no code implementations • ACL 2022 • Ryan Steed, Swetasudha Panda, Ari Kobren, Michael Wick
A few large, homogenous, pre-trained models undergird many machine learning systems — and often, these models contain harmful stereotypes learned from the internet.
no code implementations • ICLR Workshop EBM 2021 • Hao Wu, Babak Esmaeili, Michael Wick, Jean-Baptiste Tristan, Jan-Willem van de Meent
In this paper, we propose conjugate energy-based models (CEBMs), a new class of energy-based models that define a joint density over data and latent variables.
no code implementations • NeurIPS 2019 • Michael Wick, Swetasudha Panda, Jean-Baptiste Tristan
The prevailing wisdom is that a model's fairness and its accuracy are in tension with one another.
no code implementations • AKBC 2019 • Michael Wick, Swetasudha Panda, Joseph Tassarotti, Jean-Baptiste Tristan
In this case, we need the representation to be a homomorphism so that the hash of unions and differences of sets can be computed directly from the hashes of operands.
no code implementations • 2 Oct 2018 • Joseph Tassarotti, Jean-Baptiste Tristan, Michael Wick
We examine a related problem in which the parameters of a Bayesian model are very large and expensive to store in memory, and propose more compact representations of parameter values that can be used during inference.
no code implementations • 26 Jul 2017 • Jay Yoon Lee, Sanket Vaibhav Mehta, Michael Wick, Jean-Baptiste Tristan, Jaime Carbonell
Practitioners apply neural networks to increasingly complex problems in natural language processing, such as syntactic parsing and semantic role labeling that have rich output structures.