no code implementations • 6 Mar 2023 • S Chandra Mouli, Muhammad Ashraful Alam, Bruno Ribeiro
A fundamental challenge in physics-informed machine learning (PIML) is the design of robust PIML methods for out-of-distribution (OOD) forecasting tasks.
no code implementations • 12 Sep 2022 • S Chandra Mouli, Yangze Zhou, Bruno Ribeiro
Deep learning models tend not to be out-of-distribution robust primarily due to their reliance on spurious features to solve the task.
no code implementations • ICLR 2022 • S Chandra Mouli, Bruno Ribeiro
Generalizing from observed to new related environments (out-of-distribution) is central to the reliability of classifiers.
1 code implementation • 20 Apr 2021 • S Chandra Mouli, Bruno Ribeiro
In order to endow neural networks with the ability to extrapolate over group transformations, we introduce a learning framework counterfactually-guided by the learning hypothesis that any group invariance to (known) transformation groups is mandatory even without evidence, unless the learner deems it inconsistent with the training data.
no code implementations • ICLR 2021 • S Chandra Mouli, Bruno Ribeiro
In order to endow neural networks with the ability to extrapolate over group transformations, we introduce a learning framework guided by a new learning hypothesis: Any invariance to transformation groups is mandatory even without evidence, unless the learner deems it inconsistent with the training data.
no code implementations • 28 May 2020 • Mohsen Minaei, S Chandra Mouli, Mainack Mondal, Bruno Ribeiro, Aniket Kate
Our mechanism injects decoy deletions, hence creating a two-player minmax game between an adversary that seeks to classify damaging content among the deleted posts and a challenger that employs decoy deletions to masquerade real damaging deletions.
1 code implementation • 1 Oct 2019 • S Chandra Mouli, Leonardo Teixeira, Jennifer Neville, Bruno Ribeiro
The goal of lifetime clustering is to develop an inductive model that maps subjects into $K$ clusters according to their underlying (unobserved) lifetime distribution.
no code implementations • ICLR 2018 • S Chandra Mouli, Bruno Ribeiro, Jennifer Neville
The goal of survival clustering is to map subjects (e. g., users in a social network, patients in a medical study) to $K$ clusters ranging from low-risk to high-risk.