Learning Populations of Parameters

Authors: Kevin Tian, Weihao Kong, Gregory Valiant

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

Reproducibility Variable Result LLM Response
Research Type Experimental 3 Empirical performance We begin by demonstrating the effectiveness of our algorithm on several synthetic datasets.
Researcher Affiliation Academia Kevin Tian, Weihao Kong, and Gregory Valiant Department of Computer Science Stanford University Stanford, CA, 94305 (kjtian, whkong, valiant)@stanford.edu
Pseudocode Yes Algorithms 1 and 2: Distribution Recovery with Linear / Quadratic Objectives
Open Source Code No No statement providing concrete access to source code for the methodology was found.
Open Datasets No The paper mentions several datasets (synthetic, flight delay, dog litters from Norwegian Kennel Club, political data, NBA player data) but does not provide specific links, DOIs, repositories, or formal citations with authors and years for their public availability.
Dataset Splits No The paper describes experiments on synthetic and real-world datasets but does not specify any training, validation, or test dataset splits (e.g., percentages, sample counts, or cross-validation setup).
Hardware Specification No No specific hardware details (e.g., GPU/CPU models, memory amounts, or cloud instances) used for running the experiments were mentioned.
Software Dependencies No No specific software dependencies with version numbers (e.g., library names like PyTorch 1.9, or solver versions like CPLEX 12.4) were mentioned.
Experiment Setup No The paper describes the algorithms and their empirical application, but it does not provide specific experimental setup details such as hyperparameter values (e.g., learning rate, batch size) or specific configurations for the optimization problems beyond the general objective functions and the use of an ϵ-net.