Search Results for author:
Found 8 papers, 4 papers with code
Fairness under Covariate Shift: Improving Fairness-Accuracy tradeoff with few Unlabeled Test Samples
Our third contribution is theoretical, where we show that our weighted entropy term along with prediction loss on the training set approximates test loss under covariate shift.
Multi-Variate Time Series Forecasting on Variable Subsets
Through systematic experiments across 4 datasets and 5 forecast models, we show that our technique is able to recover close to 95\% performance of the models even when only 15\% of the original variables are present.
Distributional Shifts in Automated Diabetic Retinopathy Screening
Deep learning-based models are developed to automatically detect if a retina image is `referable' in diabetic retinopathy (DR) screening.
Towards Bridging the gap between Empirical and Certified Robustness against Adversarial Examples
In this paper, we propose a novel method, called \emph{Certification through Adaptation}, that transforms an AT model into a randomized smoothing classifier during inference to provide certified robustness for $\ell_2$ norm without affecting their empirical robustness against adversarial attacks.
Towards Maximizing the Representation Gap between In-Domain & Out-of-Distribution Examples
Among existing uncertainty estimation approaches, Dirichlet Prior Network (DPN) distinctly models different predictive uncertainty types.
Approximate Manifold Defense Against Multiple Adversarial Perturbations
Using adversarial training to defend against multiple types of perturbation requires expensive adversarial examples from different perturbation types at each training step.
Improving Dirichlet Prior Network for Out-of-Distribution Example Detection
Predictive uncertainties can originate from the uncertainty in model parameters, data uncertainty or due to distributional mismatch between training and test examples.
Normal Similarity Network for Generative Modelling
Gaussian distributions are commonly used as a key building block in many generative models.
