Akshay Mehra

On the Fly Neural Style Smoothing for Risk-Averse Domain Generalization

Risk-Averse Predictions on Unseen Domains via Neural Style Smoothing

Analysis of task transferability in large pre-trained classifiers

Understanding the robustness of multi-exit models under common corruptions

Do Domain Generalization Methods Generalize Well?

A spectral view of randomized smoothing under common corruptions: Benchmarking and improving certified robustness

On certifying and improving generalization to unseen domains

Certified adversarial defenses meet out-of-distribution corruptions: Benchmarking robustness and simple baselines