5 papers · 1 filter
auto-fpt: Automating Free Probability Theory Calculations for Machine Learning Theory
Arjun Subramonian, Elvis Dohmatob
A large part of modern machine learning theory often involves computing the high-dimensional expected trace of a rational expression of large rectangular random matrices. To symbol…
An Effective Theory of Bias Amplification
Arjun Subramonian, Samuel J. Bell, Levent Sagun +1
Machine learning models can capture and amplify biases present in data, leading to disparate test performance across social groups. To better understand, evaluate, and mitigate the…
Theoretical and Empirical Insights into the Origins of Degree Bias in Graph Neural Networks
Arjun Subramonian, Jian Kang, Yizhou Sun
Graph Neural Networks (GNNs) often perform better for high-degree nodes than low-degree nodes on node classification tasks. This degree bias can reinforce social marginalization by…
Strong Model Collapse
Elvis Dohmatob, Yunzhen Feng, Arjun Subramonian +1
Within the scaling laws paradigm, which underpins the training of large neural networks like ChatGPT and Llama, we consider a supervised regression setting and establish the exista…
Networked Inequality: Preferential Attachment Bias in Graph Neural Network Link Prediction
Arjun Subramonian, Levent Sagun, Yizhou Sun
Graph neural network (GNN) link prediction is increasingly deployed in citation, collaboration, and online social networks to recommend academic literature, collaborators, and frie…