Om Thakkar

According to our database, Om Thakkar authored at least 30 papers between 2015 and 2024.

Collaborative distances:

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

2024

Differentially Private Parameter-Efficient Fine-tuning for Large ASR Models.

Hongbin Liu, Lun Wang, Om Thakkar, Abhradeep Thakurta, Arun Narayanan

CoRR, 2024

Training Large ASR Encoders with Differential Privacy.

Geeticka Chauhan, Steve Chien, Om Thakkar, Abhradeep Thakurta, Arun Narayanan

CoRR, 2024

Efficiently Train ASR Models that Memorize Less and Perform Better with Per-core Clipping.

Lun Wang, Om Thakkar, Zhong Meng, Nicole Rafidi, Rohit Prabhavalkar, Arun Narayanan

CoRR, 2024

Unintended Memorization in Large ASR Models, and How to Mitigate It.

Lun Wang, Om Thakkar, Rajiv Mathews

Proceedings of the IEEE International Conference on Acoustics, 2024

Noise Masking Attacks and Defenses for Pretrained Speech Models.

Matthew Jagielski, Om Thakkar, Lun Wang

Proceedings of the IEEE International Conference on Acoustics, 2024

2023

Why Is Public Pretraining Necessary for Private Model Training?

Arun Ganesh, Mahdi Haghifam, Milad Nasr, Sewoong Oh, Thomas Steinke, Om Thakkar, Abhradeep Guha Thakurta, Lun Wang

Proceedings of the International Conference on Machine Learning, 2023

Measuring Forgetting of Memorized Training Examples.

Matthew Jagielski, Om Thakkar, Florian Tramèr, Daphne Ippolito, Katherine Lee, Nicholas Carlini, Eric Wallace, Shuang Song, Abhradeep Guha Thakurta, Nicolas Papernot, Chiyuan Zhang

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

Recycling Scraps: Improving Private Learning by Leveraging Intermediate Checkpoints.

Virat Shejwalkar, Arun Ganesh, Rajiv Mathews, Om Thakkar, Abhradeep Thakurta

CoRR, 2022

Detecting Unintended Memorization in Language-Model-Fused ASR.

W. Ronny Huang, Steve Chien, Om Dipakbhai Thakkar, Rajiv Mathews

Proceedings of the 23rd Annual Conference of the International Speech Communication Association, 2022

Extracting Targeted Training Data from ASR Models, and How to Mitigate It.

Ehsan Amid, Om Dipakbhai Thakkar, Arun Narayanan, Rajiv Mathews, Françoise Beaufays

Proceedings of the 23rd Annual Conference of the International Speech Communication Association, 2022

Public Data-Assisted Mirror Descent for Private Model Training.

Ehsan Amid, Arun Ganesh, Rajiv Mathews, Swaroop Ramaswamy, Shuang Song, Thomas Steinke, Vinith M. Suriyakumar, Om Thakkar, Abhradeep Thakurta

Proceedings of the International Conference on Machine Learning, 2022

A Method to Reveal Speaker Identity in Distributed ASR Training, and How to Counter IT.

Trung Dang, Om Thakkar, Swaroop Ramaswamy, Rajiv Mathews, Peter Chin, Françoise Beaufays

Proceedings of the IEEE International Conference on Acoustics, 2022

The Role of Adaptive Optimizers for Honest Private Hyperparameter Selection.

Shubhankar Mohapatra, Sajin Sasy, Xi He, Gautam Kamath, Om Thakkar

Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

2021

Revealing and Protecting Labels in Distributed Training.

Trung Dang, Om Thakkar, Swaroop Ramaswamy, Rajiv Mathews, Peter Chin, Françoise Beaufays

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Differentially Private Learning with Adaptive Clipping.

Galen Andrew, Om Thakkar, Brendan McMahan, Swaroop Ramaswamy

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Practical and Private (Deep) Learning Without Sampling or Shuffling.

Peter Kairouz, Brendan McMahan, Shuang Song, Om Thakkar, Abhradeep Thakurta, Zheng Xu

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

Evading the Curse of Dimensionality in Unconstrained Private GLMs.

Shuang Song, Thomas Steinke, Om Thakkar, Abhradeep Thakurta

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020

Training Production Language Models without Memorizing User Data.

Swaroop Ramaswamy, Om Thakkar, Rajiv Mathews, Galen Andrew, H. Brendan McMahan, Françoise Beaufays

CoRR, 2020

Understanding Unintended Memorization in Federated Learning.

Om Thakkar, Swaroop Ramaswamy, Rajiv Mathews, Françoise Beaufays

CoRR, 2020

Characterizing Private Clipped Gradient Descent on Convex Generalized Linear Problems.

Shuang Song, Om Thakkar, Abhradeep Thakurta

CoRR, 2020

Privacy Amplification via Random Check-Ins.

Borja Balle, Peter Kairouz, Brendan McMahan, Om Dipakbhai Thakkar, Abhradeep Thakurta

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Guaranteed Validity for Empirical Approaches to Adaptive Data Analysis.

Ryan Rogers, Aaron Roth, Adam D. Smith, Nathan Srebro, Om Thakkar, Blake E. Woodworth

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

2019

Advances in privacy-preserving machine learning

Om Dipakbhai Thakkar

PhD thesis, 2019

Differentially Private Learning with Adaptive Clipping.

Om Thakkar, Galen Andrew, H. Brendan McMahan

CoRR, 2019

Towards Practical Differentially Private Convex Optimization.

Roger Iyengar, Joseph P. Near, Dawn Song, Om Thakkar, Abhradeep Thakurta, Lun Wang

Proceedings of the 2019 IEEE Symposium on Security and Privacy, 2019

2018

Model-Agnostic Private Learning via Stability.

Raef Bassily, Om Thakkar, Abhradeep Thakurta

CoRR, 2018

Model-Agnostic Private Learning.

Raef Bassily, Abhradeep Guha Thakurta, Om Dipakbhai Thakkar

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Differentially Private Matrix Completion Revisited.

Prateek Jain, Om Dipakbhai Thakkar, Abhradeep Thakurta

Proceedings of the 35th International Conference on Machine Learning, 2018

2016

Max-Information, Differential Privacy, and Post-selection Hypothesis Testing.

Ryan M. Rogers, Aaron Roth, Adam D. Smith, Om Thakkar

Proceedings of the IEEE 57th Annual Symposium on Foundations of Computer Science, 2016

2015

Improved Upper Bounds on a'(G☐H).

Punit Mehta, Rahul Muthu, Gaurav Patel, Om Thakkar, Devanshi Vyas

CoRR, 2015