Avoiding Imposters and Delinquents: Adversarial Crowdsourcing and Peer Prediction

Authors: Jacob Steinhardt, Gregory Valiant, Moses Charikar

NeurIPS 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical Our technical tools draw on semidefinite programming methods for matrix completion... The proof of Theorem 2 can be split into two parts: analyzing Algorithm 1 (Section 4), and analyzing Algorithm 2 (Section 5). Proving Proposition 1 involves two major steps... Lemma 1. Let m n. Suppose that Assumption 1 holds. Lemma 2. Let m n. Then there is a k = O log3(2/δ) n such that... Lemma 3. Let i be the row selected in Algorithm 2. Suppose that r satisfies Assumption 1. Lemma 4. The output T of Algorithm 4 satisfies E[T] = T0, T 0 βm.
Researcher Affiliation Academia Jacob Steinhardt Stanford University Gregory Valiant Stanford University Moses Charikar Stanford University
Pseudocode Yes Algorithm 1 Algorithm for recovering β-quantile matrix M using (unreliable) ratings A. Algorithm 2 Algorithm for recovering an accurate β-quantile T from the β-quantile matrix M. Algorithm 3 Algorithm for obtaining (unreliable) ratings matrix A and noisy ratings r, r . Algorithm 4 Randomized rounding algorithm.
Open Source Code No No statement regarding the release of open-source code for the described methodology was found. No links to repositories or mentions of supplementary materials containing code were present.
Open Datasets No The paper is theoretical and describes a model with 'n workers' and 'm items' but does not specify or use any particular dataset for empirical evaluation, nor does it provide access information for any dataset.
Dataset Splits No This paper is theoretical and does not involve empirical data or experiments, therefore there is no mention of dataset splits for training, validation, or testing.
Hardware Specification No This paper is theoretical and does not describe any empirical experiments, thus no hardware specifications for running experiments are mentioned.
Software Dependencies No This paper is theoretical and does not describe any empirical experiments or implementations, thus no software dependencies with version numbers are mentioned.
Experiment Setup No This paper is theoretical and does not describe any empirical experiments, thus no experimental setup details like hyperparameters or training settings are provided.