Search Results for author:
Found 11 papers, 3 papers with code
Guarantees of confidentiality via Hammersley-Chapman-Robbins bounds
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.
Metrics of calibration for probabilistic predictions
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.
Calibration of P-values for calibration and for deviation of a subpopulation from the full population
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.
An optimizable scalar objective value cannot be objective and should not be the sole objective
This paper concerns the ethics and morality of algorithms and computational systems, and has been circulating internally at Facebook for the past couple years.
Plots of the cumulative differences between observed and expected values of ordered Bernoulli variates
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.
Secure multiparty computations in floating-point arithmetic
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).
Regression-aware decompositions
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.
A hierarchical loss and its problems when classifying non-hierarchically
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.
Poor starting points in machine learning
Poor (even random) starting points for learning/training/optimization are common in machine learning.
Convolutional networks and learning invariant to homogeneous multiplicative scalings
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.
A mathematical motivation for complex-valued convolutional networks
Courtesy of the exact correspondence, the remarkably rich and rigorous body of mathematical analysis for wavelets applies directly to (complex-valued) convnets.
