works on
data pooling 1decision theory 1geometry regularization 1gram matrix 1model auditing 1preference reversal 1

From the 1 of 1 linked paper with an AI index.

collaborators
Showing stat.MLShow all

1 paper · 1 filter

stat.ML2026

More Data, Worse Decisions? Preference Reversals in Neural Networks under Gram Incompatibility

Yanli Yan, Yuanzheng Li, Yong Zhao +2

The paper investigates how pooling data from different sources can cause neural networks with OLS output heads to reverse previously agreed-upon preferences, and proposes geometric…