Conference papers

CRISP: Curriculum based Sequential Neural Decoders for Polar Code Family
S Ashwin Hebbar, Viraj Nadkarni, Ashok Vardhan Makkuva, Suma Bhat, Sewoong Oh, Pramod Viswanath
working paper,

MAUVE Scores for Generative Models: Theory and Practice
Krishna Pillutla, Lang Liu, John Thickstun, Sean Welleck, Swabha Swayamdipta, Rowan Zellers, Sewoong Oh, Yejin Choi, Zaid Harchaoui
working paper

Near Optimal Private and Robust Linear Regression
Xiyang Liu, Prateek Jain, Weihao Kong, Sewoong Oh, Arun Sai Suggala
working paper,

Machine Learning-Aided Efficient Decoding of Reed-Muller Subcodes
Mohammad Vahid Jamali, Xiyang Liu, Ashok Vardhan Makkuva, Hessam Mahdavifar, Sewoong Oh, Pramod Viswanath
working paper,

Stochastic optimization on matrices and a graphon McKean-Vlasov limit
Zaid Harchaoui, Sewoong Oh, Soumik Pal, Raghav Somani, Raghavendra Tripathi
working paper,

Gradient flows on graphons: existence, convergence, continuity equations
Sewoong Oh, Soumik Pal, Raghav Somani, Raghavendra Tripathi
working paper,
- presented at the NeurIPS 2021 workshop on Optimal Transport and Machine Learning

Efficient Algorithms for Federated Saddle Point Optimization
Charlie Hou, Kiran K. Thekumparampil, Giulia Fanti, Sewoong Oh
working paper,

Towards a Defense against Backdoor Attacks in Continual Federated Learning
Shuaiqi Wang, Jonathan Hayase, Giulia Fanti, Sewoong Oh
working paper,

Few-shot Backdoor Attacks via Neural Tangent Kernels
Jonathan Hayase, Sewoong Oh
ICLR, 2023
- poster presented at NeurIPS 2022 workshop on Trustworthy and Socially Responsible Machine Learning (TSRML)

Zonotope Domains for Lagrangian Neural Network Verification
Matt Jordan, Jonathan Hayase, Alexandros G Dimakis, Sewoong Oh
NeurIPS 2022,

Quality Not Quantity: On the Interaction between Dataset Design and Robustness of CLIP
Thao Nguyen, Gabriel Ilharco, Mitchell Wortsman, Sewoong Oh, Ludwig Schmidt
NeurIPS 2022,
- presented at ICML 2022 workshop on Benchmarking Data for Data-Centric AI (DataPerf)

Bring Your Own Algorithm for Optimal Differentially Private Stochastic Minimax Optimization
Liang Zhang, Kiran Koshy Thekumparampil, Sewoong Oh, Niao He
NeurIPS 2022,

DP-PCA: Statistically Optimal and Differentially Private PCA
Xiyang Liu, Weihao Kong, Prateek Jain, Sewoong Oh
NeurIPS 2022,

MAML and ANIL Provably Learn Representations
Liam Collins, Aryan Mokhtari, Sewoong Oh, Sanjay Shakkottai
ICML, 2022
- video of a talk on Dec 2022 at C3 Digital Transformation Institute is available here
- slides from my talk at C3 Digital Transformation Institute is available here
- 5 minutes presentation by Liam Collins at ICML is available here

De novo mass spectrometry peptide sequencing with a transformer model
Melih Yilmaz, William E. Fondrie, Wout Bittremieux, Sewoong Oh, William Stafford Noble
ICML, 2022
- 5 minutes presentation by Melih Yilmaz at ICML is available here

Differential privacy and robust statistics in high dimensions
Xiyang Liu, Weihao Kong, Sewoong Oh
COLT, 2022
- Presented at the third AAAI Workshop on Privacy-Preserving Artificial Intelligence (PPAI-22), the recording of a 12 minute presentation is available here
- video of a talk on Nov 2021 at SNAPP seminar series is available here
- slides from my talk at SNAPP seminar is available here
- slides from my talk at Google is available here

Lifted Primal-Dual Method for Bilinearly Coupled Smooth Minimax Optimization
Kiran Koshy Thekumparampil, Niao He, Sewoong Oh
AISTATS, 2022 (Oral presentation)
- video of a presention on Feb 2022 at Simons institute by Niao He is here

Eliminating Sharp Minima from SGD with Truncated Heavy-tailed Noise
Xingyu Wang, Sewoong Oh, Chang-Han Rhee
ICLR, 2022
- presented at DeepMath 2021
- video of a talk Xingyu gave at DeepMath is available here
- slides from Xingyu's talk is available here
- video of a talk on Feb 2022 at SNAPP seminar series by Chang-han is here

FedChain: Chained Algorithms for Near-Optimal Communication Cost in Federated Learning
Charlie Hou, Kiran K. Thekumparampil, Giulia Fanti, Sewoong Oh
ICLR, 2022
- presented at the ICML 2021 Workshop on Federated Learning for User Privacy and Data Confidentiality (ICML-FL 2021)

Robust and Differentially Private Mean Estimation
Xiyang Liu, Weihao Kong, Sham Kakade, Sewoong Oh
NeurIPS 2021,
- presented at the ICML 2021 Workshop on Federated Learning for User Privacy and Data Confidentiality (ICML-FL 2021)
- presented at the CCS 2021 workshop Privacy Preserving Machine Learning (PPML’21)
- video of a talk on Oct 2021 at Simons Institute is available here
- slides from my talk is available here
- code is available here

Sample Efficient Linear Meta-Learning by Alternating Minimization
Kiran Koshy Thekumparampil, Prateek Jain, Praneeth Netrapalli, Sewoong Oh
NeurIPS, 2021

Divergence Frontiers for Generative Models: Sample Complexity, Quantization Level, and Frontier Integral
Lang Liu, Krishna Pillutla, Sean Welleck, Sewoong Oh, Yejin Choi, Zaid Harchaoui
NeurIPS, 2021

Gradient Inversion with Generative Image Prior
Jaechang Kim, Jinwoo Jeon, Kangwook Lee, Sewoong Oh, and Jungseul Ok,
NeurIPS, 2021
- presented at the ICML 2021 Workshop on Federated Learning for User Privacy and Data Confidentiality (ICML-FL 2021)

SPECTRE: Defending against backdoor attacks using robust covariance estimation
Jonathan Hayase, Weihao Kong, Raghav Somani, Sewoong Oh
ICML, 2021
- you can find the code for SPECTRE here.
- Backdoor-Suite: a user-friendly repository for backdoor attacks and defenses is available here

KO codes: Inventing Nonlinear Encoding and Decoding for Reliable WirelessCommunication via Deep-Learning
Ashok Vardhan Makkuva, Xiyang Liu, Mohammad Vahid Jamali, Hessam Mahdavifar, Sewoong Oh, Pramod Viswanath
ICML, 2021
- slides from a talk by Ashok is available here: 5 min and 1 hour

Reed-Muller Subcodes: Machine Learning-Aided Design of Efficient Soft Recursive Decoding
Mohammad Vahid Jamali, Xiyang Liu, Ashok Vardhan Makkuva, Hessam Mahdavifar, Sewoong Oh, Pramod Viswanath
ISIT, 2021

Projection Efficient Subgradient Method and Optimal Nonsmooth Frank-Wolfe Method
Kiran Koshy Thekumparampil, Prateek Jain, Praneeth Netrapalli, Sewoong Oh
NeurIPS, 2020 (Spotlight presentation)

Robust Meta-learning for Mixed Linear Regression with Small Batches
Weihao Kong, Raghav Somani, Sham Kakade, Sewoong Oh
NeurIPS, 2020
- you can find the code for Robust PCA here.

Optimal transport mapping via input convex neural networks
Ashok Vardhan Makkuva, Amirhossein Taghvaei, Sewoong Oh, Jason D. Lee
ICML, 2020

Meta-learning for mixed linear regression
Weihao Kong, Raghav Somani, Zhao Song, Sham Kakade, Sewoong Oh
ICML, 2020

InfoGAN-CR and ModelCentrality: Self-supervised Model Training and Selection for Disentangling GANs
Zinan Lin, Kiran Koshy Thekumparampil, Giulia Fanti, Sewoong Oh
ICML, 2020

Learning in Gated Neural Networks
Ashok Vardhan Makkuva, Sewoong Oh, Sreeram Kannan, and Pramod Viswanath
AISTATS, 2020

Turbo Autoencoder: Deep learning based channel code for point-to-point communication channels
Yihan Jiang, Hyeji Kim, Himanshu Asnani, Sreeram Kannan, Sewoong Oh, Pramod Viswanath
NeurIPS, 2019

Efficient Algorithms for Smooth Minimax Optimization
Kiran Koshy Thekumparampil, Prateek Jain, Praneeth Netrapalli, Sewoong Oh
NeurIPS, 2019
- you can find the code for DIAG here

Minimax Rates of Estimating Approximate Differential Privacy
Xiyang Liu, Sewoong Oh
NeurIPS, 2019

Rate Distortion For Model Compression:From Theory To Practice
Weihao Gao, Yu-Han Liu, Chong Wang, Sewoong Oh
ICML, 2019

Breaking the gridlock in Mixture-of-Experts: Consistent and Efficient Algorithms
Ashok Vardhan Makkuva, Sewoong Oh, Sreeram Kannan, and Pramod Viswanath
ICML, 2019

DeepTurbo: Deep Turbo Decoder
Yihan Jiang, Hyeji Kim, Himanshu Asnani, Sreeram Kannan, Sewoong Oh, and Pramod Viswanath
2019 IEEE 20th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), 2019

Barracuda: The Power of l-polling in Proof-of-Stake Blockchains
G Fanti, J Jiao, A Makkuva, S Oh, R Rana, and P Viswanath
ACM MobiHoc, 2019, (Best paper award)

LEARN Codes: Inventing Low-latency Codes via Recurrent Neural Networks: Yihan Jiang, Hyeji Kim, Himanshu Asnani, Sreeram Kannan, Sewoong Oh, and Pramod Viswanath
IEEE International Conference on Communications (ICC), 2019

Learning One-hidden-layer Neural Networks under General Input Distributions: Weihao Gao, Ashok Vardhan Makkuva, Sewoong Oh, and Pramod Viswanath
AISTATS, 2019

Iterative Bayesian Learning for Crowdsourced Regression: Jungseul Ok, Yunhun Jang, Sewoong Oh, Jinwoo Shin, Yung Yi
AISTATS, 2019, [ code ]

Compounding of Wealth in Proof-of-Stake Cryptocurrencies: Giulia Fanti, Leonid Kogan, Sewoong Oh, Kathleen Ruan, Pramod Viswanath, and Gerui Wang
Financial Cryptography and Data Security, 2019

Robustness of conditional GANs to noisy labels: Kiran Thekumparampil, Ashish Khetan, Zinan Lin, Sewoong Oh
NIPS, 2018 (Spotlight presentation), [ code ]

Deepcode: Feedback Codes via Deep Learning: Hyeji Kim, Yihan Jiang, Sreeram Kannan, Sewoong Oh, Pramod Viswanath
NIPS, 2018, [ code by Hyeji Kim ], [ code by Yihan Jiang ]

PacGAN: The power of two samples in generative adversarial networks: Zinan Lin, Ashish Khetan, Giulia Fanti, Sewoong Oh
NIPS, 2018, [ code ], [ project page]

Communication Algorithms via Deep Learning: H. Kim, Y. Jiang, R. B. Rana, S. Kannan, S. Oh, and P. Viswanath
ICLR, 2018

Estimating Mutual Information for Discrete-Continuous Mixtures: Weihao Gao, Sreeram Kannan, Sewoong Oh, and Pramod Viswanath
NIPS, 2017 (Spotlight presentation) [ code ]

Discovering Potential Correlations via Hypercontractivity: Hyeji Kim, Weihao Gao, Sreeram Kannan, Sewoong Oh, and Pramod Viswanath
NIPS, 2017 [ code ]

Matrix Norm Estimation from a Few Entries: Ashish Khetan, Sewoong Oh
NIPS, 2017, (Spotlight presentation) [ code ]

Top-K Ranking from Pairwise Comparisons: When Spectral Ranking is Optimal: Minje Jang, Sunghyun Kim, Changho Suh, Sewoong Oh
NIPS, 2017

Density Functional Estimators with k-Nearest Neighbor Bandwidths: Weihao Gao, Sewoong Oh, Pramod Viswanath
ISIT, 2017

Demystifying Fixed k-Nearest Neighbor Information Estimators: Weihao Gao, Sewoong Oh, Pramod Viswanath
ISIT, 2017, [ code ]

Achieving budget-optimality with adaptive schemes in crowdsourcing: Ashish Khetan, Sewoong Oh
NIPS, 2016

Computational and Statistical Tradeoffs in Learning to Rank: Ashish Khetan, Sewoong Oh
NIPS, 2016

Breaking the Bandwidth Barrier: Geometrical Adaptive Entropy Estimation: Weihao Gao, Sewoong Oh, Pramod Viswanath
NIPS, 2016, [ code ]

Conditional Dependence via Shannon Capacity: Axioms, Estimators and Applications: Weihao Gao, Sreeram Kannan, Sewoong Oh, Pramod Viswanath
ICML, 2016, [ code ]

Data-driven Rank Breaking for Efficient Rank Aggregation: Ashish Khetan, Sewoong Oh
ICML, 2016

Optimality of Belief Propagation for Crowdsourced Classification: Jungseul Ok, Sewoong Oh, Jinwoo Shin, Yung Yi
ICML, 2016

Metadata-conscious Anonymous Messaging: Giulia Fanti, Peter Kairouz, Sewoong Oh, Kannan Ramchandran and Pramod Viswanath
ICML 2016

Rumor Source Obfuscation on Irregular Trees: Giulia Fanti, Peter Kairouz, Sewoong Oh, Kannan Ramchandran and Pramod Viswanath
SIGMETRICS 2016

Collaboratively Learning Preferences from Ordinal Data: Sewoong Oh, Kiran K. Thekumparampil, and Jiaming Xu
NIPS 2015

Detecting Sponsored Recommendations: Subhashini Krishnasamy, Rajat Sen, Sewoong Oh, and Sanjay Shakkottai
SIGMETRICS (short paper) 2015

Spy vs. Spy: Rumor Source Obfuscation: Giulia Fanti, Peter Kairouz, Sewoong Oh, and Pramod Viswanath
SIGMETRICS 2015 (Best paper award)

Secure Multi-party Differential Privacy: Peter Kairouz, Sewoong Oh, and Pramod Viswanath
NIPS 2015

Extremal Mechanisms for Local Differential Privacy: Peter Kairouz, Sewoong Oh, and Pramod Viswanath
NIPS 2014

Provable Tensor Factorization with Missing Data: Prateek Jain and Sewoong Oh
NIPS 2014, [code]

Minimax-optimal Inference from Partial Rankings: Bruce Hajek, Sewoong Oh, and Jiaming Xu
NIPS 2014

Learning Mixed Multinomial Logit Model from Ordinal Data: Sewoong Oh and Devavrat Shah
NIPS 2014

Learning Mixtures of Discrete Product Distributions using Spectral Decompositions: Prateek Jain and Sewoong Oh
COLT 2014

The Composition Theorem for Differential Privacy: Peter Kairouz, Sewoong Oh and Pramod Viswanath
ICML 2015

What's your choice? Learning the mixed multi-nomial logit model: Ammar Ammar, Sewoong Oh, Devavrat Shah, and Luis-Filipe Voloch
SIGMETRICS (short paper) 2014

Efficient Crowdsourcing for Multi-class Labeling: David Karger, Sewoong Oh, and Devavrat Shah
SIGMETRICS 2013

Iterative Ranking from Pairwise Comparisons: Sahand Negahban, Sewoong Oh, and Devavrat Shah
NIPS 2012, (Spotlight presentation)

Iterative Learning for Reliable Crowdsourcing Systems: David R. Karger, Sewoong Oh, and Devavrat Shah
NIPS 2011, (Oral presentation)

Budget-optimal Crowdsourcing using Low-rank Matrix Approximations: David R. Karger, Sewoong Oh, and Devavrat Shah
Allerton 2011

Gossip PCA: Satish Babu Korada, Andrea Montanari, and Sewoong Oh
ACM SIGMETRICS 2011

On Positioning via Distributed Matrix Completion: A. Montanari and S. Oh
Sensor Array and Multichannel Signal Processing Workshop 2010

Ultrasound Tomography Calibration using Structured Matrix Completion: Reza Parhizkar, Amin Karbasi, Sewoong Oh, and Martin Vetterli
The 20th International Congress on Acoustics, 2010

Distributed Sensor Network Localization from Local Connectivity: Performance Analysis for the HOP-TERRAIN Algorithm: Amin Karbasi and Sewoong Oh
ACM SIGMETRICS 2010, (Kenneth C. Sevcik Outstanding Student Paper Award)

Sensor Network Localization from Local Connectivity: Performance Analysis for the MDS-MAP Algorithm: Sewoong Oh, Amin Karbasi, and Andrea Montanari
Information Theory Workshop 2010

OptSpace: A Gradient Descent Algorithm on Grassmann Manifold for Matrix Completion: Raghunandan Keshavan and Sewoong Oh
Technical report

Low-rank Matrix Completion with Noisy Observations: a Quantitative Comparison: Raghunandan Keshavan, Andrea Montanari, and Sewoong Oh
Allerton 2009

Matrix Completion from Noisy Entries: Raghunandan Keshavan, Andrea Montanari, and Sewoong Oh
NIPS 2009

Matrix Completion from a Few Entries: Raghunandan Keshavan, Andrea Montanari, and Sewoong Oh
ISIT 2009

Generating Random Tanner-graphs with Large Girth: Mohsen Bayati, Raghunandan H. Keshavan, Andrea montanari, Sewoong Oh, and Amin Saberi
Information Theory Workshop 2009, [ code ]

Learning low rank matrices from O(n) entries: Raghunandan Keshavan, Andrea Montanari, and Sewoong Oh
Allerton 2008

Computing the threshold shift for general channels: Jeremie Ezri, Andrea Montanari, Sewoong Oh, and Ruediger Urbanke
ISIT 2008

The Slope Scaling Parameter for General Channels, Decoders and Ensembles: Jeremie Ezri, Andrea Montanari, Sewoong Oh, and Ruediger Urbanke
ISIT 2008

Journal papers

Physical Layer Communication via Deep Learning: Hyeji Kim, Sewoong Oh, Pramod Viswanath
IEEE Transactions on Selected Areas in Information Theory (JSAIT), Vol.1, no.1, pp.5-18, 2020,

LEARN Codes: Inventing Low-latency Codes via Recurrent Neural Networks: Yihan Jiang, Hyeji Kim, Himanshu Asnani, Sreeram Kannan, Sewoong Oh, and Pramod Viswanath
IEEE Transactions on Selected Areas in Information Theory (JSAIT), Vol.1, no.1, pp.207-216, 2020,

PacGAN: The power of two samples in generative adversarial networks: Zinan Lin, Ashish Khetan, Giulia Fanti, Sewoong Oh
IEEE Transactions on Selected Areas in Information Theory (JSAIT), 2 Vol.1, no.1, pp.324-335, 2020, [ code ], [ project page]

Deepcode: Feedback Codes via Deep Learning: Hyeji Kim, Yihan Jiang, Sreeram Kannan, Sewoong Oh, Pramod Viswanath
IEEE Transactions on Selected Areas in Information Theory (JSAIT), Vol.1, no.1, pp.194-206, 2020, [ code by Hyeji Kim ], [ code by Yihan Jiang ]

Spectrum Estimation from a Few Entries: Ashish Khetan, Sewoong Oh
Journal of Machine Learning Research, Vol.20, Issue:21, January 2019

Learning from Comparisons and Choices: Sahand Negahban, Sewoong Oh, Kiran Thekumparampil, and Jiaming Xu,
Journal of Machine Learning Research, Vol.19, Issue:40, pp.1-95, September 2018

Generalized Rank-breaking: Computational and Statistical Tradeoffs: Ashish Khetan, Sewoong Oh
Journal of Machine Learning Research, Vol.19, Issue:28, pp.1-42, September 2018 [bibtex]

Optimality of Belief Propagation for Crowdsourced Classification: Jungseul Ok, Sewoong Oh, Jinwoo Shin, Yung Yi
IEEE Transactions on Information Theory, Vol.64, Issue:9, pp.6127-6138, September 2018,

Demystifying Fixed k-Nearest Neighbor Information Estimators: Weihao Gao, Sewoong Oh, Pramod Viswanath
IEEE Transactions on Information Theory, Vol.64, Issue:8, pp.5629-5661 February 2018, [bibtex]

Breaking the Bandwidth Barrier: Geometrical Adaptive Entropy Estimation: Weihao Gao, Sewoong Oh, Pramod Viswanath
IEEE Transactions on Information Theory, Vol.64, Issue:5, pp.3313-3330, May 2018, [bibtex]

Discovering Potential Correlations via Hypercontractivity: Hyeji Kim, Weihao Gao, Sreeram Kannan, Sewoong Oh, and Pramod Viswanath
Entropy, Vol.19, Issue:11, pp.586, October 2017, [ code ], [bibtex]

Data-driven Rank Breaking for Efficient Rank Aggregation: Ashish Khetan, Sewoong Oh
Journal of Machine Learning Research, Vol.17, no.193, pp.1-54, October 2016 [bibtex]

Hiding the Rumor Source: Giulia Fanti, Peter Kairouz, Sewoong Oh, Kannan Ramchandran, and Pramod Viswanath
IEEE Transactions on Information Theory, Vol.63, Issue:10, pp.6679-6713, October 2017 [bibtex]

Metadata-conscious Anonymous Messaging: Giulia Fanti, Peter Kairouz, Sewoong Oh, Kannan Ramchandran, and Pramod Viswanath
IEEE Transactions on Signal and Information Processing over Networks, Volume: 2, Issue: 4, pp.582 - 594, December 2016

Detecting Sponsored Recommendations: Subhashini Krishnasamy, Rajat Sen, Sewoong Oh, and Sanjay Shakkottai
ACM Transactions on Modeling and Performance Evaluation of Computing Systems, Volume 2, Issue 1, pp.6:1–6:29, November 2016

The Composition Theorem for Differential Privacy: Peter Kairouz, Sewoong Oh and Pramod Viswanath
IEEE Transaction on Information Theory, Volume 63, Issue 6, pp.4037-4049, June 2017 [bibtex]

Extremal Mechanisms for Local Differential Privacy: Peter Kairouz, Sewoong Oh, and Pramod Viswanath
Journal of Machine Learning Research, Volume 17, no.17, pp.1-51, April 2016 [bibtex]

RankCentrality: Ranking from Pair-wise Comparisons: Sahand Negahban, Sewoong Oh, and Devavrat Shah
Operations Research, Vol.65, no.1, pp.266-287, October 2016 [bibtex]

The Staircase Mechanisms in Differential Privacy: Q. Geng, P. Kairouz, S. Oh, and P. Viswanath
Selected Topics in Signal Processing, April 2015

Budget-optimal Task Allocation for Reliable Crowdsourcing Systems: David R. Karger, Sewoong Oh and Devavrat Shah
Operations Research, Volume 62 Issue 1, pp.1-24, January-February 2014 [bibtex]

Robust Localization from Incomplete Local Information: Amin Karbasi and Sewoong Oh
IEEE Transactions on Networking, Vol 21, pp.1131-1144, August 2013, [bibtex]

Calibration using Matrix Completion with Application to Ultrasound Tomography: Reza Parhizkar, Amin Karbai, Sewoong Oh and Martin Vetterli
IEEE Transactions on Signal Processing, Vol 61, pp.4923-4933, October 2013, [bibtex]

Counting with the Crowd: Adam Marcus, David Karger, Samuel Madden, Robert Miller, Sewoong Oh
Journal of the VLDB Endowment, Vol. 6, issue 2, pp.109-120, December 2012, [bibtex]

Matrix Completion from Noisy Entries: Raghunandan Keshavan, Andrea Montanari and Sewoong Oh
Journal of Machine Learning Research, vol. 11, pp.2057-2078, July 2010, [ bibtex , code ]

Matrix Completion from a Few Entries: Raghunandan Keshavan, Andrea Montanari and Sewoong Oh
IEEE Transactions on Information Theory,vol. 56,no. 6, pp.2980-2998, June 2010, [ bibtex , code ]

Dissertation

Matrix Completion: Fundamental Limits and Efficient Algorithms: Ph.D. Dissertation, Stanford Univesiry, December 2010