Zobrazeno 1 - 10
of 2 375
pro vyhledávání: '"A. Thakurta"'
Autor:
Choquette-Choo, Christopher A., Ganesh, Arun, Haque, Saminul, Steinke, Thomas, Thakurta, Abhradeep
We study the problem of computing the privacy parameters for DP machine learning when using privacy amplification via random batching and noise correlated across rounds via a correlation matrix $\textbf{C}$ (i.e., the matrix mechanism). Past work on
Externí odkaz:
http://arxiv.org/abs/2410.06266
Autor:
Steinke, Thomas, Nasr, Milad, Ganesh, Arun, Balle, Borja, Choquette-Choo, Christopher A., Jagielski, Matthew, Hayes, Jamie, Thakurta, Abhradeep Guha, Smith, Adam, Terzis, Andreas
We propose a simple heuristic privacy analysis of noisy clipped stochastic gradient descent (DP-SGD) in the setting where only the last iterate is released and the intermediate iterates remain hidden. Namely, our heuristic assumes a linear structure
Externí odkaz:
http://arxiv.org/abs/2410.06186
Large ASR models can inadvertently leak sensitive information, which can be mitigated by formal privacy measures like differential privacy (DP). However, traditional DP training is computationally expensive, and can hurt model performance. Our study
Externí odkaz:
http://arxiv.org/abs/2410.01948
Self-supervised learning (SSL) methods for large speech models have proven to be highly effective at ASR. With the interest in public deployment of large pre-trained models, there is a rising concern for unintended memorization and leakage of sensiti
Externí odkaz:
http://arxiv.org/abs/2409.13953
Autor:
Zhou, Guanglei, Korrapati, Bhargav, Reddy, Gaurav Rajavendra, Hu, Jiang, Chen, Yiran, Thakurta, Dipto G.
Generation of diverse VLSI layout patterns is crucial for various downstream tasks in design for manufacturing (DFM) studies. However, the lengthy design cycles often hinder the creation of a comprehensive layout pattern library, and new detrimental
Externí odkaz:
http://arxiv.org/abs/2409.01348
Autor:
R. Wester, M. van Duin, K.H. Lam, S.S. Couto, Y. Ren, M. Wang, T. Cupedo, B. van der Holt, H.B. Beverloo, A.L. Nigg, A. Thakurta, A.A. Waage, S. Zweegman, A. Broijl, P. Sonneveld
Publikováno v:
HemaSphere, Vol 7, Iss S2, Pp 7-7 (2023)
Externí odkaz:
https://doaj.org/article/ac5c45f94a93462f873cc5b325ce4129
In this paper we revisit the DP stochastic convex optimization (SCO) problem. For convex smooth losses, it is well-known that the canonical DP-SGD (stochastic gradient descent) achieves the optimal rate of $O\left(\frac{LR}{\sqrt{n}} + \frac{LR \sqrt
Externí odkaz:
http://arxiv.org/abs/2406.02716
Autor:
D. Jeyaraju, M. Alapa, A. Polonskaia, A. Risueno Perez, R. Hurren, X. Wang, M. Gronda, A. Ahsan, C. Wang, P. Subramanyam, J. Sriganesh, A. Anand, M. Bysani Reddy, K. Ghosh, C. Kyriakopoulos, N. Lailler, C. Hartl, D. Lopes de Menezes, A. Schimmer, P. Hagner, A. Gandhi, A. Thakurta
Publikováno v:
HemaSphere, Vol 6, Pp 312-313 (2022)
Externí odkaz:
https://doaj.org/article/99cef92c9e5f4658b40e8784647da594
Autor:
M. Amatangelo, Y. Cheng, W. Pierceall, N. W. van de Donk, S. Lonial, M. Wang, J. Emerson, K. Hong, P. Maciag, T. Peluso, A. Gandhi, A. Thakurta
Publikováno v:
HemaSphere, Vol 6, Pp 758-759 (2022)
Externí odkaz:
https://doaj.org/article/d46a0be0884d43448c81ea6db738014c
Autor:
Dvijotham, Krishnamurthy, McMahan, H. Brendan, Pillutla, Krishna, Steinke, Thomas, Thakurta, Abhradeep
In the task of differentially private (DP) continual counting, we receive a stream of increments and our goal is to output an approximate running total of these increments, without revealing too much about any specific increment. Despite its simplici
Externí odkaz:
http://arxiv.org/abs/2404.16706