On Medians of (Randomized) Pairwise Means
Authors: Pierre Laforgue, Stephan Clemencon, Patrice Bertail
ICML 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Beyond theoretical results guaranteeing the performance of the learning/estimation methods proposed, some numerical experiments provide empirical evidence of their relevance in practice. |
| Researcher Affiliation | Academia | 1LTCI, T elecom Paris, Institut Polytechnique de Paris 2Modal X, UPL, Universit e Paris-Nanterre. |
| Pseudocode | No | The paper describes methods in prose and mathematical formulations but does not include any explicitly labeled pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not contain any explicit statements about releasing source code or provide links to a code repository. |
| Open Datasets | No | The paper discusses experiments on samples drawn from specified distributions (Gaussian, Student, Lognormal, Pareto) but does not mention the use of publicly available datasets with concrete access information (e.g., specific links, DOIs, or formal citations to established benchmarks). |
| Dataset Splits | No | The paper mentions generating samples of size n=1000 and running 5000 replications for experiments, but it does not specify any train/validation/test dataset splits, percentages, or absolute sample counts for data partitioning. |
| Hardware Specification | No | The paper does not specify any hardware details (e.g., CPU/GPU models, memory, or cloud computing resources) used to run the experiments. |
| Software Dependencies | No | The paper does not list any specific software components with version numbers (e.g., libraries, frameworks, or programming language versions) used for its implementation or experiments. |
| Experiment Setup | Yes | Considering inference of the expectation of four specified distributions (Gaussian, Student, Lognormal and Pareto), based on a sample of size n = 1000, seven estimators are compared below: standard Mo M, and six Mo RM estimators, related to different sampling schemes (SRSWo R, Monte-Carlo) or different values of the tuning parameter τ. Results are obtained through 5000 replications of the estimation procedures. Beyond the quadratic risk, accuracy of the estimators are assessed by means of deviation probabilities (see SM), i.e. empirical quantiles for a geometrical grid of confidence levels δ. |