Om Thakkar

Publication Activity (10 Years)

Years Active: 2015-2024
Publications (10 Years): 36

Top Topics

Differentially Private

Generalized Linear

Handwritten Numeral Recognition

Training Examples

Top Venues

Publications

Matthew Jagielski, Om Thakkar, Lun Wang
Noise Masking Attacks and Defenses for Pretrained Speech Models. CoRR (2024)
Matthew Jagielski, Om Thakkar, Lun Wang
Noise Masking Attacks and Defenses for Pretrained Speech Models. ICASSP (2024)
Lun Wang, Om Thakkar, Zhong Meng, Nicole Rafidi, Rohit Prabhavalkar, Arun Narayanan
Efficiently Train ASR Models that Memorize Less and Perform Better with Per-core Clipping. CoRR (2024)
Lun Wang, Om Thakkar, Rajiv Mathews
Unintended Memorization in Large ASR Models, and How to Mitigate It. ICASSP (2024)
Arun Ganesh, Mahdi Haghifam, Milad Nasr, Sewoong Oh, Thomas Steinke, Om Thakkar, Abhradeep Guha Thakurta, Lun Wang
Why Is Public Pretraining Necessary for Private Model Training? ICML (2023)
Arun Ganesh, Mahdi Haghifam, Milad Nasr, Sewoong Oh, Thomas Steinke, Om Thakkar, Abhradeep Thakurta, Lun Wang
Why Is Public Pretraining Necessary for Private Model Training? CoRR (2023)
Lun Wang, Om Thakkar, Rajiv Mathews
Unintended Memorization in Large ASR Models, and How to Mitigate It. CoRR (2023)
Matthew Jagielski, Om Thakkar, Florian Tramèr, Daphne Ippolito, Katherine Lee, Nicholas Carlini, Eric Wallace, Shuang Song, Abhradeep Guha Thakurta, Nicolas Papernot, Chiyuan Zhang
Measuring Forgetting of Memorized Training Examples. ICLR (2023)
Virat Shejwalkar, Arun Ganesh, Rajiv Mathews, Om Thakkar, Abhradeep Thakurta
Recycling Scraps: Improving Private Learning by Leveraging Intermediate Checkpoints. CoRR (2022)
Matthew Jagielski, Om Thakkar, Florian Tramèr, Daphne Ippolito, Katherine Lee, Nicholas Carlini, Eric Wallace, Shuang Song, Abhradeep Thakurta, Nicolas Papernot, Chiyuan Zhang
Measuring Forgetting of Memorized Training Examples. CoRR (2022)
Ehsan Amid, Om Thakkar, Arun Narayanan, Rajiv Mathews, Françoise Beaufays
Extracting Targeted Training Data from ASR Models, and How to Mitigate It. CoRR (2022)
Trung Dang, Om Thakkar, Swaroop Ramaswamy, Rajiv Mathews, Peter Chin, Françoise Beaufays
A Method to Reveal Speaker Identity in Distributed ASR Training, and How to Counter IT. ICASSP (2022)
W. Ronny Huang, Steve Chien, Om Thakkar, Rajiv Mathews
Detecting Unintended Memorization in Language-Model-Fused ASR. CoRR (2022)
Ehsan Amid, Arun Ganesh, Rajiv Mathews, Swaroop Ramaswamy, Shuang Song, Thomas Steinke, Vinith M. Suriyakumar, Om Thakkar, Abhradeep Thakurta
Public Data-Assisted Mirror Descent for Private Model Training. ICML (2022)
Shubhankar Mohapatra, Sajin Sasy, Xi He, Gautam Kamath, Om Thakkar
The Role of Adaptive Optimizers for Honest Private Hyperparameter Selection. AAAI (2022)
Peter Kairouz, Brendan McMahan, Shuang Song, Om Thakkar, Abhradeep Thakurta, Zheng Xu
Practical and Private (Deep) Learning without Sampling or Shuffling. CoRR (2021)
Shuang Song, Thomas Steinke, Om Thakkar, Abhradeep Thakurta
Evading the Curse of Dimensionality in Unconstrained Private GLMs. AISTATS (2021)
Trung Dang, Om Thakkar, Swaroop Ramaswamy, Rajiv Mathews, Peter Chin, Françoise Beaufays
Revealing and Protecting Labels in Distributed Training. CoRR (2021)
Peter Kairouz, Brendan McMahan, Shuang Song, Om Thakkar, Abhradeep Thakurta, Zheng Xu
Practical and Private (Deep) Learning Without Sampling or Shuffling. ICML (2021)
Trung Dang, Om Thakkar, Swaroop Ramaswamy, Rajiv Mathews, Peter Chin, Françoise Beaufays
Revealing and Protecting Labels in Distributed Training. NeurIPS (2021)
Trung Dang, Om Thakkar, Swaroop Ramaswamy, Rajiv Mathews, Peter Chin, Françoise Beaufays
A Method to Reveal Speaker Identity in Distributed ASR Training, and How to Counter It. CoRR (2021)
Galen Andrew, Om Thakkar, Brendan McMahan, Swaroop Ramaswamy
Differentially Private Learning with Adaptive Clipping. NeurIPS (2021)
Shubhankar Mohapatra, Sajin Sasy, Xi He, Gautam Kamath, Om Thakkar
The Role of Adaptive Optimizers for Honest Private Hyperparameter Selection. CoRR (2021)
Ehsan Amid, Arun Ganesh, Rajiv Mathews, Swaroop Ramaswamy, Shuang Song, Thomas Steinke, Vinith M. Suriyakumar, Om Thakkar, Abhradeep Thakurta
Public Data-Assisted Mirror Descent for Private Model Training. CoRR (2021)
Borja Balle, Peter Kairouz, H. Brendan McMahan, Om Thakkar, Abhradeep Thakurta
Privacy Amplification via Random Check-Ins. CoRR (2020)
Shuang Song, Om Thakkar, Abhradeep Thakurta
Characterizing Private Clipped Gradient Descent on Convex Generalized Linear Problems. CoRR (2020)
Swaroop Ramaswamy, Om Thakkar, Rajiv Mathews, Galen Andrew, H. Brendan McMahan, Françoise Beaufays
Training Production Language Models without Memorizing User Data. CoRR (2020)
Om Thakkar, Swaroop Ramaswamy, Rajiv Mathews, Françoise Beaufays
Understanding Unintended Memorization in Federated Learning. CoRR (2020)
Ryan Rogers, Aaron Roth, Adam D. Smith, Nathan Srebro, Om Thakkar, Blake E. Woodworth
Guaranteed Validity for Empirical Approaches to Adaptive Data Analysis. AISTATS (2020)
Om Thakkar, Galen Andrew, H. Brendan McMahan
Differentially Private Learning with Adaptive Clipping. CoRR (2019)
Roger Iyengar, Joseph P. Near, Dawn Song, Om Thakkar, Abhradeep Thakurta, Lun Wang
Towards Practical Differentially Private Convex Optimization. IEEE Symposium on Security and Privacy (2019)
Ryan Rogers, Aaron Roth, Adam D. Smith, Nathan Srebro, Om Thakkar, Blake E. Woodworth
Guaranteed Validity for Empirical Approaches to Adaptive Data Analysis. CoRR (2019)
Raef Bassily, Om Thakkar, Abhradeep Thakurta
Model-Agnostic Private Learning via Stability. CoRR (2018)
Prateek Jain, Om Thakkar, Abhradeep Thakurta
Differentially Private Matrix Completion, Revisited. CoRR (2017)
Ryan M. Rogers, Aaron Roth, Adam D. Smith, Om Thakkar
Max-Information, Differential Privacy, and Post-Selection Hypothesis Testing. CoRR (2016)
Ryan M. Rogers, Aaron Roth, Adam D. Smith, Om Thakkar
Max-Information, Differential Privacy, and Post-selection Hypothesis Testing. FOCS (2016)
Punit Mehta, Rahul Muthu, Gaurav Patel, Om Thakkar, Devanshi Vyas
Improved Upper Bounds on $a'(G\Box H)$. CoRR (2015)