5 papers
Sample Complexity of Peer Prediction
Abdellah Aznag, Robin Bowers, Rachel Cummings +3
Peer prediction seeks to incentivize agents to truthfully report an observed signal by rewarding joint sets of reports without observing a ground truth. Following the generalizatio…
A Complexity Measure for Active Learning in Multi-group Mean Estimation
Abdellah Aznag, Rachel Cummings, Adam N. Elmachtoub
We study a \emph{max-risk} objective for active learning in a multi-group mean estimation -armed bandits: a learner adaptively allocates a budget of samples across group…
An active learning framework for multi-group mean estimation
Abdellah Aznag, Rachel Cummings, Adam N. Elmachtoub
We study a fundamental learning problem over multiple groups with unknown data distributions, where an analyst would like to learn the mean of each group. Moreover, we want to ensu…
MNL-Bandit with Knapsacks: a near-optimal algorithm
Abdellah Aznag, Vineet Goyal, Noemie Perivier
We consider a dynamic assortment selection problem where a seller has a fixed inventory of substitutable products and faces an unknown demand that arrives sequentially over …
The tropicalization of the entropic barrier
Xavier Allamigeon, Abdellah Aznag, Stéphane Gaubert +1
The entropic barrier, studied by Bubeck and Eldan (Proc. Mach. Learn. Research, 2015), is a self-concordant barrier with asymptotically optimal self-concordance parameter. In this…