The paper tackles a ranking and selection problem where a company learns from choice-based feedback presented in dynamic assortments. It introduces two efficient algorithms—Nested Elimination for best-item identification and Nested Partition for full-ranking identification—each with instance-specific, non-asymptotic sample-complexity guarantees that are asymptotically worst-case optimal. The authors analyze the algorithms via multi-dimensional random walks, extend the framework to capacity-constrained displays, and validate their results with synthetic and real data experiments.
By Junwen Yang, Yifan Feng
The paper investigates preference-based bandits where a learner selects pairs of arms and receives binary preference feedback modeled by Bradley–Terry. It introduces the locally sensitive eluder dimension, a new complexity measure for logistic preference feedback, and proposes the GINOP algorithm that uses log-loss confidence sets to balance optimism and exploration. The authors prove a first-order regret bound showing that learning with preference feedback can be as statistically efficient as learning from direct rewards, and they validate their theory with empirical experiments.
By Ahmed Ben Yahmed (CREST, ENSAE Paris, FAIRPLAY), Marc Abeille (FAIRPLAY), Cl\'ement Calauz\`enes (FAIRPLAY)
arXiv:2610.05220v2 Announce Type: replace
Abstract: Carousel interfaces allow a recommender system to directly observe how far a user has browsed. This signal distinguishes displayed but unclicked it...
By Takuma Yasuda, Atsuyoshi Nakamura, Dai Hai Nguyen
arXiv:2610. 29381v1 Announce Type: new Abstract: We propose a novel stochastic cascading bandit setup where probing an ordered shortlist of $K$ out of $L$ arms incurs position-dependent costs, and the learner observes only noisy feedback regarding each arm's true output.
By Yashaswini Kaluguri, Nikhil Karamchandani
arXiv:2607. 01715v1 Announce Type: new Abstract: Existing robust preference optimization for language-model alignment mainly studies pairwise supervision and places robustness at the dataset, prompt, or preference-pair level.
By Xudong Wu, Jian Qian, Pangpang Liu, Vaneet Aggarwal, Jiayu Chen
arXiv:2601.13885v2 Announce Type: replace-cross
Abstract: Computerized Adaptive Testing (CAT) has proven effective for efficient LLM evaluation on multiple-choice benchmarks, but modern LLM evaluatio...
By Esma Balk{\i}r, Alice Pernthaller, Marco Basaldella, Jos\'e Hern\'andez-Orallo, Nigel Collier
arXiv:2609.36740v1 Announce Type: new
Abstract: Many recommender systems such as for e-commerce and news platforms aim to provide users with rankings they are likely to interact with. Off-Policy Lear...
By Ren Kishimoto, Koichi Tanaka, Haruka Kiyohara, Yusuke Narita, Yasuo Yamamoto, Nobuyuki Shimizu, Yuta Saito
arXiv:2607. 08103v1 Announce Type: new Abstract: Rank estimation under label noise poses a fundamental challenge, as ordinal annotations often exhibit structured uncertainty rather than simple label corruption.
By Chaewon Lee, Seon-Ho Lee, Chang-Su Kim
The paper introduces a new online fair division framework where a learner must allocate indivisible items to agents in real time, balancing fairness and efficiency. Traditional methods rely on many copies of each item to estimate utilities, but this is unrealistic for platforms with many users and few interactions. By treating utility as an unknown function of item-agent features and framing the problem as a contextual bandit, the authors propose algorithms that achieve sublinear regret and demonstrate their effectiveness experimentally.
By Arun Verma, Indrajit Saha, Makoto Yokoo, Bryan Kian Hsiang Low
The paper introduces Adaptive Doubly Robust (ADR), an off‑policy evaluation method for ranking policies that blends adaptive importance weighting with reward regression to reduce variance. ADR is unbiased when the true user behavior model is known and, under a sufficient condition, achieves lower variance than the prior Adaptive Inverse Propensity Scoring (AIPS) approach. Experiments on synthetic data show that ADR consistently improves mean squared error over AIPS and other ranking OPE estimators across various data sizes and ranking lengths.
By Kosuke Iguchi, Ren Kishimoto
arXiv:2606. 26369v1 Announce Type: cross Abstract: Scoring functions are used to represent the relevance of individual documents.
By Shubham Singh, Ian A. Kash, Mesrob I. Ohannessian
The paper introduces a Bayesian Bradley‑Terry model (BBTM) that employs Polya‑Gamma data augmentation for efficient Gibbs sampling and quantifies uncertainty in latent abilities and ranks. Three active‑learning strategies based on the knowledge‑gradient principle are proposed, using Kendall’s tau distance, posterior rank entropy, and posterior separation as acquisition functions, with approximate one‑step updates to reduce computational cost. The authors also present Posterior Separation Reliability (PSR) as an internal indicator of ranking reliability, and demonstrate through synthetic experiments that BBTM outperforms preference‑based Bayesian comparative judgement, with the entropy‑based strategy excelling at low‑to‑moderate noise and the posterior‑separation strategy at high noise levels.
By Saman Jayasinghe, Sean Walton, Alma Rahat, Andy Gray, Chris Wheadon