8 papers
The Weight Gram Matrix Captures Sequential Feature Linearization in Deep Networks
Taehun Cha, Daniel Beaglehole, Adityanarayanan Radhakrishnan +1
Understanding how deep neural networks learn representations remains a central challenge in machine learning theory. In this work, we propose a feature-centric framework for analyz…
Contextual Linear Activation Steering of Language Models
Brandon Hsu, Daniel Beaglehole, Adityanarayanan Radhakrishnan +1
Linear activation steering is a powerful approach for eliciting the capabilities of large language models and specializing their behavior using limited labeled data. While effectiv…
xRFM: Accurate, scalable, and interpretable feature learning models for tabular data
Daniel Beaglehole, David Holzmüller, Adityanarayanan Radhakrishnan +1
Inference from tabular data, collections of continuous and categorical variables organized into matrices, is a foundation for modern technology and science. Yet, in contrast to the…
Steering Autoregressive Music Generation with Recursive Feature Machines
Daniel Zhao, Daniel Beaglehole, Taylor Berg-Kirkpatrick +2
Controllable music generation remains a significant challenge, with existing methods often requiring model retraining or introducing audible artifacts. We introduce MusicRFM, a fra…
DANCE: Doubly Adaptive Neighborhood Conformal Estimation
Brandon R. Feng, Brian J. Reich, Daniel Beaglehole +7
The recent developments of complex deep learning models have led to unprecedented ability to accurately predict across multiple data representation types. Conformal prediction for…
Emergence in non-neural models: grokking modular arithmetic via average gradient outer product
Neil Mallinar, Daniel Beaglehole, Libin Zhu +3
Neural networks trained to solve modular arithmetic tasks exhibit grokking, a phenomenon where the test accuracy starts improving long after the model achieves 100% training accura…