1 code implementation • 3 Apr 2024 • Kamalika Chaudhuri, Chuan Guo, Laurens van der Maaten, Saeed Mahloujifar, Mark Tygert
The HCR bounds appear to be insufficient on their own to guarantee confidentiality of the inputs to inference with standard deep neural nets, "ResNet-18" and "Swin-T," pre-trained on the data set, "ImageNet-1000," which contains 1000 classes.
1 code implementation • 19 May 2022 • Imanol Arrieta-Ibarra, Paman Gujral, Jonathan Tannen, Mark Tygert, Cherie Xu
The canonical reliability diagrams histogram the observed and expected values of the predictions; replacing the hard histogram binning with soft kernel density estimation is another common practice.
1 code implementation • 31 Jan 2022 • Mark Tygert
The author's recent research papers, "Cumulative deviation of a subpopulation from the full population" and "A graphical method of cumulative differences between two subpopulations" (both published in volume 8 of Springer's open-access "Journal of Big Data" during 2021), propose graphical methods and summary statistics, without extensively calibrating formal significance tests.
no code implementations • 3 Jun 2020 • Isabel Kloumann, Mark Tygert
This paper concerns the ethics and morality of algorithms and computational systems, and has been circulating internally at Facebook for the past couple years.
no code implementations • 3 Jun 2020 • Mark Tygert
The canonical reliability diagrams are based on histogramming the observed and expected values of the predictions; several variants of the standard reliability diagrams propose to replace the hard histogram binning with soft kernel density estimation using smooth convolutional kernels of widths similar to the widths of the bins.
no code implementations • 9 Jan 2020 • Chuan Guo, Awni Hannun, Brian Knott, Laurens van der Maaten, Mark Tygert, Ruiyu Zhu
Secure multiparty computations enable the distribution of so-called shares of sensitive data to multiple parties such that the multiple parties can effectively process the data while being unable to glean much information about the data (at least not without collusion among all parties to put back together all the shares).
no code implementations • 11 Oct 2017 • Mark Tygert
Linear least-squares regression with a "design" matrix A approximates a given matrix B via minimization of the spectral- or Frobenius-norm discrepancy ||AX-B|| over every conformingly sized matrix X.
no code implementations • 1 Sep 2017 • Cinna Wu, Mark Tygert, Yann Lecun
We define a metric that, inter alia, can penalize failure to distinguish between a sheepdog and a skyscraper more than failure to distinguish between a sheepdog and a poodle.
no code implementations • 9 Feb 2016 • Mark Tygert
Poor (even random) starting points for learning/training/optimization are common in machine learning.
no code implementations • 26 Jun 2015 • Mark Tygert, Arthur Szlam, Soumith Chintala, Marc'Aurelio Ranzato, Yuandong Tian, Wojciech Zaremba
The conventional classification schemes -- notably multinomial logistic regression -- used in conjunction with convolutional networks (convnets) are classical in statistics, designed without consideration for the usual coupling with convnets, stochastic gradient descent, and backpropagation.
no code implementations • 11 Mar 2015 • Joan Bruna, Soumith Chintala, Yann Lecun, Serkan Piantino, Arthur Szlam, Mark Tygert
Courtesy of the exact correspondence, the remarkably rich and rigorous body of mathematical analysis for wavelets applies directly to (complex-valued) convnets.