31 citations · 138 across the 17 of their papers we have counts for
18 papers
Spuriosity Didn't Kill the Classifier: Using Invariant Predictions to Harness Spurious Features
Cian Eastwood, Shashank Singh, Andrei Liviu Nicolicioiu +3
To avoid failures on out-of-distribution data, recent works have sought to extract features that have an invariant or stable relationship with the label across domains, discarding…
Probable Domain Generalization via Quantile Risk Minimization
Cian Eastwood, Alexander Robey, Shashank Singh +4
Domain generalization (DG) seeks predictors which perform well on unseen test distributions by leveraging data drawn from multiple related training distributions or domains. To ach…
Indirect Active Learning
Shashank Singh
Traditional models of active learning assume a learner can directly manipulate or query a covariate in order to study its relationship with a response . However, if is a…
Optimal Binary Classification Beyond Accuracy
Shashank Singh, Justin Khim
The vast majority of statistical theory on binary classification characterizes performance in terms of accuracy. However, accuracy is known in many cases to poorly reflect the prac…
Continuum-Armed Bandits: A Function Space Perspective
Shashank Singh
Continuum-armed bandits (a.k.a., black-box or -order optimization) involves optimizing an unknown objective function given an oracle that evaluates the function at a query…
Multiclass Classification via Class-Weighted Nearest Neighbors
Justin Khim, Ziyu Xu, Shashank Singh
We study statistical properties of the k-nearest neighbors algorithm for multiclass classification, with a focus on settings where the number of classes may be large and/or classes…