Benign Overfitting for Regression with Trained Two-Layer ReLU Networks
With J. Park and P. Bloebaum
Beta-calibration of Language Model Confidence Scores for Generative QA
With P. Manggala, A. Mastakouri, E. Kirschbaum, and A. Ramdas
Anytime-Valid Inference for Double/Debiased Machine Learning of Causal Parameters
With A. Dalal, P. Bloebaum, and A. Ramdas
Differentially Private Conditional Independence Testing
With I. Kalemaj and A. Ramdas
In proceedings of AISTATS 2024
The PetShop Dataset — Finding Causes of Performance Issues across Microservices
With M. Hardt, W. Orchard, P. Bloebaum, and E. Kirschbaum
In proceedings of CLeaR 2024
Interventional and Counterfactual Inference with Diffusion Models
With P. Chao and P. Bloebaum
Debiasing Conditional Stochastic Optimization
With L. He
In proceedings of NeurIPS 2023
Thompson Sampling with Diffusion Generative Prior
With Y. Hsieh, B. Kveton, and P. Bloebaum
In proceedings of ICML 2023
Sequential Kernelized Independence Testing
With A. Podkopaev, P. Bloebaum, and A. Ramdas
In proceedings of ICML 2023
Uplifting Bandits
With Y. Hsieh and B. Kveton
In proceedings of NeurIPS 2022
On Measuring Causal Contributions via do-interventions
With Y. Jung, J. Tian, D. Janzing, P. Bloebaum, and E. Bareinboim
In proceedings of ICML 2022
Balancing Utility and Scalability in Metric Differential Privacy
With J. Imola, S. White, A. Aggarwal, and N. Teissier
In proceedings of UAI 2022
Reconstructing Test Labels from Noisy Loss Functions
With A. Aggarwal, Z. Xu, O. Feyisetan, and N. Teissier
In proceedings of AISTATS 2022
Collaborative Causal Discovery with Atomic Interventions
With R. Addanki
In proceedings of NeurIPS 2021
Label Inference Attacks from Log-loss Scores
With A. Aggarwal, Z. Xu, O. Feyisetan, and N. Teissier
In proceedings of ICML 2021 (selected for long oral presentation)
Federated Learning under Arbitrary Communication Patterns
With Dmitrii Avdyukhin
In proceedings of ICML 2021
SGD with Low-Dimensional Gradients with Applications to Private and Distributed Learning
In proceedings of UAI 2021
Private Release of Text Embedding Vectors
With O. Feyisetan
In proceedings of First Workshop on Trustworthy Natural Language Processing (part of ACL 2021)
Restricted Isometry Property under High Correlations
With M. Rudelson
Efficient Intervention Design for Causal Discovery with Latents
With R. Addanki, A. McGregor, and C. Musco
In proceedings of ICML 2020
Contextual Online False Discovery Rate Control
With S. Chen
In proceedings of AISTATS 2020
Subsampled Renyi Differential Privacy and Analytical Moments Accountant
With Y. Wang and B. Balle
In proceedings of AISTATS 2019 (selected for oral presentation)
Winner of Notable Paper Award at AISTATS 2019
Full version, In Journal of Privacy and Confidentiality, 2020
A preliminary version appeared at workshops: PPML 2018 and TPDP 2018 - Theory and Practice of Differential Privacy
Restricted Eigenvalue from Stable Rank with Applications to Sparse Linear Regression
With M. Rudelson
In proceedings of COLT 2018
Semi-Supervised Learning on Data Streams via Temporal Label Propagation
With T. Wagner, S. Guha, and N. Mishra
In proceedings of ICML 2018
Network Approximation using Tensor Sketching
With N. Narodytska and H. Jin
In proceedings of IJCAI 2018
Preliminary version appeared at the NIPS 2016 Workshop on Deep Learning: Bridging Theory and Practice
Full version of this paper can be found here
Verifying Properties of Binarized Deep Neural Networks
With N. Narodytska, L. Ryzhyk, M. Sagiv, and T. Walsh
In proceedings of AAAI 2018
Simple Black-Box Adversarial Attacks on Deep Neural Networks
With N. Narodytska
In proceedings of CVPR 2017 Workshops
Preliminary version appeared at the NIPS 2016 Workshop on Adversarial Training
Private Incremental Regression
With K. Nissim and H. Jin
In proceedings of PODS 2017
Efficient Private Empirical Risk Minimization for High-dimensional Learning
With H. Jin
In proceedings of ICML 2016
Streaming Anomaly Detection Using Randomized Matrix Sketching
With H. Huang
In proceedings of VLDB 2016
Streaming Spectral Clustering
With S. Yoo and H. Huang
In proceedings of ICDE 2016
Private Spatial Data Aggregation in the Local Setting
With R. Chen, H. Li, A.K. Win, and H. Jin
In proceedings of ICDE 2016
Invited to IEEE Transactions on Knowledge and Data Engineering (special issue)
Spectral Norm of Random Kernel Matrices with Applications to Privacy
With M. Rudelson
In proceedings of RANDOM 2015
Unsupervised Feature Selection on Data Streams
With H. Huang and S. Yoo
In proceedings of CIKM 2015
Online Dictionary Learning on Symmetric Positive Definite Manifolds with Vision Applications
With S. Zhang, P. Yuen, and M. Harandi
In proceedings of AAAI 2015
Associated code can be found here: here
On the Semantics of Differential Privacy: A 'Bayesian' Formulation
With A. Smith
In Journal of Privacy and Confidentiality, 2014
Earlier version: A Note on Differential Privacy: Defining Resistance to Arbitrary Side Information
Bounds on the Sample Complexity for Private Learning and Private Data Release
With A. Beimel, H. Brenner, and K. Nissim
In Machine Learning Journal, 2014
Earlier version appeared in proceedings of TCC 2010
The Power of Linear Reconstruction Attacks
With M. Rudelson and A. Smith
In proceedings of SODA 2013
Analyzing Graphs with Node Differential Privacy
With K. Nissim, S. Raskhodnikova, and A. Smith
In proceedings of TCC 2013
Full version of this paper can be found here
Fast Online L1-Dictionary Learning Algorithms For Novel Document Detection
In proceedings of ICASSP 2013 (Invited Presentation)
Special session on Sparse Signal Techniques for Web Information Processing
Novel Document Detection on Massive Data Streams using Distributed Dictionary Learning
With G. Cong, P. Melville, and R. Lawrence
In IBM Journal of Research and Development, 2013
Approximately Counting Embeddings into Random Graphs
With M. Furer
In Combinatorics, Probability & Computing, 2014 (special issue on Analysis of Algorithms)
Earlier version appeared in proceedings of RANDOM 2008
An Exponential Time 2-Approximation Algorithm for Bandwidth
With M. Furer and S. Gaspers
In Theoretical Computer Science, 2013 (special issue on Exact & Parameterized Computation)
Earlier version appeared in proceedings of IWPEC 2009
Online L1-Dictionary Learning with Application to Novel Document Detection
With H. Wang, A. Banerjee, and P. Melville
In proceedings of NIPS 2012
Full version of this paper can be found here
Preliminary version appeared at the KDD SOMA Workshop 2012
Efficient and Practical Stochastic Subgradient Descent for Nuclear Norm Regularization
With H. Avron, S. Kale, and V. Sindhwani
In proceedings of ICML 2012
Emerging Topic Detection Using Dictionary Learning
With P. Melville, A. Banerjee, and V. Sindhwani
In proceedings of CIKM 2011
Full version of this paper can be found here
Geography-Based Analysis of the Internet Infrastructure
With S. Eidenbenz and G. Yan
In proceedings of IEEE INFOCOM (mini-conference) 2011
Full version of this paper can be found here
The Rigidity Transition for Random Graphs
With C. Moore and L. Theran
In proceedings of SODA 2011
Efficient Placement of Directional Antennas in Infrastructure-based Wireless Networks
With F. Pan
In proceedings of MILCOM 2011
What Can We Learn Privately?
With H. K. Lee, K. Nissim, S. Raskhodnikova, and A. Smith
In SIAM Journal on Computing, 2011 (special issue for selected papers from FOCS 2008)
Earlier version appeared in proceedings of FOCS 2008
The Price of Privately Releasing Contingency Tables and the Spectra of Random Matrices with Correlated Rows
With M. Rudelson, A. Smith, and J. Ullman
In proceedings of ACM STOC 2010
Full version of this paper can be found here
Matrix Interdiction Problem
With F. Pan
In proceedings of CPAIOR 2010
Spatial Scattering for Load Balancing in Conservatively Synchronized Parallel Discrete-Event Simulations
With S. Thulasidasan, S. Eidenbenz, and P. Romero
In proceedings of ACM/IEEE/SCS PADS 2010
Bandwidth Provisioning in Infrastructure based Wireless Networks Employing Directional Antennas
With B. Zhao, B. Urgaonkar, and S. Vasudevan
In Pervasive and Mobile Computing, 2011 (special issue for selected papers from ICDCN 2010)
Earlier version appeared in proceedings of ICDCN 2010
Designing Systems for Large-Scale, Discrete-Event Simulations: Experiences with the FastTrans Microsimulator
With S. Thulasidasan, S. Eidenbenz, E. Galli, S. Mniszewski, and P. Romero
In proceedings of IEEE HIPC 2009
Composition Attacks and Auxiliary Information in Data Privacy
With S. R. Ganta and A. Smith
In proceedings of ACM SIGKDD 2008
Approximation Algorithms for Graph Problems (please email me for a copy)
Ph.D. Thesis, Penn State University, 2008
Packing to Angles and Sectors
With P. Berman, J. Jeong, and B. Urgaonkar
In proceedings of ACM SPAA 2007
Spanners for Geometric Intersection Graphs with Applications
With M. Furer
In Journal of Computational Geometry, 2012
Earlier version appeared in proceedings of WADS 2007
Faster Approximation of Distances in Graphs
With P. Berman
In proceedings of WADS 2007
Exact Max 2-SAT: Easier and Faster
With M. Furer
In proceedings of SOFSEM 2007
Winner of best paper award
Approximate Distance Queries in Disk Graphs
With M. Furer
In proceedings of WAOA 2006
Combinatorics of TCP Reordering
With A. Hansson and G. Istrate
In Journal of Combinatorial Optimization, 2006
Approximately Counting Perfect Matchings in General Graphs
With M. Furer
In proceedings of SIAM ALENEX/ANLACO 2005
Algorithms for Counting 2-SAT Solutions and Colorings with Applications
With M. Furer
In proceedings of AAIM 2007
Full version appeared as ECCC report TR05-033, 2005
An Almost Linear Time Approximation Algorithm for the Permanent of Random (0-1) Matrix
With M. Furer
In proceedings of FSTTCS 2004
Beta-calibration of Language Model Confidence Scores for Generative QA
Anytime-Valid Inference for Double/Debiased Machine Learning of Causal Parameters
Differentially Private Conditional Independence Testing
The PetShop Dataset — Finding Causes of Performance Issues across Microservices
Interventional and Counterfactual Inference with Diffusion Models
Debiasing Conditional Stochastic Optimization
Thompson Sampling with Diffusion Generative Prior
Sequential Kernelized Independence Testing
Uplifting Bandits
On Measuring Causal Contributions via do-interventions
Balancing Utility and Scalability in Metric Differential Privacy
Reconstructing Test Labels from Noisy Loss Functions
Collaborative Causal Discovery with Atomic Interventions
Label Inference Attacks from Log-loss Scores
Federated Learning under Arbitrary Communication Patterns
SGD with Low-Dimensional Gradients with Applications to Private and Distributed Learning
Private Release of Text Embedding Vectors
Restricted Isometry Property under High Correlations
Efficient Intervention Design for Causal Discovery with Latents
Contextual Online False Discovery Rate Control
Subsampled Renyi Differential Privacy and Analytical Moments Accountant
Restricted Eigenvalue from Stable Rank with Applications to Sparse Linear Regression
Semi-Supervised Learning on Data Streams via Temporal Label Propagation
Network Approximation using Tensor Sketching
Verifying Properties of Binarized Deep Neural Networks
Simple Black-Box Adversarial Attacks on Deep Neural Networks
Private Incremental Regression
Efficient Private Empirical Risk Minimization for High-dimensional Learning
Streaming Anomaly Detection Using Randomized Matrix Sketching
Streaming Spectral Clustering
Private Spatial Data Aggregation in the Local Setting
Spectral Norm of Random Kernel Matrices with Applications to Privacy
Unsupervised Feature Selection on Data Streams
Online Dictionary Learning on Symmetric Positive Definite Manifolds with Vision Applications
On the Semantics of Differential Privacy: A 'Bayesian' Formulation
Bounds on the Sample Complexity for Private Learning and Private Data Release
The Power of Linear Reconstruction Attacks
Analyzing Graphs with Node Differential Privacy
Fast Online L1-Dictionary Learning Algorithms For Novel Document Detection
Novel Document Detection on Massive Data Streams using Distributed Dictionary Learning
Approximately Counting Embeddings into Random Graphs
An Exponential Time 2-Approximation Algorithm for Bandwidth
Online L1-Dictionary Learning with Application to Novel Document Detection
Efficient and Practical Stochastic Subgradient Descent for Nuclear Norm Regularization
Emerging Topic Detection Using Dictionary Learning
Geography-Based Analysis of the Internet Infrastructure
The Rigidity Transition for Random Graphs
Efficient Placement of Directional Antennas in Infrastructure-based Wireless Networks
What Can We Learn Privately?
The Price of Privately Releasing Contingency Tables and the Spectra of Random Matrices with Correlated Rows
Matrix Interdiction Problem
Spatial Scattering for Load Balancing in Conservatively Synchronized Parallel Discrete-Event Simulations
Bandwidth Provisioning in Infrastructure based Wireless Networks Employing Directional Antennas
Designing Systems for Large-Scale, Discrete-Event Simulations: Experiences with the FastTrans Microsimulator
Composition Attacks and Auxiliary Information in Data Privacy
Approximation Algorithms for Graph Problems (please email me for a copy)
Packing to Angles and Sectors
Spanners for Geometric Intersection Graphs with Applications
Faster Approximation of Distances in Graphs
Exact Max 2-SAT: Easier and Faster
Approximate Distance Queries in Disk Graphs
Combinatorics of TCP Reordering
Approximately Counting Perfect Matchings in General Graphs
Algorithms for Counting 2-SAT Solutions and Colorings with Applications
An Almost Linear Time Approximation Algorithm for the Permanent of Random (0-1) Matrix