1 citations · 3 across the 6 of their papers we have counts for
11 papers
Narrowing the Collaboration Gap, Probably
Mirah Shi, Marcel Hussing, Ira Globus-Harris +3
Large language models are increasingly deployed as teams of agents that hold different private information about a shared task. How should such agents concisely communicate in a wa…
Augmented Feature Boosting for Multicalibration
Ira Globus-Harris, Inbal Livni Navon
Multicalibration requires a predictor's residuals to be unbiased not only globally, but also after conditioning on the predictor's own level sets and reweighting by a rich class of…
Collaborative Prediction: Tractable Information Aggregation via Agreement
Natalie Collina, Ira Globus-Harris, Surbhi Goel +3
We give efficient "collaboration protocols" through which two parties, who observe different features about the same instances, can interact to arrive at predictions that are more…
Model Ensembling for Constrained Optimization
Ira Globus-Harris, Varun Gupta, Michael Kearns +1
There is a long history in machine learning of model ensembling, beginning with boosting and bagging and continuing to the present day. Much of this history has focused on combinin…
Diversified Ensembling: An Experiment in Crowdsourced Machine Learning
Ira Globus-Harris, Declan Harrison, Michael Kearns +2
Crowdsourced machine learning on competition platforms such as Kaggle is a popular and often effective method for generating accurate models. Typically, teams vie for the most accu…
Multicalibration as Boosting for Regression
Ira Globus-Harris, Declan Harrison, Michael Kearns +2
We study the connection between multicalibration and boosting for squared error regression. First we prove a useful characterization of multicalibration in terms of a ``swap regret…
Multicalibrated Regression for Downstream Fairness
Ira Globus-Harris, Varun Gupta, Christopher Jung +3
We show how to take a regression function that is appropriately ``multicalibrated'' and efficiently post-process it into an approximately error minimizing classifier sati…
An Algorithmic Framework for Bias Bounties
Ira Globus-Harris, Michael Kearns, Aaron Roth
We propose and analyze an algorithmic framework for "bias bounties": events in which external participants are invited to propose improvements to a trained model, akin to bug bount…
Non-parametric Differentially Private Confidence Intervals for the Median
Joerg Drechsler, Ira Globus-Harris, Audra McMillan +2
Differential privacy is a restriction on data processing algorithms that provides strong confidentiality guarantees for individual records in the data. However, research on proper…
Lexicographically Fair Learning: Algorithms and Generalization
Emily Diana, Wesley Gill, Ira Globus-Harris +3
We extend the notion of minimax fairness in supervised learning problems to its natural conclusion: lexicographic minimax fairness (or lexifairness for short). Informally, given a…
Improved Differentially Private Analysis of Variance
Marika Swanberg, Ira Globus-Harris, Iris Griffith +3
Hypothesis testing is one of the most common types of data analysis and forms the backbone of scientific research in many disciplines. Analysis of variance (ANOVA) in particular is…