Search Results for author:
Found 12 papers, 2 papers with code
Generative models improve fairness of medical classifiers under distribution shifts
In our work, we show that learning realistic augmentations automatically from data is possible in a label-efficient manner using generative models.
Evaluating the Adversarial Robustness of Adaptive Test-time Defenses
Adaptive defenses, which optimize at test time, promise to improve adversarial robustness.
Role of Human-AI Interaction in Selective Prediction
Using real-world conservation data and a selective prediction system that improves expected accuracy over that of the human or AI system working individually, we show that this messaging has a significant impact on the accuracy of human judgements.
A Fine-Grained Analysis on Distribution Shift
Despite this necessity, there has been little work in defining the underlying mechanisms that cause these shifts and evaluating the robustness of algorithms across multiple, different distribution shifts.
Does Your Dermatology Classifier Know What It Doesn't Know? Detecting the Long-Tail of Unseen Conditions
We develop and rigorously evaluate a deep learning based system that can accurately classify skin conditions while detecting rare conditions for which there is not enough data available for training a confident classifier.
The Autoencoding Variational Autoencoder
We provide experimental results on the ColorMnist and CelebA benchmark datasets that quantify the properties of the learned representations and compare the approach with a baseline that is specifically trained for the desired property.
Unbiased Gradient Estimation for Variational Auto-Encoders using Coupled Markov Chains
The variational auto-encoder (VAE) is a deep latent variable model that has two neural networks in an autoencoder-like architecture; one of them parameterizes the model's likelihood.
Contrastive Training for Improved Out-of-Distribution Detection
Reliable detection of out-of-distribution (OOD) inputs is increasingly understood to be a precondition for deployment of machine learning systems.
Ranked #12 on
Out-of-Distribution Detection
on CIFAR-100 vs CIFAR-10
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Adversarially Robust Representations with Smooth Encoders
This paper studies the undesired phenomena of over-sensitivity of representations learned by deep networks to semantically-irrelevant changes in data.
Achieving Robustness in the Wild via Adversarial Mixing with Disentangled Representations
Specifically, we leverage the disentangled latent representations computed by a StyleGAN model to generate perturbations of an image that are similar to real-world variations (like adding make-up, or changing the skin-tone of a person) and train models to be invariant to these perturbations.
Asynchronous Stochastic Quasi-Newton MCMC for Non-Convex Optimization
The results support our theory and show that the proposed algorithm provides a significant speedup over the recently proposed synchronous distributed L-BFGS algorithm.
Summary Statistics for Partitionings and Feature Allocations
Experiments on various infinite mixture posteriors as well as a feature allocation dataset demonstrate that the proposed statistics are useful in practice.
