Common Ground in Cooperative Communication

Authors: Xiaoran Hao, Yash Jhaveri, Patrick Shafto

NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Finally, we carry out a series of empirical simulations to support and elaborate on our theoretical results.
Researcher Affiliation Academia 1Department of Math and Computer Science, Rutgers University Newark 2School of Mathematics, Institute for Advanced Study, Princeton
Pseudocode No The paper does not contain any pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any concrete access to source code for the methodology.
Open Datasets No The paper describes generating data for its experiments (e.g., 'we assume that m = |D| and n = |H|, and we fix our common ground pair as follows: Pg = {g (d | h)g(h)} with g (d | h) = Cat(d | (h)) and g(h) = Cat(d | )' and 'g is a mixture of l Gaussians'), but it does not specify the use of a publicly available or open dataset with access information.
Dataset Splits No The paper does not specify explicit train/validation/test splits or reference predefined splits for a dataset. It describes 'sampling initializations for a gradient descent based optimization scheme' and mentions '50 initializations' or '100 initializations' but not specific data splits for validation.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments.
Software Dependencies No The paper mentions 'Py Torch via Adam (Kingma and Ba, 2015)' but does not provide specific version numbers for PyTorch or Adam.
Experiment Setup Yes We sample initializations for a gradient descent based optimization scheme of L ,δ, in Py Torch via Adam (Kingma and Ba, 2015), over (Pg f) from a pair of probability distributions and on the parameters and λ. ... we consider a multilayer perceptron-based form of common ground... We conduct experiments under various priors f and g and compare different initializations. We also analyze our model through variations on the coefficients and δ.