Search Results for author:
Found 9 papers, 1 papers with code
Privacy Loss of Noisy Stochastic Gradient Descent Might Converge Even for Non-Convex Losses
The Noisy-SGD algorithm is widely used for privately training machine learning models.
Contraction of $E_γ$-Divergence and Its Applications to Privacy
First, it implies that local differential privacy can be equivalently expressed in terms of the contraction of $E_\gamma$-divergence.
On the alpha-loss Landscape in the Logistic Model
We analyze the optimization landscape of a recently introduced tunable class of loss functions called $\alpha$-loss, $\alpha \in (0,\infty]$, in the logistic model.
To Split or Not to Split: The Impact of Disparate Treatment in Classification
To evaluate the effect of disparate treatment, we compare the performance of split classifiers (i. e., classifiers trained and deployed separately on each group) with group-blind classifiers (i. e., classifiers which do not use a sensitive attribute).
Privacy Amplification of Iterative Algorithms via Contraction Coefficients
We investigate the framework of privacy amplification by iteration, recently proposed by Feldman et al., from an information-theoretic lens.
Theoretical Guarantees for Model Auditing with Finite Adversaries
Privacy concerns have led to the development of privacy-preserving approaches for learning models from sensitive data.
A Tunable Loss Function for Robust Classification: Calibration, Landscape, and Generalization
We introduce a tunable loss function called $\alpha$-loss, parameterized by $\alpha \in (0,\infty]$, which interpolates between the exponential loss ($\alpha = 1/2$), the log-loss ($\alpha = 1$), and the 0-1 loss ($\alpha = \infty$), for the machine learning setting of classification.
A Tunable Loss Function for Binary Classification
We present $\alpha$-loss, $\alpha \in [1,\infty]$, a tunable loss function for binary classification that bridges log-loss ($\alpha=1$) and $0$-$1$ loss ($\alpha = \infty$).
Information Extraction Under Privacy Constraints
To this end, the so-called {\em rate-privacy function} is introduced to quantify the maximal amount of information (measured in terms of mutual information) that can be extracted from $Y$ under a privacy constraint between $X$ and the extracted information, where privacy is measured using either mutual information or maximal correlation.
