1 code implementation • 29 Feb 2024 • Benjamin Cohen-Wang, Joshua Vendrow, Aleksander Madry
In particular, we focus on two possible failure modes of models under distribution shift: poor extrapolation (e. g., they cannot generalize to a different domain) and biases in the training data (e. g., they rely on spurious features).
1 code implementation • 11 Dec 2023 • Kristian Georgiev, Joshua Vendrow, Hadi Salman, Sung Min Park, Aleksander Madry
Then, we provide a method for computing these attributions efficiently.
no code implementations • 28 Feb 2023 • Tyler Will, Runyu Zhang, Eli Sadovnik, Mengdi Gao, Joshua Vendrow, Jamie Haddock, Denali Molitor, Deanna Needell
We introduce a new method based on nonnegative matrix factorization, Neural NMF, for detecting latent hierarchical structure in data.
1 code implementation • 15 Feb 2023 • Joshua Vendrow, Saachi Jain, Logan Engstrom, Aleksander Madry
In this work, we introduce the notion of a dataset interface: a framework that, given an input dataset and a user-specified shift, returns instances from that input distribution that exhibit the desired shift.
1 code implementation • 28 Aug 2022 • Elena Sizikova, Joshua Vendrow, Xu Cao, Rachel Grotheer, Jamie Haddock, Lara Kassab, Alona Kryshchenko, Thomas Merkh, R. W. M. A. Madushani, Kenny Moise, Annie Ulichney, Huy V. Vo, Chuntian Wang, Megan Coffee, Kathryn Leonard, Deanna Needell
Automatic infectious disease classification from images can facilitate needed medical diagnoses.
1 code implementation • 30 Sep 2021 • Joshua Vendrow, Jamie Haddock, Deanna Needell
Hierarchical NTF (HNTF) methods have been proposed, however these methods do not naturally generalize their matrix-based counterparts.
no code implementations • 28 Apr 2021 • Ryan Budahazy, Lu Cheng, Yihuan Huang, Andrew Johnson, Pengyu Li, Joshua Vendrow, Zhoutong Wu, Denali Molitor, Elizaveta Rebrova, Deanna Needell
The California Innocence Project (CIP), a clinical law school program aiming to free wrongfully convicted prisoners, evaluates thousands of mails containing new requests for assistance and corresponding case files.
2 code implementations • 13 Feb 2021 • Hanbaek Lyu, Yacoub H. Kureh, Joshua Vendrow, Mason A. Porter
It is common to use networks to encode the architecture of interactions between entities in complex systems in the physical, biological, social, and information sciences.
no code implementations • 1 Jan 2021 • Joshua Vendrow, Jamie Haddock, Deanna Needell
We propose a new hierarchical nonnegative CANDECOMP/PARAFAC (CP) decomposition (hierarchical NCPD) model and a training method, Neural NCPD, for performing hierarchical topic modeling on multi-modal tensor data.
1 code implementation • 28 Dec 2020 • Hardeep Bassi, Richard Yim, Rohith Kodukula, Joshua Vendrow, Cherlin Zhu, Hanbaek Lyu
However, in the problem setting where these graph statistics cannot distinguish the two classes very well (e. g., when the graphs are generated from the same random graph model), we find that pairing a few iterations of the initial dynamics along with the graph statistics as the input to our classification algorithms can lead to significant improvement in accuracy; far exceeding what is known by the classical oscillator theory.
1 code implementation • 22 Oct 2020 • Joshua Vendrow, Jamie Haddock, Elizaveta Rebrova, Deanna Needell
Fully unsupervised topic models have found fantastic success in document clustering and classification.
no code implementations • 24 Aug 2020 • Joshua Vendrow, Jamie Haddock, Deanna Needell, Lorraine Johnson
We first analyze the general performance of the model and then identify the most important features for predicting participant answers to GROC.