default search action
Abhradeep Thakurta
Abhradeep Guha Thakurta
Person information
- affiliation: Microsoft Research Silicon Valley
- affiliation: Pennsylvania State University, Computer Science and Engineering Department
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
- [j6]Bing Zhang, Vadym Doroshenko, Peter Kairouz, Thomas Steinke, Abhradeep Thakurta, Ziyin Ma, Eidan Cohen, Himani Apte, Jodi Spacek:
Differentially Private Stream Processing at Scale. Proc. VLDB Endow. 17(12): 4145-4158 (2024) - [c58]Soumyabrata Pal, Prateek Varshney, Gagan Madan, Prateek Jain, Abhradeep Thakurta, Gaurav Aggarwal, Pradeep Shenoy, Gaurav Srivastava:
Sample-Efficient Personalization: Modeling User Parameters as Low Rank Plus Sparse Components. AISTATS 2024: 1702-1710 - [c57]Walid Krichene, Nicolas Mayoraz, Steffen Rendle, Shuang Song, Abhradeep Thakurta, Li Zhang:
Private Learning with Public Features. AISTATS 2024: 4150-4158 - [c56]Christopher A. Choquette-Choo, Krishnamurthy Dj Dvijotham, Krishna Pillutla, Arun Ganesh, Thomas Steinke, Abhradeep Guha Thakurta:
Correlated Noise Provably Beats Independent Noise for Differentially Private Learning. ICLR 2024 - [c55]Christopher A. Choquette-Choo, Arun Ganesh, Thomas Steinke, Abhradeep Guha Thakurta:
Privacy Amplification for Matrix Mechanisms. ICLR 2024 - [c54]Gavin Brown, Krishnamurthy Dj Dvijotham, Georgina Evans, Daogao Liu, Adam Smith, Abhradeep Guha Thakurta:
Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimation. ICML 2024 - [c53]Naman Agarwal, Satyen Kale, Karan Singh, Abhradeep Guha Thakurta:
Improved Differentially Private and Lazy Online Convex Optimization: Lower Regret without Smoothness Requirements. ICML 2024 - [i60]Gavin Brown, Krishnamurthy Dvijotham, Georgina Evans, Daogao Liu, Adam Smith, Abhradeep Thakurta:
Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimation. CoRR abs/2402.13531 (2024) - [i59]Krishnamurthy Dvijotham, H. Brendan McMahan, Krishna Pillutla, Thomas Steinke, Abhradeep Thakurta:
Efficient and Near-Optimal Noise Generation for Streaming Differential Privacy. CoRR abs/2404.16706 (2024) - [i58]Christopher A. Choquette-Choo, Arun Ganesh, Abhradeep Thakurta:
Optimal Rates for DP-SCO with a Single Epoch and Large Batches. CoRR abs/2406.02716 (2024) - [i57]Geeticka Chauhan, Steve Chien, Om Thakkar, Abhradeep Thakurta, Arun Narayanan:
Training Large ASR Encoders with Differential Privacy. CoRR abs/2409.13953 (2024) - [i56]Hongbin Liu, Lun Wang, Om Thakkar, Abhradeep Thakurta, Arun Narayanan:
Differentially Private Parameter-Efficient Fine-tuning for Large ASR Models. CoRR abs/2410.01948 (2024) - [i55]Thomas Steinke, Milad Nasr, Arun Ganesh, Borja Balle, Christopher A. Choquette-Choo, Matthew Jagielski, Jamie Hayes, Abhradeep Guha Thakurta, Adam D. Smith, Andreas Terzis:
The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD. CoRR abs/2410.06186 (2024) - [i54]Christopher A. Choquette-Choo, Arun Ganesh, Saminul Haque, Thomas Steinke, Abhradeep Thakurta:
Near Exact Privacy Amplification for Matrix Mechanisms. CoRR abs/2410.06266 (2024) - 2023
- [j5]Natalia Ponomareva, Hussein Hazimeh, Alex Kurakin, Zheng Xu, Carson Denison, H. Brendan McMahan, Sergei Vassilvitskii, Steve Chien, Abhradeep Guha Thakurta:
How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy. J. Artif. Intell. Res. 77: 1113-1201 (2023) - [j4]Harsh Mehta, Walid Krichene, Abhradeep Guha Thakurta, Alexey Kurakin, Ashok Cutkosky:
Differentially Private Image Classification from Features. Trans. Mach. Learn. Res. 2023 (2023) - [j3]Harsh Mehta, Abhradeep Guha Thakurta, Alexey Kurakin, Ashok Cutkosky:
Towards Large Scale Transfer Learning for Differentially Private Image Classification. Trans. Mach. Learn. Res. 2023 (2023) - [c52]Arun Ganesh, Abhradeep Thakurta, Jalaj Upadhyay:
Universality of Langevin Diffusion for Private Optimization, with Applications to Sampling from Rashomon Sets. COLT 2023: 1730-1773 - [c51]Naman Agarwal, Satyen Kale, Karan Singh, Abhradeep Thakurta:
Differentially Private and Lazy Online Convex Optimization. COLT 2023: 4599-4632 - [c50]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 - [c49]Christopher A. Choquette-Choo, Hugh Brendan McMahan, J. Keith Rush, Abhradeep Guha Thakurta:
Multi-Epoch Matrix Factorization Mechanisms for Private Machine Learning. ICML 2023: 5924-5963 - [c48]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: 10611-10627 - [c47]Walid Krichene, Prateek Jain, Shuang Song, Mukund Sundararajan, Abhradeep Guha Thakurta, Li Zhang:
Multi-Task Differential Privacy Under Distribution Skew. ICML 2023: 17784-17807 - [c46]Christopher A. Choquette-Choo, Arun Ganesh, Ryan McKenna, H. Brendan McMahan, John Rush, Abhradeep Guha Thakurta, Zheng Xu:
(Amplified) Banded Matrix Factorization: A unified approach to private training. NeurIPS 2023 - [c45]Arun Ganesh, Mahdi Haghifam, Thomas Steinke, Abhradeep Guha Thakurta:
Faster Differentially Private Convex Optimization via Second-Order Methods. NeurIPS 2023 - [c44]Daogao Liu, Arun Ganesh, Sewoong Oh, Abhradeep Guha Thakurta:
Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Risks. NeurIPS 2023 - [c43]Stephan Rabanser, Anvith Thudi, Abhradeep Guha Thakurta, Krishnamurthy Dvijotham, Nicolas Papernot:
Training Private Models That Know What They Don't Know. NeurIPS 2023 - [i53]Walid Krichene, Prateek Jain, Shuang Song, Mukund Sundararajan, Abhradeep Thakurta, Li Zhang:
Multi-Task Differential Privacy Under Distribution Skew. CoRR abs/2302.07975 (2023) - [i52]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 abs/2302.09483 (2023) - [i51]Arun Ganesh, Daogao Liu, Sewoong Oh, Abhradeep Thakurta:
Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Risks. CoRR abs/2302.09699 (2023) - [i50]Natalia Ponomareva, Hussein Hazimeh, Alex Kurakin, Zheng Xu, Carson Denison, H. Brendan McMahan, Sergei Vassilvitskii, Steve Chien, Abhradeep Thakurta:
How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy. CoRR abs/2303.00654 (2023) - [i49]Bing Zhang, Vadym Doroshenko, Peter Kairouz, Thomas Steinke, Abhradeep Thakurta, Ziyin Ma, Himani Apte, Jodi Spacek:
Differentially Private Stream Processing at Scale. CoRR abs/2303.18086 (2023) - [i48]Rachel Cummings, Damien Desfontaines, David Evans, Roxana Geambasu, Matthew Jagielski, Yangsibo Huang, Peter Kairouz, Gautam Kamath, Sewoong Oh, Olga Ohrimenko, Nicolas Papernot, Ryan Rogers, Milan Shen, Shuang Song, Weijie J. Su, Andreas Terzis, Abhradeep Thakurta, Sergei Vassilvitskii, Yu-Xiang Wang, Li Xiong, Sergey Yekhanin, Da Yu, Huanyu Zhang, Wanrong Zhang:
Challenges towards the Next Frontier in Privacy. CoRR abs/2304.06929 (2023) - [i47]Arun Ganesh, Mahdi Haghifam, Thomas Steinke, Abhradeep Thakurta:
Faster Differentially Private Convex Optimization via Second-Order Methods. CoRR abs/2305.13209 (2023) - [i46]Stephan Rabanser, Anvith Thudi, Abhradeep Thakurta, Krishnamurthy Dvijotham, Nicolas Papernot:
Training Private Models That Know What They Don't Know. CoRR abs/2305.18393 (2023) - [i45]Christopher A. Choquette-Choo, Arun Ganesh, Ryan McKenna, H. Brendan McMahan, Keith Rush, Abhradeep Guha Thakurta, Zheng Xu:
(Amplified) Banded Matrix Factorization: A unified approach to private training. CoRR abs/2306.08153 (2023) - [i44]Christopher A. Choquette-Choo, Krishnamurthy Dvijotham, Krishna Pillutla, Arun Ganesh, Thomas Steinke, Abhradeep Thakurta:
Correlated Noise Provably Beats Independent Noise for Differentially Private Learning. CoRR abs/2310.06771 (2023) - [i43]Walid Krichene, Nicolas Mayoraz, Steffen Rendle, Shuang Song, Abhradeep Thakurta, Li Zhang:
Private Learning with Public Features. CoRR abs/2310.15454 (2023) - [i42]Christopher A. Choquette-Choo, Arun Ganesh, Thomas Steinke, Abhradeep Thakurta:
Privacy Amplification for Matrix Mechanisms. CoRR abs/2310.15526 (2023) - [i41]Naman Agarwal, Satyen Kale, Karan Singh, Abhradeep Guha Thakurta:
Improved Differentially Private and Lazy Online Convex Optimization. CoRR abs/2312.11534 (2023) - 2022
- [c42]Prateek Varshney, Abhradeep Thakurta, Prateek Jain:
(Nearly) Optimal Private Linear Regression for Sub-Gaussian Data via Adaptive Clipping. COLT 2022: 1126-1166 - [c41]Oren Mangoubi, Yikai Wu, Satyen Kale, Abhradeep Thakurta, Nisheeth K. Vishnoi:
Private Matrix Approximation and Geometry of Unitary Orbits. COLT 2022: 3547-3588 - [c40]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: 517-535 - [c39]Sergey Denisov, H. Brendan McMahan, John Rush, Adam D. Smith, Abhradeep Guha Thakurta:
Improved Differential Privacy for SGD via Optimal Private Linear Operators on Adaptive Streams. NeurIPS 2022 - [c38]Xuechen Li, Daogao Liu, Tatsunori B. Hashimoto, Huseyin A. Inan, Janardhan Kulkarni, Yin Tat Lee, Abhradeep Guha Thakurta:
When Does Differentially Private Learning Not Suffer in High Dimensions? NeurIPS 2022 - [i40]Alexey Kurakin, Steve Chien, Shuang Song, Roxana Geambasu, Andreas Terzis, Abhradeep Thakurta:
Toward Training at ImageNet Scale with Differential Privacy. CoRR abs/2201.12328 (2022) - [i39]Brendan McMahan, Keith Rush, Abhradeep Guha Thakurta:
Private Online Prefix Sums via Optimal Matrix Factorizations. CoRR abs/2202.08312 (2022) - [i38]Arun Ganesh, Abhradeep Thakurta, Jalaj Upadhyay:
Langevin Diffusion: An Almost Universal Algorithm for Private Euclidean (Convex) Optimization. CoRR abs/2204.01585 (2022) - [i37]Harsh Mehta, Abhradeep Thakurta, Alexey Kurakin, Ashok Cutkosky:
Large Scale Transfer Learning for Differentially Private Image Classification. CoRR abs/2205.02973 (2022) - [i36]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 abs/2207.00099 (2022) - [i35]Xuechen Li, Daogao Liu, Tatsunori Hashimoto, Huseyin A. Inan, Janardhan Kulkarni, Yin Tat Lee, Abhradeep Guha Thakurta:
When Does Differentially Private Learning Not Suffer in High Dimensions? CoRR abs/2207.00160 (2022) - [i34]Oren Mangoubi, Yikai Wu, Satyen Kale, Abhradeep Guha Thakurta, Nisheeth K. Vishnoi:
Private Matrix Approximation and Geometry of Unitary Orbits. CoRR abs/2207.02794 (2022) - [i33]Prateek Varshney, Abhradeep Thakurta, Prateek Jain:
(Nearly) Optimal Private Linear Regression via Adaptive Clipping. CoRR abs/2207.04686 (2022) - [i32]Virat Shejwalkar, Arun Ganesh, Rajiv Mathews, Om Thakkar, Abhradeep Thakurta:
Recycling Scraps: Improving Private Learning by Leveraging Intermediate Checkpoints. CoRR abs/2210.01864 (2022) - [i31]Yannis Cattan, Christopher A. Choquette-Choo, Nicolas Papernot, Abhradeep Thakurta:
Fine-Tuning with Differential Privacy Necessitates an Additional Hyperparameter Search. CoRR abs/2210.02156 (2022) - [i30]Soumyabrata Pal, Prateek Varshney, Prateek Jain, Abhradeep Guha Thakurta, Gagan Madan, Gaurav Aggarwal, Pradeep Shenoy, Gaurav Srivastava:
Private and Efficient Meta-Learning with Low Rank and Sparse Decomposition. CoRR abs/2210.03505 (2022) - [i29]Adam D. Smith, Abhradeep Thakurta:
Fully Adaptive Composition for Gaussian Differential Privacy. CoRR abs/2210.17520 (2022) - [i28]Christopher A. Choquette-Choo, H. Brendan McMahan, Keith Rush, Abhradeep Thakurta:
Multi-Epoch Matrix Factorization Mechanisms for Private Machine Learning. CoRR abs/2211.06530 (2022) - [i27]Harsh Mehta, Walid Krichene, Abhradeep Thakurta, Alexey Kurakin, Ashok Cutkosky:
Differentially Private Image Classification from Features. CoRR abs/2211.13403 (2022) - 2021
- [c37]Nicolas Papernot, Abhradeep Thakurta, Shuang Song, Steve Chien, Úlfar Erlingsson:
Tempered Sigmoid Activations for Deep Learning with Differential Privacy. AAAI 2021: 9312-9321 - [c36]Shuang Song, Thomas Steinke, Om Thakkar, Abhradeep Thakurta:
Evading the Curse of Dimensionality in Unconstrained Private GLMs. AISTATS 2021: 2638-2646 - [c35]Peter Kairouz, Mónica Ribero Diaz, Keith Rush, Abhradeep Thakurta:
(Nearly) Dimension Independent Private ERM with AdaGrad Ratesvia Publicly Estimated Subspaces. COLT 2021: 2717-2746 - [c34]Steve Chien, Prateek Jain, Walid Krichene, Steffen Rendle, Shuang Song, Abhradeep Thakurta, Li Zhang:
Private Alternating Least Squares: Practical Private Matrix Completion with Tighter Rates. ICML 2021: 1877-1887 - [c33]Peter Kairouz, Brendan McMahan, Shuang Song, Om Thakkar, Abhradeep Thakurta, Zheng Xu:
Practical and Private (Deep) Learning Without Sampling or Shuffling. ICML 2021: 5213-5225 - [c32]Samuel Deng, Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Abhradeep Guha Thakurta:
A Separation Result Between Data-oblivious and Data-aware Poisoning Attacks. NeurIPS 2021: 10862-10875 - [c31]Prateek Jain, John Rush, Adam D. Smith, Shuang Song, Abhradeep Guha Thakurta:
Differentially Private Model Personalization. NeurIPS 2021: 29723-29735 - [c30]Nicholas Carlini, Samuel Deng, Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Abhradeep Thakurta, Florian Tramèr:
Is Private Learning Possible with Instance Encoding? SP 2021: 410-427 - [c29]Milad Nasr, Shuang Song, Abhradeep Thakurta, Nicolas Papernot, Nicholas Carlini:
Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning. SP 2021: 866-882 - [i26]Milad Nasr, Shuang Song, Abhradeep Thakurta, Nicolas Papernot, Nicholas Carlini:
Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning. CoRR abs/2101.04535 (2021) - [i25]Peter Kairouz, Brendan McMahan, Shuang Song, Om Thakkar, Abhradeep Thakurta, Zheng Xu:
Practical and Private (Deep) Learning without Sampling or Shuffling. CoRR abs/2103.00039 (2021) - [i24]Steve Chien, Prateek Jain, Walid Krichene, Steffen Rendle, Shuang Song, Abhradeep Thakurta, Li Zhang:
Private Alternating Least Squares: Practical Private Matrix Completion with Tighter Rates. CoRR abs/2107.09802 (2021) - [i23]Ameya Daigavane, Gagan Madan, Aditya Sinha, Abhradeep Guha Thakurta, Gaurav Aggarwal, Prateek Jain:
Node-Level Differentially Private Graph Neural Networks. CoRR abs/2111.15521 (2021) - [i22]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 abs/2112.00193 (2021) - 2020
- [j2]Raef Bassily, Kobbi Nissim, Uri Stemmer, Abhradeep Thakurta:
Practical Locally Private Heavy Hitters. J. Mach. Learn. Res. 21: 16:1-16:42 (2020) - [c28]Borja Balle, Peter Kairouz, Brendan McMahan, Om Dipakbhai Thakkar, Abhradeep Thakurta:
Privacy Amplification via Random Check-Ins. NeurIPS 2020 - [c27]Adam D. Smith, Shuang Song, Abhradeep Thakurta:
The Flajolet-Martin Sketch Itself Preserves Differential Privacy: Private Counting with Minimal Space. NeurIPS 2020 - [i21]Úlfar Erlingsson, Vitaly Feldman, Ilya Mironov, Ananth Raghunathan, Shuang Song, Kunal Talwar, Abhradeep Thakurta:
Encode, Shuffle, Analyze Privacy Revisited: Formalizations and Empirical Evaluation. CoRR abs/2001.03618 (2020) - [i20]Daniel Kifer, Solomon Messing, Aaron Roth, Abhradeep Thakurta, Danfeng Zhang:
Guidelines for Implementing and Auditing Differentially Private Systems. CoRR abs/2002.04049 (2020) - [i19]Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Abhradeep Thakurta:
Obliviousness Makes Poisoning Adversaries Weaker. CoRR abs/2003.12020 (2020) - [i18]Shuang Song, Om Thakkar, Abhradeep Thakurta:
Characterizing Private Clipped Gradient Descent on Convex Generalized Linear Problems. CoRR abs/2006.06783 (2020) - [i17]Borja Balle, Peter Kairouz, H. Brendan McMahan, Om Thakkar, Abhradeep Thakurta:
Privacy Amplification via Random Check-Ins. CoRR abs/2007.06605 (2020) - [i16]Nicolas Papernot, Abhradeep Thakurta, Shuang Song, Steve Chien, Úlfar Erlingsson:
Tempered Sigmoid Activations for Deep Learning with Differential Privacy. CoRR abs/2007.14191 (2020) - [i15]Peter Kairouz, Mónica Ribero, Keith Rush, Abhradeep Thakurta:
Dimension Independence in Unconstrained Private ERM via Adaptive Preconditioning. CoRR abs/2008.06570 (2020) - [i14]Nicholas Carlini, Samuel Deng, Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Shuang Song, Abhradeep Thakurta, Florian Tramèr:
An Attack on InstaHide: Is Private Learning Possible with Instance Encoding? CoRR abs/2011.05315 (2020)
2010 – 2019
- 2019
- [c26]Raef Bassily, Vitaly Feldman, Kunal Talwar, Abhradeep Guha Thakurta:
Private Stochastic Convex Optimization with Optimal Rates. NeurIPS 2019: 11279-11288 - [c25]Úlfar Erlingsson, Vitaly Feldman, Ilya Mironov, Ananth Raghunathan, Kunal Talwar, Abhradeep Thakurta:
Amplification by Shuffling: From Local to Central Differential Privacy via Anonymity. SODA 2019: 2468-2479 - [c24]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: 299-316 - [c23]Krishnaram Kenthapadi, Ilya Mironov, Abhradeep Guha Thakurta:
Privacy-preserving Data Mining in Industry. WSDM 2019: 840-841 - [c22]Krishnaram Kenthapadi, Ilya Mironov, Abhradeep Thakurta:
Privacy-preserving Data Mining in Industry. WWW (Companion Volume) 2019: 1308-1310 - [i13]Raef Bassily, Vitaly Feldman, Kunal Talwar, Abhradeep Thakurta:
Private Stochastic Convex Optimization with Optimal Rates. CoRR abs/1908.09970 (2019) - 2018
- [j1]Kashyap Dixit, Sofya Raskhodnikova, Abhradeep Thakurta, Nithin Varma:
Erasure-Resilient Property Testing. SIAM J. Comput. 47(2): 295-329 (2018) - [c21]Vitaly Feldman, Ilya Mironov, Kunal Talwar, Abhradeep Thakurta:
Privacy Amplification by Iteration. FOCS 2018: 521-532 - [c20]Prateek Jain, Om Dipakbhai Thakkar, Abhradeep Thakurta:
Differentially Private Matrix Completion Revisited. ICML 2018: 2220-2229 - [c19]Raef Bassily, Abhradeep Guha Thakurta, Om Dipakbhai Thakkar:
Model-Agnostic Private Learning. NeurIPS 2018: 7102-7112 - [i12]Raef Bassily, Om Thakkar, Abhradeep Thakurta:
Model-Agnostic Private Learning via Stability. CoRR abs/1803.05101 (2018) - [i11]Vitaly Feldman, Ilya Mironov, Kunal Talwar, Abhradeep Thakurta:
Privacy Amplification by Iteration. CoRR abs/1808.06651 (2018) - [i10]Úlfar Erlingsson, Vitaly Feldman, Ilya Mironov, Ananth Raghunathan, Kunal Talwar, Abhradeep Thakurta:
Amplification by Shuffling: From Local to Central Differential Privacy via Anonymity. CoRR abs/1811.12469 (2018) - 2017
- [c18]Raef Bassily, Kobbi Nissim, Uri Stemmer, Abhradeep Guha Thakurta:
Practical Locally Private Heavy Hitters. NIPS 2017: 2288-2296 - [c17]Adam D. Smith, Abhradeep Thakurta, Jalaj Upadhyay:
Is Interaction Necessary for Distributed Private Learning? IEEE Symposium on Security and Privacy 2017: 58-77 - [i9]Raef Bassily, Kobbi Nissim, Uri Stemmer, Abhradeep Thakurta:
Practical Locally Private Heavy Hitters. CoRR abs/1707.04982 (2017) - [i8]Prateek Jain, Om Thakkar, Abhradeep Thakurta:
Differentially Private Matrix Completion, Revisited. CoRR abs/1712.09765 (2017) - 2016
- [c16]Kashyap Dixit, Sofya Raskhodnikova, Abhradeep Thakurta, Nithin Varma:
Erasure-Resilient Property Testing. ICALP 2016: 91:1-91:15 - [r1]Abhradeep Thakurta:
Beyond Worst Case Sensitivity in Private Data Analysis. Encyclopedia of Algorithms 2016: 192-199 - [i7]Kashyap Dixit, Sofya Raskhodnikova, Abhradeep Thakurta, Nithin Varma:
Erasure-Resilient Property Testing. CoRR abs/1607.05786 (2016) - 2015
- [c15]Kunal Talwar, Abhradeep Thakurta, Li Zhang:
Nearly Optimal Private LASSO. NIPS 2015: 3025-3033 - [c14]Nikita Mishra, Abhradeep Thakurta:
(Nearly) Optimal Differentially Private Stochastic Multi-Arm Bandits. UAI 2015: 592-601 - [i6]Prateek Jain, Vivek Kulkarni, Abhradeep Thakurta, Oliver Williams:
To Drop or Not to Drop: Robustness, Consistency and Differential Privacy Properties of Dropout. CoRR abs/1503.02031 (2015) - 2014
- [c13]Raef Bassily, Adam D. Smith, Abhradeep Thakurta:
Private Empirical Risk Minimization: Efficient Algorithms and Tight Error Bounds. FOCS 2014: 464-473 - [c12]Prateek Jain, Abhradeep Guha Thakurta:
(Near) Dimension Independent Risk Bounds for Differentially Private Learning. ICML 2014: 476-484 - [c11]Cynthia Dwork, Kunal Talwar, Abhradeep Thakurta, Li Zhang:
Analyze gauss: optimal bounds for privacy-preserving principal component analysis. STOC 2014: 11-20 - [i5]Raef Bassily, Adam D. Smith, Abhradeep Thakurta:
Private Empirical Risk Minimization, Revisited. CoRR abs/1405.7085 (2014) - [i4]Kunal Talwar, Abhradeep Thakurta, Li Zhang:
Private Empirical Risk Minimization Beyond the Worst Case: The Effect of the Constraint Set Geometry. CoRR abs/1411.5417 (2014) - 2013
- [c10]Abhradeep Thakurta, Adam D. Smith:
Differentially Private Feature Selection via Stability Arguments, and the Robustness of the Lasso. COLT 2013: 819-850 - [c9]Prateek Jain, Abhradeep Thakurta:
Differentially Private Learning with Kernels. ICML (3) 2013: 118-126 - [c8]Abhradeep Guha Thakurta, Adam D. Smith:
(Nearly) Optimal Algorithms for Private Online Learning in Full-information and Bandit Settings. NIPS 2013: 2733-2741 - [c7]Kashyap Dixit, Madhav Jha, Sofya Raskhodnikova, Abhradeep Thakurta:
Testing the Lipschitz Property over Product Distributions with Applications to Data Privacy. TCC 2013: 418-436 - 2012
- [c6]Prateek Jain, Abhradeep Thakurta:
Mirror Descent Based Database Privacy. APPROX-RANDOM 2012: 579-590 - [c5]