Badih Ghazi

Orcid: 0009-0004-1555-5321

Affiliations:
  • Google Research, Mountain View, CA, USA
  • Massachusetts Institute of Technology, Cambridge, MA, USA (PhD 2018)
  • American University of Beirut, Lebanon (former)


According to our database1, Badih Ghazi authored at least 74 papers between 2013 and 2024.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
Training Differentially Private Ad Prediction Models with Semi-Sensitive Features.
CoRR, 2024

2023
Summary Reports Optimization in the Privacy Sandbox Attribution Reporting API.
CoRR, 2023

Pure-DP Aggregation in the Shuffle Model: Error-Optimal and Communication-Efficient.
CoRR, 2023

Separating Computational and Statistical Differential Privacy (Under Plausible Assumptions).
CoRR, 2023

Differentially Private All-Pairs Shortest Path Distances: Improved Algorithms and Lower Bounds.
Proceedings of the 2023 ACM-SIAM Symposium on Discrete Algorithms, 2023

Differentially Private Data Release over Multiple Tables.
Proceedings of the 42nd ACM SIGMOD-SIGACT-SIGAI Symposium on Principles of Database Systems, 2023

Optimal Unbiased Randomizers for Regression with Label Differential Privacy.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

On Computing Pairwise Statistics with Local Differential Privacy.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

User-Level Differential Privacy With Few Examples Per User.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Sparsity-Preserving Differentially Private Training of Large Embedding Models.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

On Differentially Private Sampling from Gaussian and Product Distributions.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Privacy in Advertising: Analytics and Modeling.
Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2023

Private Counting of Distinct and k-Occurring Items in Time Windows.
Proceedings of the 14th Innovations in Theoretical Computer Science Conference, 2023

Algorithms with More Granular Differential Privacy Guarantees.
Proceedings of the 14th Innovations in Theoretical Computer Science Conference, 2023

On User-Level Private Convex Optimization.
Proceedings of the International Conference on Machine Learning, 2023

Regression with Label Differential Privacy.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

On Differentially Private Counting on Trees.
Proceedings of the 50th International Colloquium on Automata, Languages, and Programming, 2023

Towards Separating Computational and Statistical Differential Privacy.
Proceedings of the 64th IEEE Annual Symposium on Foundations of Computer Science, 2023

Ticketed Learning-Unlearning Schemes.
Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

Differentially Private Aggregation via Imperfect Shuffling.
Proceedings of the 4th Conference on Information-Theoretic Cryptography, 2023

Private Ad Modeling with DP-SGD.
Proceedings of the Workshop on Data Mining for Online Advertising (AdKDD 2023) co-located with the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2023), 2023

Optimizing Hierarchical Queries for the Attribution Reporting API.
Proceedings of the Workshop on Data Mining for Online Advertising (AdKDD 2023) co-located with the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2023), 2023

Differentially Private Heatmaps.
Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

2022
Private Aggregation of Trajectories.
Proc. Priv. Enhancing Technol., 2022

Multiparty Reach and Frequency Histogram: Private, Secure, and Practical.
Proc. Priv. Enhancing Technol., 2022

Connect the Dots: Tighter Discrete Approximations of Privacy Loss Distributions.
Proc. Priv. Enhancing Technol., 2022

Distributed, Private, Sparse Histograms in the Two-Server Model.
IACR Cryptol. ePrint Arch., 2022

Differentially Private All-Pairs Shortest Path Distances: Improved Algorithms and Lower Bounds.
CoRR, 2022

Private Isotonic Regression.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Anonymized Histograms in Intermediate Privacy Models.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Faster Privacy Accounting via Evolving Discretization.
Proceedings of the International Conference on Machine Learning, 2022

Large-Scale Differentially Private BERT.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2022, 2022

Private Rank Aggregation in Central and Local Models.
Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

2021
Advances and Open Problems in Federated Learning.
Found. Trends Mach. Learn., 2021

User-Level Private Learning via Correlated Sampling.
CoRR, 2021

Google COVID-19 Vaccination Search Insights: Anonymization Process Description.
CoRR, 2021

Sample-efficient proper PAC learning with approximate differential privacy.
Proceedings of the STOC '21: 53rd Annual ACM SIGACT Symposium on Theory of Computing, 2021

User-Level Differentially Private Learning via Correlated Sampling.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Deep Learning with Label Differential Privacy.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

On Distributed Differential Privacy and Counting Distinct Elements.
Proceedings of the 12th Innovations in Theoretical Computer Science Conference, 2021

Differentially Private Aggregation in the Shuffle Model: Almost Central Accuracy in Almost a Single Message.
Proceedings of the 38th International Conference on Machine Learning, 2021

Locally Private k-Means in One Round.
Proceedings of the 38th International Conference on Machine Learning, 2021

On the Power of Multiple Anonymous Messages: Frequency Estimation and Selection in the Shuffle Model of Differential Privacy.
Proceedings of the Advances in Cryptology - EUROCRYPT 2021, 2021

On Avoiding the Union Bound When Answering Multiple Differentially Private Queries.
Proceedings of the Conference on Learning Theory, 2021

Near-tight closure b ounds for the Littlestone and threshold dimensions.
Proceedings of the Algorithmic Learning Theory, 2021

Robust and Private Learning of Halfspaces.
Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020
Optimality of Correlated Sampling Strategies.
Theory Comput., 2020

Near-tight closure bounds for Littlestone and threshold dimensions.
CoRR, 2020

Differentially Private Clustering: Tight Approximation Ratios.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Private Counting from Anonymous Messages: Near-Optimal Accuracy with Vanishing Communication Overhead.
Proceedings of the 37th International Conference on Machine Learning, 2020

Pure Differentially Private Summation from Anonymous Messages.
Proceedings of the 1st Conference on Information-Theoretic Cryptography, 2020

Private Aggregation from Fewer Anonymous Messages.
Proceedings of the Advances in Cryptology - EUROCRYPT 2020, 2020

2019
On the Power of Multiple Anonymous Messages.
IACR Cryptol. ePrint Arch., 2019

Advances and Open Problems in Federated Learning.
CoRR, 2019

Private Heavy Hitters and Range Queries in the Shuffled Model.
CoRR, 2019

Scalable and Differentially Private Distributed Aggregation in the Shuffled Model.
CoRR, 2019

Recursive Sketches for Modular Deep Learning.
Proceedings of the 36th International Conference on Machine Learning, 2019

2018
Computational aspects of communication amid uncertainty.
PhD thesis, 2018

LP/SDP Hierarchy Lower Bounds for Decoding Random LDPC Codes.
IEEE Trans. Inf. Theory, 2018

Communication-Rounds Tradeoffs for Common Randomness and Secret Key Generation.
Electron. Colloquium Comput. Complex., 2018

Communication with Contextual Uncertainty.
Comput. Complex., 2018

2017
The Power of Shared Randomness in Uncertain Communication.
Electron. Colloquium Comput. Complex., 2017

Dimension Reduction for Polynomials over Gaussian Space and Applications.
Electron. Colloquium Comput. Complex., 2017

Resource-Efficient Common Randomness and Secret-Key Schemes.
Electron. Colloquium Comput. Complex., 2017

Compression in a Distributed Setting.
Proceedings of the 8th Innovations in Theoretical Computer Science Conference, 2017

On the Power of Learning from k-Wise Queries.
Proceedings of the 8th Innovations in Theoretical Computer Science Conference, 2017

2016
Decidability of Non-Interactive Simulation of Joint Distributions.
Electron. Colloquium Comput. Complex., 2016

NP-Hardness of Reed-Solomon Decoding, and the Prouhet-Tarry-Escott Problem.
Electron. Colloquium Comput. Complex., 2016

The Optimality of Correlated Sampling.
Electron. Colloquium Comput. Complex., 2016

2015
Communication Complexity of Permutation-Invariant Functions.
Electron. Colloquium Comput. Complex., 2015

On the NP-hardness of bounded distance decoding of Reed-Solomon codes.
Proceedings of the IEEE International Symposium on Information Theory, 2015

2014
Linear Programming Decoding of Spatially Coupled Codes.
IEEE Trans. Inf. Theory, 2014

The Information Complexity of Hamming Distance.
Proceedings of the Approximation, 2014

2013
Sample-optimal average-case sparse Fourier Transform in two dimensions.
Proceedings of the 51st Annual Allerton Conference on Communication, 2013


  Loading...