5 papers · 1 filter
Estimating the expected output of wide random MLPs more efficiently than sampling
Wilson Wu, Victor Lecomte, Michael Winer +3
By far the most common way to estimate an expected loss in machine learning is to draw samples, compute the loss on each one, and take the empirical average. However, sampling is n…
Bayesian Influence Functions for Hessian-Free Data Attribution
Philipp Alexander Kreer, Wilson Wu, Maxwell Adam +2
Classical influence functions face significant challenges when applied to deep neural networks, primarily due to non-invertible Hessians and high-dimensional parameter spaces. We p…
Towards a unified and verified understanding of group-operation networks
Wilson Wu, Louis Jaburi, Jacob Drori +1
A recent line of work in mechanistic interpretability has focused on reverse-engineering the computation performed by neural networks trained on the binary operation of finite grou…
Do language models plan ahead for future tokens?
Wilson Wu, John X. Morris, Lionel Levine
Do transformers "think ahead" during inference at a given position? It is known transformers prepare information in the hidden states of the forward pass at time step that is t…
Analyzing and Improving Neural Networks by Generating Semantic Counterexamples through Differentiable Rendering
Lakshya Jain, Varun Chandrasekaran, Uyeong Jang +6
Even as deep neural networks (DNNs) have achieved remarkable success on vision-related tasks, their performance is brittle to transformations in the input. Of particular interest a…