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 • 24 Mar 2023 • Rafael Frongillo, Manuel Lladser, Anish Thilagar, Bo Waggoner
We initiate the study of forecasting competitions for correlated events.
no code implementations • 7 Nov 2022 • Rafael Frongillo, Dhamma Kimpara, Bo Waggoner
The characterization rules out a loss whose expectation is the cross-entropy between the target distribution and the model.
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 • NeurIPS 2021 • Rafael Frongillo, Bo Waggoner
Surrogate risk minimization is an ubiquitous paradigm in supervised machine learning, wherein a target problem is solved by minimizing a surrogate loss on a dataset.
no code implementations • NeurIPS 2021 • Jessica Finocchiaro, Rafael Frongillo, Bo Waggoner
The convex consistency dimension of a supervised learning task is the lowest prediction dimension $d$ such that there exists a convex surrogate $L : \mathbb{R}^d \times \mathcal Y \to \mathbb R$ that is consistent for the given task.
no code implementations • 18 Feb 2021 • Bo Waggoner
This note investigates functions from $\mathbb{R}^d$ to $\mathbb{R} \cup \{\pm \infty\}$ that satisfy axioms of linearity wherever allowed by extended-value arithmetic.
Statistics Theory Computer Science and Game Theory Statistics Theory
no code implementations • 16 Feb 2021 • Rafael Frongillo, Robert Gomez, Anish Thilagar, Bo Waggoner
Winner-take-all competitions in forecasting and machine-learning suffer from distorted incentives.
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 • 19 Oct 2020 • Ariel Avital, Klim Efremenko, Aryeh Kontorovich, David Toplin, Bo Waggoner
We propose a non-parametric variant of binary regression, where the hypothesis is regularized to be a Lipschitz function taking a metric space to [0, 1] and the loss is logarithmic.
no code implementations • 16 Jul 2020 • Zhiyuan Liu, Huazheng Wang, Bo Waggoner, Youjian, Liu, Lijun Chen
We investigate the sparse linear contextual bandit problem where the parameter $\theta$ is sparse.
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.
1 code implementation • 16 Jul 2019 • Justin D. Harris, Bo Waggoner
Machine learning has recently enabled large advances in artificial intelligence, but these tend to be highly centralized.
no code implementations • NeurIPS 2019 • Nika Haghtalab, Cameron Musco, Bo Waggoner
We aim to understand this fact, taking an axiomatic approach to the design of loss functions for learning distributions.
1 code implementation • NeurIPS 2019 • Yahav Bechavod, Katrina Ligett, Aaron Roth, Bo Waggoner, Zhiwei Steven Wu
We study an online classification problem with partial feedback in which individuals arrive one at a time from a fixed but unknown distribution, and must be classified as positive or negative.
no code implementations • 27 Feb 2018 • Rafael Frongillo, Nishant A. Mehta, Tom Morgan, Bo Waggoner
Recent work introduced loss functions which measure the error of a prediction based on multiple simultaneous observations or outcomes.
no code implementations • NeurIPS 2018 • Matthew Joseph, Aaron Roth, Jonathan Ullman, Bo Waggoner
Moreover, existing techniques to mitigate this effect do not apply in the "local model" of differential privacy that these systems use.
no code implementations • NeurIPS 2018 • Sampath Kannan, Jamie Morgenstern, Aaron Roth, Bo Waggoner, Zhiwei Steven Wu
Bandit learning is characterized by the tension between long-term exploration and short-term exploitation.
no code implementations • NeurIPS 2017 • Katrina Ligett, Seth Neel, Aaron Roth, Bo Waggoner, Steven Z. Wu
Traditional approaches to differential privacy assume a fixed privacy requirement ε for a computation, and attempt to maximize the accuracy of the computation subject to the privacy constraint.
no code implementations • 22 Oct 2017 • Jinshuo Dong, Aaron Roth, Zachary Schutzman, Bo Waggoner, Zhiwei Steven Wu
We study an online linear classification problem, in which the data is generated by strategic agents who manipulate their features in an effort to change the classification outcome.
no code implementations • 5 Jun 2017 • Sebastian Casalaina-Martin, Rafael Frongillo, Tom Morgan, Bo Waggoner
We study loss functions that measure the accuracy of a prediction based on multiple data points simultaneously.
1 code implementation • 30 May 2017 • Katrina Ligett, Seth Neel, Aaron Roth, Bo Waggoner, Z. Steven Wu
Traditional approaches to differential privacy assume a fixed privacy requirement $\epsilon$ for a computation, and attempt to maximize the accuracy of the computation subject to the privacy constraint.
no code implementations • NeurIPS 2015 • Bo Waggoner, Rafael Frongillo, Jacob D. Abernethy
We propose a mechanism for purchasing information from a sequence of participants. The participants may simply hold data points they wish to sell, or may have more sophisticated information; either way, they are incentivized to participate as long as they believe their data points are representative or their information will improve the mechanism's future prediction on a test set. The mechanism, which draws on the principles of prediction markets, has a bounded budget and minimizes generalization error for Bregman divergence loss functions. We then show how to modify this mechanism to preserve the privacy of participants' information: At any given time, the current prices and predictions of the mechanism reveal almost no information about any one participant, yet in total over all participants, information is accurately aggregated.
no code implementations • 20 Feb 2015 • Jacob Abernethy, Yi-Ling Chen, Chien-Ju Ho, Bo Waggoner
Our results in a sense parallel classic sample complexity guarantees, but with the key resource being money rather than quantity of data: With a budget constraint $B$, we give robust risk (predictive error) bounds on the order of $1/\sqrt{B}$.
no code implementations • 7 Dec 2014 • Bo Waggoner
For $p > 1$, we can learn and test with a number of samples that is independent of the support size of the distribution: With an $\ell_p$ tolerance $\epsilon$, $O(\max\{ \sqrt{1/\epsilon^q}, 1/\epsilon^2 \})$ samples suffice for testing uniformity and $O(\max\{ 1/\epsilon^q, 1/\epsilon^2\})$ samples suffice for learning, where $q=p/(p-1)$ is the conjugate of $p$.