AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

Train 'n Trade: Foundations of Parameter Markets

Tzu-Heng Huang, Harit Vishwakarma, Frederic Sala

NeurIPS 2023 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Boundedly rational agent modeling · 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
add parameter trading with alignment vs separate trainingResNet20 · TinyImageNettesting accuracy: +10.02% and +15.93%Improved
add model alignment before merging (ablation)parameter trading · MNIST + MLPtesting accuracy: 84.64% -> 86.96%Improved
add model alignment before merging (ablation)parameter trading · CIFAR10 + ResNet20testing accuracy: 78.31% -> 79.90%Improved
add model alignment before merging (ablation)parameter trading · TinyImageNet + ResNet20testing accuracy: 31.28% -> 31.69%Improved
replace broker-assisted merge with FedAvgparameter trading · CIFAR10 + ResNet20testing accuracy: 79.90% -> 70.35%Hurt
replace broker-assisted merge with FedAvgparameter trading · TinyImageNet + ResNet20testing accuracy: 31.69% -> 19.95%Hurt
FedAvg vs out-of-market trainingFedAvg · MNIST + MLPtesting accuracy: 68.50% -> 81.98%Improved
trade only deep layers {3, 4} (ablation)MLP parameter trading · MNIST + MLPtesting accuracy: 71.29% -> 66.28%Hurt
trade shallow layers {0, 1} instead of deep layers {3, 4} (ablation)MLP parameter trading · MNIST + MLPtesting accuracy: 66.28% -> 78.86%Improved
trade all layers instead of a subset {0, 1} (ablation)MLP parameter trading · MNIST + MLPtesting accuracy: 78.86% -> 86.96%Improved
add parameter trading vs out-of-marketlinear regression · synthetictesting loss: 42.84% and 23.88% lower loss for agents A and BImproved
trade parameters across more distant taskslinear regression · synthetic different tasksrelative testing loss improvementMixed

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