Search Results for author:
Found 6 papers, 5 papers with code
Statistically Efficient Bayesian Sequential Experiment Design via Reinforcement Learning with Cross-Entropy Estimators
We propose the use of an alternative estimator based on the cross-entropy of the joint model distribution and a flexible proposal distribution.
Deviations in Representations Induced by Adversarial Attacks
Deep learning has been a popular topic and has achieved success in many areas.
Measuring the Contribution of Multiple Model Representations in Detecting Adversarial Instances
While these models have worked well under many scenarios, it has been shown that they are vulnerable to adversarial attacks.
Visualizing Representations of Adversarially Perturbed Inputs
It has been shown that deep learning models are vulnerable to adversarial attacks.
Fast Fair Regression via Efficient Approximations of Mutual Information
Most work in algorithmic fairness to date has focused on discrete outcomes, such as deciding whether to grant someone a loan or not.
Fairness Measures for Regression via Probabilistic Classification
For the regression setting we introduce tractable approximations of the independence, separation and sufficiency criteria by observing that they factorise as ratios of different conditional probabilities of the protected attributes.
