liaw, Abbas Mehrabian, Yaniv Plan, Roman Vershynin:
A simple tool for bounding the deviation of random matrices on geometric sets. CoRR abs/1603.00897 (2016) - [i16]Jess Banks, Cristopher Moore, Roman Vershynin, Jiaming Xu:
Information-theoretic bounds and phase transitions in clustering, sparse PCA, and submatrix localization. CoRR abs/1607.05222 (2016) - [i15]Roman Vershynin:
Four lectures on probabilistic methods for data science. CoRR abs/1612.06661 (2016) - 2015
- [j9]Raja Giryes, Yaniv Plan, Roman Vershynin:
On the Effective Measure of Dimension in the Analysis Cosparse Model. IEEE Trans. Inf. Theory 61(10): 5745-5753 (2015) - [i14]Can M. Le, Elizaveta Levina, Roman Vershynin:
Sparse random graphs: regularization and concentration of the Laplacian. CoRR abs/1502.03049 (2015) - [i13]Yaniv Plan, Roman Vershynin:
The generalized Lasso with non-linear observations. CoRR abs/1502.04071 (2015) - [i12]Can M. Le, Roman Vershynin:
Concentration and regularization of random graphs. CoRR abs/1506.00669 (2015) - 2014
- [j8]Yaniv Plan, Roman Vershynin:
Dimension Reduction by Random Hyperplane Tessellations. Discret. Comput. Geom. 51(2): 438-461 (2014) - [j7]Roman Vershynin:
Invertibility of symmetric random matrices. Random Struct. Algorithms 44(2): 135-182 (2014) - [i11]Can M. Le, Elizaveta Levina, Roman Vershynin:
Optimization via Low-rank Approximation, with Applications to Community Detection in Networks. CoRR abs/1406.0067 (2014) - [i10]Raja Giryes, Yaniv Plan, Roman Vershynin:
On the Effective Measure of Dimension in the Analysis Cosparse Model. CoRR abs/1410.0989 (2014) - [i9]Olivier Guédon, Roman Vershynin:
Community detection in sparse networks via Grothendieck's inequality. CoRR abs/1411.4686 (2014) - 2013
- [j6]Yaniv Plan, Roman Vershynin:
Robust 1-bit Compressed Sensing and Sparse Logistic Regression: A Convex Programming Approach. IEEE Trans. Inf. Theory 59(1): 482-494 (2013) - 2012
- [p1]Roman Vershynin:
Introduction to the non-asymptotic analysis of random matrices. Compressed Sensing 2012: 210-268 - [i8]Yaniv Plan, Roman Vershynin:
Robust 1-bit compressed sensing and sparse logistic regression: A convex programming approach. CoRR abs/1202.1212 (2012) - [i7]Albert Ai, Alex Lapanowski, Yaniv Plan, Roman Vershynin:
One-bit compressed sensing with non-Gaussian measurements. CoRR abs/1208.6279 (2012) - 2011
- [i6]Yaniv Plan, Roman Vershynin:
One-bit compressed sensing by linear programming. CoRR abs/1109.4299 (2011) - 2010
- [j5]Deanna Needell, Roman Vershynin:
Signal Recovery From Incomplete and Inaccurate Measurements Via Regularized Orthogonal Matching Pursuit. IEEE J. Sel. Top. Signal Process. 4(2): 310-316 (2010) - [j4]Yurii Lyubarskii, Roman Vershynin:
Uncertainty principles and vector quantization. IEEE Trans. Inf. Theory 56(7): 3491-3501 (2010) - [i5]Roman Vershynin:
Introduction to the non-asymptotic analysis of random matrices. CoRR abs/1011.3027 (2010)
2000 – 2009
- 2009
- [j3]Deanna Needell, Roman Vershynin:
Uniform Uncertainty Principle and Signal Recovery via Regularized Orthogonal Matching Pursuit. Found. Comput. Math. 9(3): 317-334 (2009) - [j2]Roman Vershynin:
Beyond Hirsch Conjecture: Walks on Random Polytopes and Smoothed Complexity of the Simplex Method. SIAM J. Comput. 39(2): 646-678 (2009) - 2008
- [c8]Deanna Needell, Joel A. Tropp, Roman Vershynin:
Greedy signal recovery review. ACSCC 2008: 1048-1050 - [c7]Deanna Needell, Roman Vershynin:
Greedy signal recovery and uncertainty principles. Computational Imaging 2008: 68140 - [i4]Deanna Needell, Joel A. Tropp, Roman Vershynin:
Greedy Signal Recovery Review. CoRR abs/0812.2202 (2008) - 2007
- [j1]Mark Rudelson, Roman Vershynin:
Sampling from large matrices: An approach through geometric functional analysis. J. ACM 54(4): 21 (2007) - [c6]Anna C. Gilbert, Martin J. Strauss, Joel A. Tropp, Roman Vershynin:
One sketch for all: fast algorithms for compressed sensing. STOC 2007: 237-246 - [i3]Roman Vershynin:
Some problems in asymptotic convex geometry and random matrices motivated by numerical algorithms. CoRR abs/cs/0703093 (2007) - 2006
- [c5]Thomas Strohmer, Roman Vershynin:
A Randomized Solver for Linear Systems with Exponential Convergence. APPROX-RANDOM 2006: 499-507 - [c4]Mark Rudelson, Roman Vershynin:
Sparse reconstruction by convex relaxation: Fourier and Gaussian measurements. CISS 2006: 207-212 - [c3]Roman Vershynin:
Beyond Hirsch Conjecture: Walks on Random Polytopes and Smoothed Complexity of the Simplex Method. FOCS 2006: 133-142 - [i2]Roman Vershynin:
Beyond Hirsch Conjecture: walks on random polytopes and smoothed complexity of the simplex method. CoRR abs/cs/0604055 (2006) - [i1]Anna C. Gilbert, Martin J. Strauss, Joel A. Tropp, Roman Vershynin:
Algorithmic linear dimension reduction in the l_1 norm for sparse vectors. CoRR abs/cs/0608079 (2006) - 2005
- [c2]Emmanuel J. Candès, Mark Rudelson, Terence Tao, Roman Vershynin:
Error Correction via Linear Programming. FOCS 2005: 295-308 - 2002
- [c1]Shahar Mendelson, Roman Vershynin:
Entropy, Combinatorial Dimensions and Random Averages. COLT 2002: 14-28
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-10-07 01:17 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
