Badih Ghazi

ORCID

Publication Activity (10 Years)

Years Active: 2013-2024
Publications (10 Years): 133

Top Venues

CoRR

NeurIPS

Electron. Colloquium Comput. Complex.

SODA

Massachusetts Institute of Technology, Cambridge, USA (PHD)

Education History

Massachusetts Institute of Technology, Cambridge, USA

PHD

Publications

John Delaney, Badih Ghazi, Charlie Harrison, Christina Ilvento, Ravi Kumar, Pasin Manurangsi, Martin Pál, Karthik Prabhakar, Mariana Raykova
Differentially Private Ad Conversion Measurement. Proc. Priv. Enhancing Technol. 2024 (2) (2024)
Hidayet Aksu, Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Adam Sealfon, Avinash V. Varadarajan
Summary Reports Optimization in the Privacy Sandbox Attribution Reporting API. Proc. Priv. Enhancing Technol. 2024 (4) (2024)
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Raghu Meka, Chiyuan Zhang
On Convex Optimization with Semi-Sensitive Features. COLT (2024)
Lynn Chua, Badih Ghazi, Yangsibo Huang, Pritish Kamath, Daogao Liu, Pasin Manurangsi, Amer Sinha, Chiyuan Zhang
Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning. CoRR (2024)
Lynn Chua, Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Amer Sinha, Chiyuan Zhang
How Private is DP-SGD? CoRR (2024)
Badih Ghazi, Yangsibo Huang, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Chiyuan Zhang
LabelDP-Pro: Learning with Label Differential Privacy via Projections. ICLR (2024)
John Delaney, Badih Ghazi, Charlie Harrison, Christina Ilvento, Ravi Kumar, Pasin Manurangsi, Martin Pal, Karthik Prabhakar, Mariana Raykova
Differentially Private Ad Conversion Measurement. CoRR (2024)
Badih Ghazi, Ravi Kumar, Pasin Manurangsi
Privacy in Web Advertising: Analytics and Modeling. WWW (Companion Volume) (2024)
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Raghu Meka, Chiyuan Zhang
On Convex Optimization with Semi-Sensitive Features. CoRR (2024)
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Adam Sealfon
Individualized Privacy Accounting via Subsampling with Applications in Combinatorial Optimization. CoRR (2024)
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Adam Sealfon
On Computing Pairwise Statistics with Local Differential Privacy. CoRR (2024)
Lynn Chua, Qiliang Cui, Badih Ghazi, Charlie Harrison, Pritish Kamath, Walid Krichene, Ravi Kumar, Pasin Manurangsi, Krishna Giri Narra, Amer Sinha, Avinash V. Varadarajan, Chiyuan Zhang
Training Differentially Private Ad Prediction Models with Semi-Sensitive Features. CoRR (2024)
Lynn Chua, Badih Ghazi, Yangsibo Huang, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Amer Sinha, Chulin Xie, Chiyuan Zhang
Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models. CoRR (2024)
Badih Ghazi, Cristóbal Guzmán, Pritish Kamath, Ravi Kumar, Pasin Manurangsi
Differentially Private Optimization with Sparse Gradients. CoRR (2024)
Badih Ghazi, Ravi Kumar, Pasin Manurangsi
Pure-DP Aggregation in the Shuffle Model: Error-Optimal and Communication-Efficient. ITC (2024)
Badih Ghazi, Junfeng He, Kai Kohlhoff, Ravi Kumar, Pasin Manurangsi, Vidhya Navalpakkam, Nachiappan Valliappan
Differentially Private Heatmaps. AAAI (2023)
Badih Ghazi, Rahul Ilango, Pritish Kamath, Ravi Kumar, Pasin Manurangsi
Separating Computational and Statistical Differential Privacy (Under Plausible Assumptions). CoRR (2023)
Badih Ghazi, Xiao Hu, Ravi Kumar, Pasin Manurangsi
On Differentially Private Sampling from Gaussian and Product Distributions. CoRR (2023)
Badih Ghazi, Pritish Kamath, Ravi Kumar, Raghu Meka, Pasin Manurangsi, Chiyuan Zhang
On User-Level Private Convex Optimization. CoRR (2023)
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Ayush Sekhari, Chiyuan Zhang
Ticketed Learning-Unlearning Schemes. COLT (2023)
Ashwinkumar Badanidiyuru Varadaraja, Badih Ghazi, Pritish Kamath, Ravi Kumar, Ethan Leeman, Pasin Manurangsi, Avinash V. Varadarajan, Chiyuan Zhang
Optimal Unbiased Randomizers for Regression with Label Differential Privacy. NeurIPS (2023)
Carson Denison, Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Krishna Giri Narra, Amer Sinha, Avinash V. Varadarajan, Chiyuan Zhang
Private Ad Modeling with DP-SGD. AdKDD@KDD (2023)
Badih Ghazi, Xiao Hu, Ravi Kumar, Pasin Manurangsi
Differentially Private Data Release over Multiple Tables. PODS (2023)
Badih Ghazi, Pritish Kamath, Ravi Kumar, Ethan Leeman, Pasin Manurangsi, Avinash Varadarajan, Chiyuan Zhang
Regression with Label Differential Privacy. ICLR (2023)
Badih Ghazi, Ravi Kumar, Pasin Manurangsi
Privacy in Advertising: Analytics and Modeling. KDD (2023)
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Raghu Meka, Chiyuan Zhang
On User-Level Private Convex Optimization. ICML (2023)
Badih Ghazi, Rahul Ilango, Pritish Kamath, Ravi Kumar, Pasin Manurangsi
Towards Separating Computational and Statistical Differential Privacy. FOCS (2023)
Matthew Dawson, Badih Ghazi, Pritish Kamath, Kapil Kumar, Ravi Kumar, Bo Luan, Pasin Manurangsi, Nishanth Mundru, Harikesh Nair, Adam Sealfon, Shengyu Zhu
Optimizing Hierarchical Queries for the Attribution Reporting API. CoRR (2023)
Badih Ghazi, Yangsibo Huang, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Amer Sinha, Chiyuan Zhang
Sparsity-Preserving Differentially Private Training of Large Embedding Models. NeurIPS (2023)
Badih Ghazi, Ravi Kumar, Jelani Nelson, Pasin Manurangsi
Private Counting of Distinct and k-Occurring Items in Time Windows. ITCS (2023)
Matthew Dawson, Badih Ghazi, Pritish Kamath, Kapil Kumar, Ravi Kumar, Bo Luan, Pasin Manurangsi, Nishanth Mundru, Harikesh Nair, Adam Sealfon, Shengyu Zhu
Optimizing Hierarchical Queries for the Attribution Reporting API. AdKDD@KDD (2023)
Badih Ghazi, Ravi Kumar, Pasin Manurangsi, Jelani Nelson, Samson Zhou
Differentially Private Aggregation via Imperfect Shuffling. CoRR (2023)
Hidayet Aksu, Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Adam Sealfon, Avinash V. Varadarajan
Summary Reports Optimization in the Privacy Sandbox Attribution Reporting API. CoRR (2023)
Badih Ghazi, Ravi Kumar, Pasin Manurangsi
Pure-DP Aggregation in the Shuffle Model: Error-Optimal and Communication-Efficient. CoRR (2023)
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Raghu Meka, Chiyuan Zhang
User-Level Differential Privacy With Few Examples Per User. CoRR (2023)
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Kewen Wu
On Differentially Private Counting on Trees. ICALP (2023)
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Adam Sealfon
On Computing Pairwise Statistics with Local Differential Privacy. NeurIPS (2023)
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Ayush Sekhari, Chiyuan Zhang
Ticketed Learning-Unlearning Schemes. CoRR (2023)
Badih Ghazi, Ravi Kumar, Pasin Manurangsi, Jelani Nelson, Samson Zhou
Differentially Private Aggregation via Imperfect Shuffling. ITC (2023)
Justin Y. Chen, Badih Ghazi, Ravi Kumar, Pasin Manurangsi, Shyam Narayanan, Jelani Nelson, Yinzhan Xu
Differentially Private All-Pairs Shortest Path Distances: Improved Algorithms and Lower Bounds. SODA (2023)
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Raghu Meka, Chiyuan Zhang
User-Level Differential Privacy With Few Examples Per User. NeurIPS (2023)
Badih Ghazi, Xiao Hu, Ravi Kumar, Pasin Manurangsi
Differentially Private Data Release over Multiple Tables. CoRR (2023)
Badih Ghazi, Yangsibo Huang, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Amer Sinha, Chiyuan Zhang
Sparsity-Preserving Differentially Private Training of Large Embedding Models. CoRR (2023)
Badih Ghazi, Xiao Hu, Ravi Kumar, Pasin Manurangsi
On Differentially Private Sampling from Gaussian and Product Distributions. NeurIPS (2023)
Ashwinkumar Badanidiyuru, Badih Ghazi, Pritish Kamath, Ravi Kumar, Ethan Leeman, Pasin Manurangsi, Avinash V. Varadarajan, Chiyuan Zhang
Optimal Unbiased Randomizers for Regression with Label Differential Privacy. CoRR (2023)
Badih Ghazi, Ravi Kumar, Pasin Manurangsi, Thomas Steinke
Algorithms with More Granular Differential Privacy Guarantees. ITCS (2023)
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi
Faster Privacy Accounting via Evolving Discretization. ICML (2022)
Badih Ghazi, Ravi Kumar, Pasin Manurangsi, Jelani Nelson
Private Counting of Distinct and k-Occurring Items in Time Windows. CoRR (2022)
Badih Ghazi, Ravi Kumar, Pasin Manurangsi, Thomas Steinke
Algorithms with More Granular Differential Privacy Guarantees. CoRR (2022)
Vadym Doroshenko, Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi
Connect the Dots: Tighter Discrete Approximations of Privacy Loss Distributions. CoRR (2022)
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi
Anonymized Histograms in Intermediate Privacy Models. CoRR (2022)
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi
Faster Privacy Accounting via Evolving Discretization. CoRR (2022)
Daniel Alabi, Badih Ghazi, Ravi Kumar, Pasin Manurangsi
Private Rank Aggregation in Central and Local Models. AAAI (2022)
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Kewen Wu
On Differentially Private Counting on Trees. CoRR (2022)
Badih Ghazi, Neel Kamal, Ravi Kumar, Pasin Manurangsi, Annika Zhang
Private Aggregation of Trajectories. Proc. Priv. Enhancing Technol. 2022 (4) (2022)
Badih Ghazi, Ravi Kumar, Pasin Manurangsi, Jelani Nelson
Differentially Private All-Pairs Shortest Path Distances: Improved Algorithms and Lower Bounds. CoRR (2022)
Badih Ghazi, Ben Kreuter, Ravi Kumar, Pasin Manurangsi, Jiayu Peng, Evgeny Skvortsov, Yao Wang, Craig Wright
Multiparty Reach and Frequency Histogram: Private, Secure, and Practical. Proc. Priv. Enhancing Technol. 2022 (1) (2022)
Badih Ghazi, Pritish Kamath, Ravi Kumar, Ethan Leeman, Pasin Manurangsi, Avinash Varadarajan, Chiyuan Zhang
Regression with Label Differential Privacy. CoRR (2022)
James Bell, Adrià Gascón, Badih Ghazi, Ravi Kumar, Pasin Manurangsi, Mariana Raykova, Phillipp Schoppmann
Distributed, Private, Sparse Histograms in the Two-Server Model. IACR Cryptol. ePrint Arch. 2022 (2022)
Rohan Anil, Badih Ghazi, Vineet Gupta, Ravi Kumar, Pasin Manurangsi
Large-Scale Differentially Private BERT. EMNLP (Findings) (2022)
Badih Ghazi, Junfeng He, Kai Kohlhoff, Ravi Kumar, Pasin Manurangsi, Vidhya Navalpakkam, Nachiappan Valliappan
Differentially Private Heatmaps. CoRR (2022)
James Bell, Adrià Gascón, Badih Ghazi, Ravi Kumar, Pasin Manurangsi, Mariana Raykova, Phillipp Schoppmann
Distributed, Private, Sparse Histograms in the Two-Server Model. CCS (2022)
Vadym Doroshenko, Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi
Connect the Dots: Tighter Discrete Approximations of Privacy Loss Distributions. Proc. Priv. Enhancing Technol. 2022 (4) (2022)
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi
Private Isotonic Regression. NeurIPS (2022)
Carson Denison, Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Krishna Giri Narra, Amer Sinha, Avinash Varadarajan, Chiyuan Zhang
Private Ad Modeling with DP-SGD. CoRR (2022)
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi
Anonymized Histograms in Intermediate Privacy Models. NeurIPS (2022)
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi
Private Isotonic Regression. CoRR (2022)
Badih Ghazi, Ravi Kumar, Pasin Manurangsi, Rasmus Pagh, Amer Sinha
Differentially Private Aggregation in the Shuffle Model: Almost Central Accuracy in Almost a Single Message. ICML (2021)
Badih Ghazi, Ravi Kumar, Pasin Manurangsi, Thao Nguyen
Robust and Private Learning of Halfspaces. AISTATS (2021)
Badih Ghazi, Ravi Kumar, Pasin Manurangsi
User-Level Differentially Private Learning via Correlated Sampling. NeurIPS (2021)
Badih Ghazi, Ravi Kumar, Pasin Manurangsi
On Avoiding the Union Bound When Answering Multiple Differentially Private Queries. COLT (2021)
Badih Ghazi, Noah Golowich, Ravi Kumar, Pasin Manurangsi
Near-tight closure b ounds for the Littlestone and threshold dimensions. ALT (2021)
Badih Ghazi, Ravi Kumar, Pasin Manurangsi, Rasmus Pagh, Amer Sinha
Differentially Private Aggregation in the Shuffle Model: Almost Central Accuracy in Almost a Single Message. CoRR (2021)
Badih Ghazi, Noah Golowich, Ravi Kumar, Pasin Manurangsi, Chiyuan Zhang
On Deep Learning with Label Differential Privacy. CoRR (2021)
Lijie Chen, Badih Ghazi, Ravi Kumar, Pasin Manurangsi
On Distributed Differential Privacy and Counting Distinct Elements. ITCS (2021)
Shailesh Bavadekar, Adam Boulanger, John Davis, Damien Desfontaines, Evgeniy Gabrilovich, Krishna Gadepalli, Badih Ghazi, Tague Griffith, Jai Prakash Gupta, Chaitanya Kamath, Dennis Kraft, Ravi Kumar, Akim Kumok, Yael Mayer, Pasin Manurangsi, Arti Patankar, Irippuge Milinda Perera, Chris Scott, Tomer Shekel, Benjamin Miller, Karen Smith, Charlotte Stanton, Mimi Sun, Mark Young, Gregory Wellenius
Google COVID-19 Vaccination Search Insights: Anonymization Process Description. CoRR (2021)
Badih Ghazi, Ravi Kumar, Pasin Manurangsi
User-Level Private Learning via Correlated Sampling. CoRR (2021)
Badih Ghazi, Noah Golowich, Ravi Kumar, Rasmus Pagh, Ameya Velingker
On the Power of Multiple Anonymous Messages: Frequency Estimation and Selection in the Shuffle Model of Differential Privacy. EUROCRYPT (3) (2021)
Alisa Chang, Badih Ghazi, Ravi Kumar, Pasin Manurangsi
Locally Private k-Means in One Round. CoRR (2021)
Rohan Anil, Badih Ghazi, Vineet Gupta, Ravi Kumar, Pasin Manurangsi
Large-Scale Differentially Private BERT. CoRR (2021)
Badih Ghazi, Noah Golowich, Ravi Kumar, Pasin Manurangsi
Sample-efficient proper PAC learning with approximate differential privacy. STOC (2021)
Badih Ghazi, Noah Golowich, Ravi Kumar, Pasin Manurangsi, Chiyuan Zhang
Deep Learning with Label Differential Privacy. NeurIPS (2021)
Badih Ghazi, Ravi Kumar, Pasin Manurangsi, Rasmus Pagh
Private Counting from Anonymous Messages: Near-Optimal Accuracy with Vanishing Communication Overhead. CoRR (2021)
Alisa Chang, Badih Ghazi, Ravi Kumar, Pasin Manurangsi
Locally Private k-Means in One Round. ICML (2021)
Peter Kairouz, H. Brendan McMahan, Brendan Avent, Aurélien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, Kallista A. Bonawitz, Zachary Charles, Graham Cormode, Rachel Cummings, Rafael G. L. D'Oliveira, Hubert Eichner, Salim El Rouayheb, David Evans, Josh Gardner, Zachary Garrett, Adrià Gascón, Badih Ghazi, Phillip B. Gibbons, Marco Gruteser, Zaïd Harchaoui, Chaoyang He, Lie He, Zhouyuan Huo, Ben Hutchinson, Justin Hsu, Martin Jaggi, Tara Javidi, Gauri Joshi, Mikhail Khodak, Jakub Konecný, Aleksandra Korolova, Farinaz Koushanfar, Sanmi Koyejo, Tancrède Lepoint, Yang Liu, Prateek Mittal, Mehryar Mohri, Richard Nock, Ayfer Özgür, Rasmus Pagh, Hang Qi, Daniel Ramage, Ramesh Raskar, Mariana Raykova, Dawn Song, Weikang Song, Sebastian U. Stich, Ziteng Sun, Ananda Theertha Suresh, Florian Tramèr, Praneeth Vepakomma, Jianyu Wang, Li Xiong, Zheng Xu, Qiang Yang, Felix X. Yu, Han Yu, Sen Zhao
Advances and Open Problems in Federated Learning. Found. Trends Mach. Learn. 14 (1-2) (2021)
Daniel Alabi, Badih Ghazi, Ravi Kumar, Pasin Manurangsi
Private Rank Aggregation in Central and Local Models. CoRR (2021)
Badih Ghazi, Noah Golowich, Ravi Kumar, Pasin Manurangsi, Rasmus Pagh, Ameya Velingker
Pure Differentially Private Summation from Anonymous Messages. CoRR (2020)
Badih Ghazi, Ravi Kumar, Pasin Manurangsi
Differentially Private Clustering: Tight Approximation Ratios. CoRR (2020)
Badih Ghazi, Ravi Kumar, Pasin Manurangsi
Differentially Private Clustering: Tight Approximation Ratios. NeurIPS (2020)
Badih Ghazi, Noah Golowich, Ravi Kumar, Pasin Manurangsi
Near-tight closure bounds for Littlestone and threshold dimensions. CoRR (2020)
Badih Ghazi, Ravi Kumar, Pasin Manurangsi, Thao Nguyen
Robust and Private Learning of Halfspaces. CoRR (2020)
Badih Ghazi, Noah Golowich, Ravi Kumar, Pasin Manurangsi, Rasmus Pagh, Ameya Velingker
Pure Differentially Private Summation from Anonymous Messages. ITC (2020)
Badih Ghazi, Noah Golowich, Ravi Kumar, Pasin Manurangsi
Sample-efficient proper PAC learning with approximate differential privacy. CoRR (2020)
Lijie Chen, Badih Ghazi, Ravi Kumar, Pasin Manurangsi
On Distributed Differential Privacy and Counting Distinct Elements. CoRR (2020)
Mohammad Bavarian, Badih Ghazi, Elad Haramaty, Pritish Kamath, Ronald L. Rivest, Madhu Sudan
Optimality of Correlated Sampling Strategies. Theory Comput. 16 (2020)
Badih Ghazi, Pasin Manurangsi, Rasmus Pagh, Ameya Velingker
Private Aggregation from Fewer Anonymous Messages. EUROCRYPT (2) (2020)
Badih Ghazi, Ravi Kumar, Pasin Manurangsi, Rasmus Pagh
Private Counting from Anonymous Messages: Near-Optimal Accuracy with Vanishing Communication Overhead. ICML (2020)
Badih Ghazi, Ravi Kumar, Pasin Manurangsi
On Avoiding the Union Bound When Answering Multiple Differentially Private Queries. CoRR (2020)
Badih Ghazi, Rina Panigrahy, Joshua R. Wang
Recursive Sketches for Modular Deep Learning. ICML (2019)
Badih Ghazi, Rasmus Pagh, Ameya Velingker
Scalable and Differentially Private Distributed Aggregation in the Shuffled Model. CoRR (2019)

Badih Ghazi.css-eqlu8i{font-size:small;padding-left:4px;}

Publication Activity (10 Years)

Top Topics

Top Venues

Badih Ghazi