Tight Bounds for Approximate Carathéodory and Beyond

Authors: Vahab Mirrokni, Renato Paes Leme, Adrian Vladu, Sam Chiu-wai Wong

ICML 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We illustrate the performance of our algorithm in two numerical experiments, presented in the figure below. We ran both the original sampling algorithm (Barman, 2015; Pisier, 1980) (where vertices are sampled from an exact convex combination) and our deterministic mirror-descent based algorithm on 100 instances.
Researcher Affiliation Collaboration 1Google Research, New York, NY, USA 2MIT, Cambridge, MA, USA 3UC Berkeley, Berkeley, CA, USA.
Pseudocode Yes zt+1 = zt rf(yt) yt+1 = r! (zt+1) (MD)
Open Source Code No The paper does not contain any statement or link indicating that the source code for the described methodology is publicly available.
Open Datasets No The paper states that instances were "obtained by sampling a 1000 1000 Gaussian matrix, then scaling each column by the maximum 2 (respectively 8) column norm," indicating synthetically generated data rather than a publicly accessible dataset with concrete access information.
Dataset Splits No The paper mentions running experiments on "100 instances" but does not specify how data was split into training, validation, or test sets with percentages, sample counts, or predefined citations.
Hardware Specification No The paper does not specify any hardware details like GPU/CPU models, processor types, or memory used for running the experiments.
Software Dependencies No The paper does not list specific software dependencies with version numbers (e.g., library or solver names with versions like Python 3.8, CPLEX 12.4) needed to replicate the experiment.
Experiment Setup No The paper describes how the input data instances were generated (e.g., "sampling a 1000 1000 Gaussian matrix"), but it does not provide specific experimental setup details such as hyperparameter values (learning rates, batch sizes) or optimizer settings.