From the 1 of 7 linked papers with an AI index.
7 papers
The Challenger: When Do New Data Sources Justify Switching Machine Learning Models?
Vassilis Digalakis, Christophe Pérignon, Sébastien Saurin +1
The paper proposes a framework for deciding when to replace an existing predictive model with a new one that uses additional data features, linking learning‑curve dynamics to the e…
Flexibility allocation in random bipartite matching markets: exact matching rates and dominance regimes
Taha Ameen, Flore Sentenac, Sophie H. Yu
This paper studies how a fixed flexibility budget should be allocated across the two sides of a balanced bipartite matching market. We model compatibilities via a sparse bipartite…
On the Average-Case Performance of Greedy for Maximum Coverage
Eric Balkanski, Jason Chatzitheodorou, Flore Sentenac
For the classical maximum coverage problem, the greedy algorithm achieves a worst-case approximation, which is optimal unless . The notion of coverage…
A uniformity principle for spatial matching
Taha Ameen, Flore Sentenac, Sophie H. Yu
Platforms matching spatially distributed supply to demand face a fundamental design choice: given a fixed total budget of service range, how should it be allocated across supply no…
Balancing optimism and pessimism in offline-to-online learning
Flore Sentenac, Ilbin Lee, Csaba Szepesvari
We consider what we call the offline-to-online learning setting, focusing on stochastic finite-armed bandit problems. In offline-to-online learning, a learner starts with offline d…
Online Matching in Geometric Random Graphs
Flore Sentenac, Nathan Noiry, Matthieu Lerasle +2
We investigate online maximum cardinality matching, a central problem in ad allocation. In this problem, users are revealed sequentially, and each new user can be paired with any p…