Convergence Analysis of Prediction Markets via Randomized Subspace Descent

Authors: Rafael Frongillo, Mark D. Reid

NeurIPS 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In this paper we show how some previously studied prediction market trading models can be understood as a natural generalization of randomized coordinate descent which we call randomized subspace descent (RSD). We establish convergence rates for RSD and leverage them to prove rates for the two prediction market models above, answering the open questions. Our results extend beyond standard centralized markets to arbitrary trade networks. Figure 1: Average (in bold) of 30 market simulations for the complete and star graphs. The empirical gap in iteration complexity is just under 2 (cf. Fig. 3).
Researcher Affiliation Academia Rafael Frongillo Department of Computer Science University of Colorado, Boulder raf@colorado.edu Mark D. Reid Research School of Computer Science The Australian National University & NICTA mark.reid@anu.edu.au
Pseudocode Yes ALGORITHM 1: Randomized Subspace Descent
Open Source Code No The paper does not provide any links to source code or explicit statements about its availability for the methodology described.
Open Datasets No The paper discusses "market simulations for the complete and star graphs" and shows an "Average... of 30 market simulations" in Figure 1. This indicates a simulation-based approach rather than the use of a traditional publicly available dataset.
Dataset Splits No The paper does not specify any training, validation, or test dataset splits. Its empirical analysis is based on simulations rather than traditional machine learning dataset evaluation.
Hardware Specification No The paper does not provide any specific hardware details (e.g., GPU/CPU models, memory, cloud resources) used for running its simulations or experiments.
Software Dependencies No The paper does not specify any software dependencies with version numbers (e.g., Python, PyTorch, specific solvers) that would be needed to reproduce the experimental setup.
Experiment Setup No The paper mentions "30 market simulations" but does not provide specific experimental setup details such as hyperparameters, optimization settings, or other configuration specifics that would be required for reproduction.