activity
20182026
most citedGradient descent with momentum --- to accelerate or to super-accelerate?

5 citations · 6 across the 3 of their papers we have counts for

collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2026

Tabular foundation models for non-tabular tasks

Goran Nakerst, John Brennan, Wouter Beugeling +1

Tabular foundation models (TFMs) have recently emerged as a promising paradigm for machine learning on tabular data, offering the ability to generalize across datasets without task…

cs.LG2020

Not Half Bad: Exploring Half-Precision in Graph Convolutional Neural Networks

John Brennan, Stephen Bonner, Amir Atapour-Abarghouei +3

With the growing significance of graphs as an effective representation of data in numerous applications, efficient graph analysis using modern machine learning is receiving a growi…

cs.LG20205 cited

Gradient descent with momentum --- to accelerate or to super-accelerate?

Goran Nakerst, John Brennan, Masudul Haque

We consider gradient descent with `momentum', a widely used method for loss function minimization in machine learning. This method is often used with `Nesterov acceleration', meani…

cs.LG2018

Predicting the Computational Cost of Deep Learning Models

Daniel Justus, John Brennan, Stephen Bonner +1

Deep learning is rapidly becoming a go-to tool for many artificial intelligence problems due to its ability to outperform other approaches and even humans at many problems. Despite…

cs.LG2018

Exploring the Semantic Content of Unsupervised Graph Embeddings: An Empirical Study

Stephen Bonner, Ibad Kureshi, John Brennan +3

Graph embeddings have become a key and widely used technique within the field of graph mining, proving to be successful across a broad range of domains including social, citation,…