Search Results for author:
Found 11 papers, 1 papers with code
A Unifying Generator Loss Function for Generative Adversarial Networks
A unifying $\alpha$-parametrized generator loss function is introduced for a dual-objective generative adversarial network (GAN), which uses a canonical (or classical) discriminator loss function such as the one in the original GAN (VanillaGAN) system.
Evaluating Trade-offs in Computer Vision Between Attribute Privacy, Fairness and Utility
This paper investigates to what degree and magnitude tradeoffs exist between utility, fairness and attribute privacy in computer vision.
On the Rényi Cross-Entropy
The R\'{e}nyi cross-entropy measure between two distributions, a generalization of the Shannon cross-entropy, was recently used as a loss function for the improved design of deep learning generative adversarial networks.
Classification Utility, Fairness, and Compactness via Tunable Information Bottleneck and Rényi Measures
Designing machine learning algorithms that are accurate yet fair, not discriminating based on any sensitive attribute, is of paramount importance for society to accept AI for critical applications.
Renyi Fair Information Bottleneck for Image Classification
We develop a novel method for ensuring fairness in machine learning which we term as the Renyi Fair Information Bottleneck (RFIB).
An Information Bottleneck Problem with Rényi's Entropy
This paper considers an information bottleneck problem with the objective of obtaining a most informative representation of a hidden feature subject to a R\'enyi entropy complexity constraint.
Information Theory Information Theory
TARA: Training and Representation Alteration for AI Fairness and Domain Generalization
Our experiments also demonstrate the ability of these novel metrics in assessing the Pareto efficiency of the proposed methods.
Least $k$th-Order and Rényi Generative Adversarial Networks
Another novel GAN generator loss function is next proposed in terms of R\'{e}nyi cross-entropy functionals with order $\alpha >0$, $\alpha\neq 1$.
Unsupervised Discovery, Control, and Disentanglement of Semantic Attributes with Applications to Anomaly Detection
Our work focuses on unsupervised and generative methods that address the following goals: (a) learning unsupervised generative representations that discover latent factors controlling image semantic attributes, (b) studying how this ability to control attributes formally relates to the issue of latent factor disentanglement, clarifying related but dissimilar concepts that had been confounded in the past, and (c) developing anomaly detection methods that leverage representations learned in (a).
Capacity of Generalized Discrete-Memoryless Push-to-Talk Two-Way Channels
In this report, we generalize Shannon's push-to-talk two-way channel (PTT-TWC) by allowing reliable full-duplex transmission as well as noisy reception in the half-duplex (PTT) mode.
Information Theory Information Theory
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.
