AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Common Ground in Cooperative Communication

Xiaoran Hao, Yash Jhaveri, Patrick Shafto

NeurIPS 2023 · Probabilistic and scientific modeling › Molecules and proteins · approach: Counterfactual and statistical explanations · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use sparse initialization (p=0.5) instead of uniform initialization (p=0.0625)MLP-based common ground, eps=1, delta=0 · Fully discrete, varying mcooperative indexImproved
run with eps=1 and several random initializationsMLP-based common ground · Fully discrete, varying mpairwise l1-distance between minimizersHurt
increase eps from 0 toward 1MLP-based common ground · Fully discrete, m=20l1-distance between teacher and learner plansImproved
increase eps from 0 toward 1MLP-based common ground · Fully discrete, m=20cooperative indexImproved
increase initialization range p from 0.01 to 0.8Variational cooperative communication, 3-Gaussian g, eps=1, delta=10 · Semi-continuousaverage reconstruction lossHurt
increase initialization range p from 0.01 to 0.8Variational cooperative communication, 3-Gaussian g, eps=1, delta=10 · Semi-continuousdata activation percentageHurt
vary eps across values around 1Variational cooperative communication · Semi-continuous, 1/3/5 Gaussiansaverage reconstruction lossMixed
vary deltaVariational cooperative communication · Semi-continuous, 1/3/5 Gaussiansdata activation percentageNo clear effect
vary deltaVariational cooperative communication · Semi-continuous, 1/3/5 Gaussiansaverage reconstruction lossNo clear effect
increase number of Gaussians in teacher prior g from 1 to 5Variational cooperative communication · Semi-continuousoptimal eps locationMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy