Search Results for author: Vinayak Pathak

Found 5 papers, 0 papers with code

Tensorial tomographic differential phase-contrast microscopy

no code implementations25 Apr 2022 Shiqi Xu, Xiang Dai, Xi Yang, Kevin C. Zhou, Kanghyun Kim, Vinayak Pathak, Carolyn Glass, Roarke Horstmeyer

We report Tensorial Tomographic Differential Phase-Contrast microscopy (T2DPC), a quantitative label-free tomographic imaging method for simultaneous measurement of phase and anisotropy.

Adversarially Robust Learning with Tolerance

no code implementations2 Mar 2022 Hassan Ashtiani, Vinayak Pathak, Ruth Urner

In the tolerant version, the error of the learner is compared with the best achievable error with respect to a slightly larger perturbation radius $(1+\gamma)r$.

PAC learning

Increasing a microscope's effective field of view via overlapped imaging and machine learning

no code implementations10 Oct 2021 Xing Yao, Vinayak Pathak, Haoran Xi, Amey Chaware, Colin Cooke, Kanghyun Kim, Shiqi Xu, Yuting Li, Timothy Dunn, Pavan Chandra Konda, Kevin C. Zhou, Roarke Horstmeyer

This work demonstrates a multi-lens microscopic imaging system that overlaps multiple independent fields of view on a single sensor for high-efficiency automated specimen analysis.

BIG-bench Machine Learning

Black-box Certification and Learning under Adversarial Perturbations

no code implementations ICML 2020 Hassan Ashtiani, Vinayak Pathak, Ruth Urner

We formally study the problem of classification under adversarial perturbations from a learner's perspective as well as a third-party who aims at certifying the robustness of a given black-box classifier.

Cannot find the paper you are looking for? You can Submit a new open access paper.