Feature-Based Online Bilateral Trade

Authors: Solenne Gaucher, Martino Bernasconi, Matteo Castiglioni, Andrea Celli, Vianney Perchet

ICLR 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We characterize the regret regimes of different settings, taking as a baseline the best context-dependent prices in hindsight. First, in the setting in which the learner has two-bit feedback and strong budget balance constraints, we propose an algorithm with O(log T) regret. Then, we study the same set-up with noisy valuations, providing a tight e O(T 2/3) regret upper bound. Finally, we show that loosening budget balance constraints allows the learner to operate under more restrictive feedback.
Researcher Affiliation Collaboration The authors are affiliated with 'CMAP, École polytechnique, IPP', 'Bocconi University', 'Politecnico di Milano' (academic institutions) and 'Criteo AI Lab' (an industry lab), indicating a collaboration between academia and industry.
Pseudocode Yes The paper contains several algorithm blocks, explicitly labeled as 'Algorithm 1 ELLIPSOIDPRICING FOR BILATERAL TRADE (EP-BT)', 'Algorithm 2 ESTIMATION SUBROUTINES', 'Algorithm 3 EXPLORE-OR-COMMIT FOR BILATERAL TRADE (EOC-BT)', and 'Algorithm 4 SCOUTING BANDIT WITH INFORMATION POOLING (SBIP)'.
Open Source Code No The paper does not provide any explicit statements about open-sourcing code, links to repositories, or mentions of code in supplementary materials for the methodology described.
Open Datasets No The paper introduces a theoretical model: 'We introduce the feature-based online bilateral trade problem, in which the learner observes a feature vector xt Rd before posting prices for round t.' It does not mention the use of any specific publicly available datasets for experiments.
Dataset Splits No The paper is theoretical and focuses on algorithm design and regret analysis, not empirical experiments. Therefore, it does not provide any training/test/validation dataset splits.
Hardware Specification No The paper is theoretical, analyzing algorithms and their regret bounds. It does not describe empirical experiments or specify any hardware used for computations.
Software Dependencies No The paper is theoretical, providing algorithms and mathematical analysis. It does not specify any software dependencies with version numbers.
Experiment Setup No The paper is theoretical, focusing on the design and analysis of algorithms for feature-based online bilateral trade, including regret bounds. It does not describe any empirical experiments or provide details such as hyperparameters or system-level training settings.