activity
20242026
collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2025

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…

cs.LG2025

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…

cs.LG2024

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…

cs.LG2024

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…

cs.LG2024

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…