Amer Sinha

According to our database, Amer Sinha authored at least 13 papers between 2021 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2025

Scaling Laws for Differentially Private Language Models.

Ryan McKenna, Yangsibo Huang, Amer Sinha, Borja Balle, Zachary Charles, Christopher A. Choquette-Choo, Badih Ghazi, Georgios Kaissis, Ravi Kumar, Ruibo Liu, Da Yu, Chiyuan Zhang

CoRR, January, 2025

Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy.

Yangsibo Huang, Daogao Liu, Lynn Chua, Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Milad Nasr, Amer Sinha, Chiyuan Zhang

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Balls-and-Bins Sampling for DP-SGD.

Lynn Chua, Badih Ghazi, Charlie Harrison, Pritish Kamath, Ravi Kumar, Ethan Leeman, Pasin Manurangsi, Amer Sinha, Chiyuan Zhang

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2025

2024

Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models.

Lynn Chua, Badih Ghazi, Yangsibo Huang, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Amer Sinha, Chulin Xie, Chiyuan Zhang

CoRR, 2024

Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning.

Lynn Chua, Badih Ghazi, Yangsibo Huang, Pritish Kamath, Daogao Liu, Pasin Manurangsi, Amer Sinha, Chiyuan Zhang

CoRR, 2024

How Private is DP-SGD?

Lynn Chua, Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Amer Sinha, Chiyuan Zhang

CoRR, 2024

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

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

CoRR, 2024

Scalable DP-SGD: Shuffling vs. Poisson Subsampling.

Lynn Chua, Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Amer Sinha, Chiyuan Zhang

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

How Private are DP-SGD Implementations?

Lynn Chua, Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Amer Sinha, Chiyuan Zhang

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Training Differentially Private Ad Prediction Models With Semi-Sensitive Features.

Lynn Chua, Qiliang Cui, Badih Ghazi, Charlie Harrison, Pritish Kamath, Walid Krichene, Ravi Kumar, Pasin Manurangsi, Nicolas Mayoraz, Hema Venkata Krishna Giri Narra, Steffen Rendle, Amer Sinha, Avinash V. Varadarajan, Chiyuan Zhang

Proceedings of the Workshop on Data Mining for Online Advertising (AdKDD 2024) co-located with the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2024), 2024

2023

Sparsity-Preserving Differentially Private Training of Large Embedding Models.

Badih Ghazi, Yangsibo Huang, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Amer Sinha, Chiyuan Zhang

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Private Ad Modeling with DP-SGD.

Carson Denison, Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Krishna Giri Narra, Amer Sinha, Avinash V. Varadarajan, Chiyuan Zhang

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

2021

Differentially Private Aggregation in the Shuffle Model: Almost Central Accuracy in Almost a Single Message.

Badih Ghazi, Ravi Kumar, Pasin Manurangsi, Rasmus Pagh, Amer Sinha

Proceedings of the 38th International Conference on Machine Learning, 2021