Arya Mazumdar (Publications by Topics)
As of 2022: I no longer update this page
Copyright: Most of the papers listed below are published and the copyrights may have been transferred to the publisher. Papers cannot be duplicated for commercial purposes.
Author ordering: I try to maintain alphabetical ordering of authors in most of my papers since I was a graduate student. However, as per engineering tradition student/junior authors are sometimes listed first.
Below is a hard partitioning of my papers according to topics. However in reality the clustering should be soft/overlapping/fuzzy.
J: Journal. C: Conferences.
Mixtures and Statistical Reconstructions
(C) On Learning Mixture of Linear Regressions in the Non-Realizable Setting
Avishek Ghosh, Arya Mazumdar, Soumyabrata Pal, Rajat Sen
International Conference on Machine Learning (ICML), 2022.
(C) On Learning Mixture Models with Sparse Parameters
Arya Mazumdar, Soumyabrata Pal
International Conference on Artificial Intelligence and Statistics (AISTATS), 2022.
(C) Lower Bounds on the Total Variation Distance Between Mixtures of Two Gaussians
Sami Davies, Arya Mazumdar, Soumyabrata Pal, Cyrus Rashtchian
Algorithmic Learning Theory (ALT), 2022.
(C) Support Recovery of Sparse Signals from a Mixture of Linear Measurements
Venkata Gandikota, Arya Mazumdar, Soumyabrata Pal
Neural Information Processing Systems (NeurIPS), 2021.
(J) Trace Reconstruction: Generalized and Parameterized
Akshay Krishnamurthy, Arya Mazumdar, Andrew McGregor, Soumyabrata Pal
IEEE Transactions on Information Theory (TIT), Special Levenshtein Memorial Issue, vol. 67, no. 6, 2021.
Shorter version in European Symposium on Algorithms (ESA), 2019.
(C) Recovery of Sparse Linear Classifiers from Mixture of Responses
Venkata Gandikota, Arya Mazumdar, Soumyabrata Pal
Neural Information Processing Systems (NeurIPS), 2020.
(C) Recovery of Sparse Signals from a Mixture of Linear Samples
Arya Mazumdar, Soumyabrata Pal
International Conference on Machine Learning (ICML), 2020.
(C) Algebraic and Analytic Approaches for Parameter Learning in Mixture Models
Akshay Krishnamurthy, Arya Mazumdar, Andrew McGregor and Soumyabrata Pal
Algorithmic Learning Theory (ALT), 2020.
(C) Sample Complexity of Learning Mixture of Sparse Linear Regressions
Akshay Krishnamurthy, Arya Mazumdar, Andrew McGregor, Soumyabrata Pal
Neural Information Processing Systems (NeurIPS), 2019.
Distributed Learning and Optimization
Escaping Saddle Points in Distributed Newton's Method with Communication efficiency and Byzantine Resilience
Avishek Ghosh, Raj Kumar Maity, Arya Mazumdar.
(C) vqSGD: Vector Quantized Stochastic Gradient Descent
Venkata Gandikota, Daniel Kane, Raj Kumar Maity, Arya Mazumdar
IEEE Transactions on Information Theory (TIT), to appear in 2022.
Preliminary version in International Conference on Artificial Intelligence and Statistics (AISTATS), 2021.
Also in ICML 2019 Workshop on Security and Privacy in Machine Learning. Oral Presentation.
(C) Byzantine Resilient Distributed Clustering with Redundant Data Assignment
Saikiran Bulusu, Venkata Gandikota, Arya Mazumdar, Ankit Singh Rawat, Pramod Kumar Varshney
IEEE International Symposium on Information Theory (ISIT), 2021.
(C) Distributed Newton Can Communicate Less and Resist Byzantine Workers
Avishek Ghosh, Raj Kumar Maity, Arya Mazumdar
Neural Information Processing Systems (NeurIPS), 2020.
Also in ICML 2020 Workshop on Beyond first order methods in machine learning systems, 2020.
(C) Communication Efficient Distributed Approximate Newton Method
Avishek Ghosh, Raj Kumar Maity, Arya Mazumdar, Kannan Ramchandran
IEEE International Symposium on Information Theory (ISIT), 2020.
(J) Communication-Efficient and Byzantine-Robust Distributed Learning with Error Feedback
Avishek Ghosh, Raj Kumar Maity, Swanand Kadhe, Arya Mazumdar, Kannan Ramchandran
IEEE Journal on Selected Areas of Information Theory (JSAIT), Sep 2021
Shorter version in International Symposium on Information Theory (ISIT), 2020.
(C) Reliable Distributed Clustering with Redundant Data Assignment
Venkata Gandikota, Arya Mazumdar, Ankit Singh Rawat
IEEE International Symposium on Information Theory (ISIT), 2020
Also in ICML 2019 Workshop on Coding Theory for Large-Scale Machine Learning, 2019. Spotlight Presentation.
(C) Robust Gradient Descent via Moment Encoding with LDPC Codes
Raj Kumar Maity, Ankit Singh Rawat, Arya Mazumdar
IEEE International Symposium on Information Theory (ISIT), 2019
Extended abstract in The SysML Conference, 2018. Oral Presentation.
Clustering with Oracle Queries
Random Subgraph Detection Using Queries
Wasim Huleihel, Arya Mazumdar, Soumyabrata Pal.
(C) Fuzzy Clustering with Similarity Queries
Wasim Huleihel, Arya Mazumdar, Soumyabrata Pal
Neural Information Processing Systems (NeurIPS), 2021.
(J) Semisupervised Clustering by Queries and Locally Encodable Source Coding
Arya Mazumdar, Soumyabrata Pal
IEEE Transactions on Information Theory (TIT), vol. 67, no. 2, 2021.
Also in Neural Information Processing Systems (NeurIPS), 2017. Spotlight Presentation
(C) Same-Cluster Querying for Overlapping Clusters
Wasim Huleihel, Arya Mazumdar, Muriel Medard, Soumyabrata Pal
Neural Information Processing Systems (NeurIPS), 2019.
(C) Query Complexity of Clustering with Side Information
Arya Mazumdar, Barna Saha
Neural Information Processing Systems (NeurIPS), 2017.
See an older version here: Clustering via Crowdsourcing.
(C) Clustering with Noisy Queries
Arya Mazumdar, Barna Saha
Neural Information Processing Systems (NeurIPS), 2017.
(C) A Theoretical Analysis of First Heuristics of Crowdsourced Entity Resolution
Arya Mazumdar, Barna Saha
31st AAAI Conference on Artificial Intelligence (AAAI), 2017.
Extreme Multilabel Classification
(C) Session-Aware Query Auto-completion using Extreme Multi-label Ranking
Nishant Yadav, Rajat Sen, Daniel N. Hill, Arya Mazumdar, Inderjit S. Dhillon
SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2021.
(C) Multilabel Classification by Hierarchical Partitioning and Data-dependent Grouping
Shashanka Ubaru, Sanjeeb Dash, Arya Mazumdar, Oktay Gunluk
Neural Information Processing Systems (NeurIPS), 2020.
Also in NeurIPS Workshop on Information Theory and Machine Learning, 2019.
(C) Multilabel Classification with Group Testing and Codes
Shashanka Ubaru, Arya Mazumdar
Thirty-fourth International Conference on Machine Learning (ICML), 2017.
Compressed Sensing and Sparsity
(C) Binary Iterative Hard Thresholding Converges with Optimal Number of Measurements for 1-Bit Compressed Sensing
Namiko Matsumoto, Arya Mazumdar
Foundations of Computer Science (FOCS), 2022.
(C) Support Recovery in Universal One-bit Compressed Sensing
Arya Mazumdar, Soumyabrata Pal
The 13th Innovations in Theoretical Computer Science (ITCS), 2022.
(C) Superset Technique for Approximate Recovery in One-Bit Compressed Sensing
Larkin Flodin, Venkata Gandikota, Arya Mazumdar
Neural Information Processing Systems (NeurIPS), 2019.
(C) Learning and Recovery in the ReLU Model
Arya Mazumdar, Ankit Singh Rawat
Allerton Conference on Communication, Control and Computing (Allerton), Monticello, IL, 2019.
Also as Learning Network Parameters in the ReLU Model
NeurIPS 2019 Workshop on Solving inverse problems with deep networks: New architectures, theoretical foundations, and applications (DeepInverse), 2019.
(C) Compressive Traffic Analysis: A New Paradigm for Scalable Traffic Analysis
Milad Nasr, Amir Houmansadr, Arya Mazumdar
ACM Conference on Computer and Communications Security (CCS), 2017.
(C) Estimation of Sparsity via Simple Measurements
Abhishek Agarwal, Larkin Flodin, Arya Mazumdar
IEEE International Symposium on Information Theory (ISIT), 2017.
(J) Restricted Isometry Property of Random Subdictionaries #
Alexander Barg, Arya Mazumdar, Rongrong Wang
IEEE Transactions on Information Theory (TIT), vol. 61, no. 8, Aug 2015, arXiv version
An earlier version with some extra results.
(I) Sparse-Recovery Properties of Statistical RIP Matrices
Arya Mazumdar, Alexander Barg
49th Allerton Conference on Communication, Control and Computing (Allerton), Monticello, IL, 2011.
(I) Statistical RIP Sampling Matrices and Robust Recovery
Arya Mazumdar, Alexander Barg
International Mathematical Conference: 50 Years of IITP, St. Petersburg, Russia, Jul 25–29, 2011. (Invited).
(C) General Constructions of Deterministic (Statistical) RIP Matrices for Compressive Sampling
Arya Mazumdar, Alexander Barg
IEEE International Symposium on Information Theory (ISIT), St. Petersburg, Russia 2011.
(C) Small Ensembles of Sampling Matrices Constructed from Coding Theory
Alexander Barg, Arya Mazumdar
Proc. IEEE International Symposium on Information Theory (ISIT), Austin, Jul 13-18, 2010, pp 1963-1967.
Group Testing
(C) Probabilistic Group Testing with a Linear Number of Tests
Larkin Flodin, Arya Mazumdar
IEEE International Symposium on Information Theory (ISIT), 2021.
(C) Novel Impossibility Results for Group-Testing
Abhishek Agarwal, Sidharth Jaggi, Arya Mazumdar
IEEE International Symposium on Information Theory (ISIT), 2018.
(J) Group Testing Schemes from Codes and Designs
Alexander Barg, Arya Mazumdar
IEEE Transactions on Information Theory (TIT), vol. 63, no. 11, Nov 2017.
(J) Nonadaptive Group Testing with Random Set of Defectives
Arya Mazumdar
IEEE Transactions on Information Theory (TIT), vol. 62, no. 12, Dec 2016, arXiv version.
(C) Group testing schemes from low-weight codewords of BCH codes
Shashanka Ubaru, Arya Mazumdar, Alexander Barg
IEEE International Symposium on Information Theory (ISIT), Barcelona, 2016.
(I) Group Testing with Unreliable Elements
Arya Mazumdar, Soheil Mohajer
52nd Allerton Conference on Communication, Control and Computing (Allerton), Monticello, IL, 2014. (Invited).
(C) On Almost Disjunct Matrices for Group Testing
Arya Mazumdar
Algorithms and Computation (ISAAC), Springer LNCS 7676, pp. 649–658, 2012.
Differential Privacy
Index Coding and Storage Capacity
(J) Storage Capacity as an Information-Theoretic Vertex Cover and the Index Coding Rate
Arya Mazumdar, Andrew McGregor, Sofya Vorotnikova
IEEE Transactions on Information Theory (TIT), vol. 65, no. 9, 2019.
Also in IEEE International Symposium on Information Theory (ISIT), 2017.
(J) Linear Programming Approximations for Index Coding
Abhishek Agarwal, Larkin Flodin, Arya Mazumdar
IEEE Transactions on Information Theory (TIT), vol. 65, no. 9, 2019.
(C) Local partial clique and cycle covers for index coding
Abhishek Agarwal, Arya Mazumdar
Network Coding and Applications (NetCod), IEEE GLOBECOM Workshop, 2016.
Also in Signal Processing and Communications (SPCOM), Bangalore, India, 2016. (Invited).
(J) Storage Capacity of Repairable Networks
Arya Mazumdar
IEEE Transactions on Information Theory (TIT), vol. 61, no. 11, Nov 2015, arXiv version.
(I) Achievable Schemes and Limits for local Recovery on a Graph
Arya Mazumdar
52nd Allerton Conference on Communication, Control and Computing (Allerton), Monticello, IL, 2014. (Invited).
(C) On a Duality Between Recoverable Distributed Storage and Index Coding
Arya Mazumdar
IEEE International Symposium on Information Theory (ISIT), Hawaii, 2014.
Codes and Sampling
(C) High Dimensional Discrete Integration over the Hypergrid
Raj Kumar Maity, Arya Mazumdar, Soumyabrata Pal
Uncertainty in Artificial Intelligence (UAI), 2020.
(J) Low Rank Approximation and Decomposition of Large Matrices using Error Correcting Codes
Shashanka Ubaru, Arya Mazumdar, Yousef Saad
IEEE Transactions on Information Theory (TIT), vol. 63, no. 9, Sep 2017.
Also in International Conference on Machine Learning (ICML), Lille, France, 2015.
ICML version contains some minor errors that have since been corrected in the above revised version.
Community Detection and Random Graphs
(C) Connectivity in Random Annulus Graphs and the Geometric Block Model
Sainyam Galhotra, Arya Mazumdar, Soumyabrata Pal, Barna Saha
International Conference on Randomization and Computation (RANDOM), 2019.
(C) The Geometric Block Model
Sainyam Galhotra, Arya Mazumdar, Soumyabrata Pal, Barna Saha
The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI), 2018.
The above revised version in arXiv contains some corrections to the proceeding version.
Also in NIPS 2017 Workshop on Learning on Distributions, Functions, Graphs and Groups, 2017.
Locally Repairable Codes
(J) Combinatorial Alphabet-Dependent Bounds for Locally Recoverable Codes
Abhishek Agarwal, Alexander Barg, Sihuang Hu, Arya Mazumdar, Itzhak Tamo
IEEE Transactions on Information Theory (TIT), vol. 64, no. 5, May 2018.
(C) Capacity of Locally Recoverable Codes
Arya Mazumdar
IEEE Information Theory Workshop (ITW), 2018.
(J) Security in Locally Repairable Storage
Abhishek Agarwal, Arya Mazumdar
IEEE Transactions on Information Theory (TIT), vol. 62, no. 11, Nov 2016, arXiv version.
(C) Bounds on the Rate of Linear Locally Repairable Codes over Small Alphabets
Abhishek Agarwal, Arya Mazumdar
54nd Allerton Conference on Communication, Control and Computing (Allerton), Monticello, IL, 2016.
(J) Cooperative Local Repair in Distributed Storage
Ankit Singh Rawat, Arya Mazumdar, Sriram Vishwanath
EURASIP Journal on Advances in Signal Processing (JASP), 2015:107, Dec 2015, arXiv version
2020 EURASIP JASP Best Paper Award
Also in Conference on Information Sciences and Systems (CISS), 2014. (Invited).
(J) Bounds on the Size of Locally Recoverable Codes
Viveck Cadambe, Arya Mazumdar
IEEE Transactions on Information Theory (TIT), vol. 61, no. 11, Nov 2015, arXiv version.
(I) Alphabet-size dependent bounds for Exact Repair in Distributed Storage
Viveck Cadambe, Arya Mazumdar
IEEE Information Theory Workshop (ITW), Jeju Island, 2015. (Invited).
(C) Local Recovery in Data Compression for General Sources
Arya Mazumdar, Venkat Chandar, Gregory Wornell
IEEE International Symposium on Information Theory (ISIT), Hong Kong, 2015.
(C) Security in Locally Repairable Storage
Abhishek Agarwal, Arya Mazumdar
IEEE Information Theory Workshop (ITW), Jerusalem, Israel, 2015.
(J) Update-Eficiency and Local Repairability Limits for Capacity Approaching Codes
Arya Mazumdar, Venkat Chandar, Gregory Wornell
IEEE Journal on Selected Areas of Communications (JSAC), vol. 32, no. 5, May 2014, view/download here, arXiv version.
Special issue on Communication Methodologies for the Next-Generation Storage.
(C) An Upper Bound on the Size of Locally Recoverable Codes
Viveck Cadambe, Arya Mazumdar
IEEE International Symposium on Network Coding (NetCod), Calgary, Canada, 2013.
(I) Local Recovery Properties of Capacity-Achieving Codes
Arya Mazumdar, Venkat Chandar, Gregory W. Wornell
Information Theory and Applications (ITA), San Diego, CA, 2013. (Invited).
(C) Update-Efficient Codes for Error Correction
Arya Mazumdar, Gregory W. Wornell, Venkat Chandar
IEEE International Symposium on Information Theory (ISIT), Boston, MA, 2012.
Rank Aggregation
Associative Memory
Combinatorial Joint-Source-Channel Codes/Error Reducing Codes
(C) Hamming codes as error-reducing codes
William Rurik, Arya Mazumdar
IEEE Information Theory Workshop (ITW), Cambridge, UK 2016.
(C) Distance preserving maps and combinatorial joint source-channel coding for large alphabets
Arya Mazumdar, Yury Polyanskiy, Ankit Singh Rawat, Hajir Roozbehani
IEEE International Symposium on Information Theory (ISIT), Barcelona, 2016.
(C) On Adversarial Joint Source Channel Coding
Arya Mazumdar, Ankit Singh Rawat
IEEE International Symposium on Information Theory (ISIT), Hong Kong, 2015.
(C) On Chebyshev Radius in Hamming Space and the Closest String Problem
Arya Mazumdar, Yury Polyanskiy, Barna Saha
IEEE International Symposium on Information Theory (ISIT), Istanbul, Turkey, 2013, pp. 1401–1405.
(I) Results on Combinatorial Joint Source Channel Coding
Yuval Kochman, Arya Mazumdar, Yury Polyanskiy
IEEE Information Theory Workshop (ITW), 2012. (Invited).
(C) Adversarial Joint Source Channel Problem
Yuval Kochman, Arya Mazumdar, Yury Polyanskiy
IEEE International Symposium on Information Theory (ISIT), Boston, MA, 2012.
Rank Modulation and Codes in Permutation
(J) Compression in the Space of Permutations
Da Wang, Arya Mazumdar, Gregory Wornell
IEEE Transactions on Information Theory (TIT), vol. 61, no. 12, Dec 2015, arXiv version.
(C) Lossy Compression of Permutations
Da Wang, Arya Mazumdar, Gregory Wornell
IEEE International Symposium on Information Theory (ISIT), Hawaii, 2014.
Errata: Part 2 and 6 of Theorem 5 is incorrect. Hence the claim of equivalence of source codes for different metrics are not as universal. However, this does not affect the final result, i.e., Theorem 6, which is still true.
(I) Smooth Representation of Rankings
Arya Mazumdar, Olgica Milenkovic
Conference on Information Sciences and Systems (CISS), 2014. (Invited).
(J) Constructions of Rank Modulation Codes #
Arya Mazumdar, Alexander Barg, Gilles Zemor
IEEE Transactions on Information Theory (TIT), vol. 59, no. 2, Feb 2013, arXiv version.
(C) A Rate-Distortion Theory for Permutation Spaces
Da Wang, Arya Mazumdar, Gregory W. Wornell
IEEE International Symposium on Information Theory (ISIT), Istanbul, Turkey, 2013, pp. 2562–2566.
(I) Parameters of Rank Modulation Codes: Examples
Arya Mazumdar, Alexander Barg, Gilles Zemor
49th Allerton Conference on Communication, Control and Computing (Allerton), Monticello, IL, 2011. (Invited).
(C) Constructions of Rank Modulation Codes
Arya Mazumdar, Alexander Barg, Gilles Zemor
IEEE International Symposium on Information Theory (ISIT) St. Petersburg, Russia, 2011.
(J) Codes in Permutations and Error Correction for Rank Modulation #
Alexander Barg, Arya Mazumdar
IEEE Transactions on Information Theory (TIT), Vol. 56, Issue 7, July 2010, pp. 3158-3165.
Also in Proc. IEEE International Symposium on Information Theory (ISIT), Austin, Jul 13-18, 2010, pp 854–858.
Jack K. Wolf Paper Award
Information Theory
Codes for Memory and Storage
(J) Coding for High Density Recording on
a 1-D Granular Magnetic Medium
Arya Mazumdar, Alexander Barg, Navin Kashyap
IEEE Transactions on Information Theory (TIT), vol. 57,
no. 11, Nov 2011, arXiv version.
(C) Channels with Intermittent Errors
Arya Mazumdar, Alexander Barg
IEEE International Symposium on Information Theory (ISIT) St. Petersburg, Russia, 2011. Runner-up for Jack K. Wolf Paper Award
(J) On Linear Balancing Sets
Arya Mazumdar, Ron Roth, Pascal Vontobel
Advances in Mathematics of Communications (AMC), Vol. 4, No. 3, Aug 2010, pp. 345-361.
Also in Proc. IEEE International Symposium on Information Theory (ISIT), Seoul, Jun 28-Jul 3, 2009, pp. 2699-2703.
(I) On the Capacity of High-Density Magnetic Recording on a 1-D Granular Medium
Arya Mazumdar, Alexander Barg, Navin Kashyap
Proc. 48th Annual Allerton Conference on Communication, Control and Computing (Allerton), Monticello, Illinois, Sep 28–Oct 1, 2010.
(C) Coding for High-Density Magnetic Recording
Arya Mazumdar, Alexander Barg, Navin Kashyap
Proc. IEEE International Symposium on Information Theory (ISIT), Austin, Jul 13-18, 2010, pp 978-982.
(I) Codes for Storage of Data on a 1-d Granular Magnetic Medium
Arya Mazumdar, Alexander Barg, Navin Kashyap
Proc. International Conference on Signal Processing and Communications (SPCOM), Bangalore, Jul 18-21, 2010, pp 1-3. (Invited).
Codes on Graphs
(J) On the Number of Errors Correctable with Codes on Graphs #
Alexander Barg, Arya Mazumdar
IEEE Transactions on Information Theory (TIT), vol. 57, no. 2, Feb 2011, arXiv version
Special Ralf Koetter memorial issue:
Facets of Coding Theory: from Algorithms to Networks.
Also in Proc. IEEE International Symposium on Information Theory (ISIT), Seoul, Jun 28-Jul 3, 2009, pp. 2482-2486.
(J) Weight Distribution and Decoding of Codes on Hypergraphs #
Alexander Barg, Arya Mazumdar, Gilles Zemor
Advances in Mathematics of Communications (AMC), Vol. 2, No. 4, November 2008, pp. 433-450.
(J) Construction of Turbo Code Interleavers from 3-regular Hamiltonian Graph
Arya Mazumdar, A K Chaturvedi, Adrish Banerjee
IEEE Communication Letters (ComLetters), Vol. 10, Issue 4, April 2006, pp. 284-286.
(I) Weight Distribution of Codes on Hypergraphs
Alexander Barg, Arya Mazumdar, Gilles Zemor
Proc. 46th Annual Allerton Conference on Communication, Control and Computing (Allerton), Monticello, Illinois, Sep 23-26, 2008, pp. 400-401. (Invited).
(C) Analysis of Bipartite Graph Codes on the Binary Erasure Channel
Arya Mazumdar
Proc. 45th Annual Allerton Conference on Communication, Control and Computing (Allerton), Illinois, 2007, pp. 897-904.
(C) On the Spread of Random Interleavers
Arya Mazumdar, A Banerjee, A K Chaturvedi
Proc. IEEE International Symposium on Information Theory (ISIT), Adelaide, 2005, pp. 439-443.
Thesis
Combinatorial Methods in Coding Theory
Ph.D. Thesis, University of Maryland, 2011. Distinguished Dissertation Award.
My work in the thesis is essentially equal to the sum of contents of journal publications marked with a #.
Reviews
Undergraduate Stuff
(C) Bidirectional Fuzzy-Regression Model for Roadline Detection
Barna Saha, Arya Mazumdar, N R Pal
Proc. IEEE International Conference on Engineering of Intelligent Systems (ICIES) 2006, Islamabad, pp. 1-6.
(C) Towards Optimal Set of Bases for Orthonormal Code Diversity Detection CDMA Systems
Arya Mazumdar, M P Sriram, A K Chaturvedi
Proc. National Conference on Communications (NCC), New Delhi, 2006.
|