no code implementations • 16 Feb 2024 • Enrique Nueve, Bo Waggoner, Dhamma Kimpara, Jessie Finocchiaro
We investigate ways to trade off surrogate loss dimension, the number of problem instances, and restricting the region of consistency in the simplex for multiclass classification.
no code implementations • 20 Sep 2023 • Jessie Finocchiaro
Predictive algorithms are often trained by optimizing some loss function, to which regularization functions are added to impose a penalty for violating constraints.
no code implementations • 18 Jul 2022 • Jessie Finocchiaro, Rafael Frongillo, Emma Goodwill, Anish Thilagar
For the proposed hinge-like surrogates that are convex (i. e., polyhedral), we apply the recent embedding framework of Finocchiaro et al. (2019; 2022) to determine the prediction problem for which the surrogate is consistent.
no code implementations • 29 Jun 2022 • Jessie Finocchiaro, Rafael M. Frongillo, Bo Waggoner
Using these results, we establish that indirect elicitation, a necessary condition for consistency, is also sufficient when working with polyhedral surrogates.
no code implementations • 16 Mar 2022 • Jessie Finocchiaro, Rafael Frongillo, Enrique Nueve
The Lov\'asz hinge is a convex surrogate recently proposed for structured binary classification, in which $k$ binary predictions are made simultaneously and the error is judged by a submodular set function.
no code implementations • NeurIPS 2021 • Jessie Finocchiaro, Rafael Frongillo, Bo Waggoner
Given a prediction task, understanding when one can and cannot design a consistent convex surrogate loss, particularly a low-dimensional one, is an important and active area of machine learning research.
no code implementations • 12 Oct 2020 • Jessie Finocchiaro, Roland Maio, Faidra Monachou, Gourab K Patro, Manish Raghavan, Ana-Andreea Stoica, Stratis Tsirtsis
Decision-making systems increasingly orchestrate our world: how to intervene on the algorithmic components to build fair and equitable systems is therefore a question of utmost importance; one that is substantially complicated by the context-dependent nature of fairness and discrimination.
no code implementations • NeurIPS 2019 • Jessie Finocchiaro, Rafael Frongillo, Bo Waggoner
Conversely, we show how to construct a consistent polyhedral surrogate for any given discrete loss.