15 papers
Two-Sided Time-Independent Regret for Matching Markets with Limited Interviews
Amirmahdi Mirfakhar, Xuchuang Wang, Mengfan Xu +2
Two-sided matching platforms rely on preferences from both sides, yet participants can evaluate only a small fraction of potential partners. In practice, they use low-cost pre-matc…
Unlearning Offline Stochastic Multi-Armed Bandits
Zichun Ye, Runqi Wang, Xuchuang Wang +3
Machine unlearning aims to unlearn data points from a learned model, offering a principled way to process data-deletion requests and mitigate privacy risks without full retraining.…
The Secretary Problem with Predictions and a Chosen Order
Helia Karisani, Mohammadreza Daneshvaramoli, Hedyeh Beyhaghi +2
We study a learning-augmented variant of the secretary problem, recently introduced by Fujii and Yoshida (2023), in which the decision-maker has access to machine-learned predictio…
Online Learning to Rank under Corruption: A Robust Cascading Bandits Approach
Fatemeh Ghaffari, Siddarth Sitaraman, Xutong Liu +2
Online learning to rank (OLTR) studies how to recommend a short ranked list of items from a large pool and improves future rankings based on user clicks. This setting is commonly m…
Quantum Network Tomography for General Topology with SPAM Errors
Xuchuang Wang, Matheus Guedes De Andrade, Guus Avis +3
The goal of quantum network tomography (QNT) is the characterization of internal quantum channels in a quantum network from external peripheral operations. Prior research has prima…
Offline Clustering of Preference Learning with Active-data Augmentation
Jingyuan Liu, Fatemeh Ghaffari, Xuchuang Wang +3
Preference learning from pairwise feedback is a widely adopted framework in applications such as reinforcement learning with human feedback and recommendations. In many practical s…