Pareto-Optimality, Smoothness, and Stochasticity in Learning-Augmented One-Max-Search
Authors: Ziyad Benomar, Lorenzo Croissant, Vianney Perchet, Spyros Angelopoulos
ICML 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We validate our theoretical results through numerical experiments, in which we compare our algorithm to the state of the art, by testing it under both synthetic and real data. |
| Researcher Affiliation | Academia | 1CREST, ENSAE, Palaiseau, France 2INRIA Fairplay joint team, Palaiseau, France 3Criteo AI Lab, Paris, France 4CNRS and International Laboratory on Learning Systems, Montreal, Canada. Correspondence to: Ziyad Benomar <EMAIL>. |
| Pseudocode | No | The paper describes algorithms using mathematical formulations and descriptive text, such as "the proposed algorithms select the first price that exceeds a threshold Φ(y)", but does not include a clearly labeled pseudocode or algorithm block. |
| Open Source Code | No | The paper does not contain any explicit statements about open-sourcing its code or provide any links to a code repository for the methodology described. |
| Open Datasets | No | The paper mentions using 'real Bitcoin data (USD) recorded every minute from the beginning of 2020 to the end of 2024' but does not provide a specific link, DOI, repository name, or formal citation for accessing this dataset. |
| Dataset Splits | No | The paper describes a simulation setup involving randomly sampled 10-week windows of prices and a process of generating predictions, but it does not specify explicit training/test/validation dataset splits with percentages, sample counts, or predefined partition references. |
| Hardware Specification | No | The paper does not provide any specific hardware details such as GPU models, CPU models, or cloud computing instance types used for running the experiments. |
| Software Dependencies | No | The paper does not provide specific ancillary software details, such as library or solver names with version numbers, that would be needed to replicate the experiment. |
| Experiment Setup | Yes | We fix θ = 5, λ = 0.5, and r = θ (1 λ/2). We randomly sample a 10-week window of prices W0... To simulate worst-case scenarios, the last price in W0 is changed to L with a probability of 0.75. For each value of α, we sample m = 100 windows... We choose the robustness r of Aρ r by setting λ [0, 1] and r = θ (1 λ/2). |