Search Results for author: Vittorio Romaniello

Found 2 papers, 1 papers with code

Revealing Unfair Models by Mining Interpretable Evidence

no code implementations • 12 Jul 2022 • Mohit Bajaj, Lingyang Chu, Vittorio Romaniello, Gursimran Singh, Jian Pei, Zirui Zhou, Lanjun Wang, Yong Zhang

The key idea is to find solid evidence in the form of a group of data instances discriminated most by the model.

BIG-bench Machine Learning Medical Diagnosis

Paper
Add Code

Parallel Tempering on Optimized Paths

1 code implementation • 15 Feb 2021 • Saifuddin Syed, Vittorio Romaniello, Trevor Campbell, Alexandre Bouchard-Côté

Parallel tempering (PT) is a class of Markov chain Monte Carlo algorithms that constructs a path of distributions annealing between a tractable reference and an intractable target, and then interchanges states along the path to improve mixing in the target.

Computation 65C05

Paper
Code

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