13 citations · 15 across the 2 of their papers we have counts for
5 papers
Rethinking Tabular Foundation Models On Data Streams
Nilesh Verma, Daniel Nowak-Assis, Afonso Lourenço +4
Tabular foundation models (TFMs) outperform established machine learning models on tabular benchmarks through in-context learning. Building on this success, interest is growing in…
TuiML: Machine Learning for AI Agents
Nilesh Verma, Nick Lim, Albert Bifet +1
Machine-learning libraries such as Weka and scikit-learn were designed for human programmers. Language-model agents now use these same libraries by recalling APIs from memory and w…
Detecting Domain Shifts in Myoelectric Activations: Challenges and Opportunities in Stream Learning
Yibin Sun, Nick Lim, Guilherme Weigert Cassales +4
Detecting domain shifts in myoelectric activations poses a significant challenge due to the inherent non-stationarity of electromyography (EMG) signals. This paper explores the det…
A simple but strong baseline for online continual learning: Repeated Augmented Rehearsal
Yaqian Zhang, Bernhard Pfahringer, Eibe Frank +3
Online continual learning (OCL) aims to train neural networks incrementally from a non-stationary data stream with a single pass through data. Rehearsal-based methods attempt to ap…
Linear Dimensionality Reduction in Linear Time: Johnson-Lindenstrauss-type Guarantees for Random Subspace
Nick Lim, Robert J. Durrant
We consider the problem of efficient randomized dimensionality reduction with norm-preservation guarantees. Specifically we prove data-dependent Johnson-Lindenstrauss-type geometry…