44 citations · 153 across the 39 of their papers we have counts for
10 papers · 1 filter
The Geometric Wall: Manifold Structure Predicts Layerwise Sparse Autoencoder Scaling Laws
Eslam Zaher, Maciej Trzaskowski, Quan Nguyen +1
Sparse autoencoders (SAEs) operationalise the linear representation hypothesis: they reconstruct model activations as sparse linear combinations of interpretable dictionary atoms,…
Counterfactual Explanations on Robust Perceptual Geodesics
Eslam Zaher, Maciej Trzaskowski, Quan Nguyen +1
Latent-space optimization methods for counterfactual explanations - framed as minimal semantic perturbations that change model predictions - inherit the ambiguity of Wachter et al.…
Importance Sampling for Nonlinear Models
Prakash Palanivelu Rajmohan, Fred Roosta
While norm-based and leverage-score-based methods have been extensively studied for identifying "important" data points in linear models, analogous tools for nonlinear models remai…
Manifold Integrated Gradients: Riemannian Geometry for Feature Attribution
Eslam Zaher, Maciej Trzaskowski, Quan Nguyen +1
In this paper, we dive into the reliability concerns of Integrated Gradients (IG), a prevalent feature attribution method for black-box deep learning models. We particularly addres…
Non-PSD Matrix Sketching with Applications to Regression and Optimization
Zhili Feng, Fred Roosta, David P. Woodruff
A variety of dimensionality reduction techniques have been applied for computations involving large matrices. The underlying matrix is randomly compressed into a smaller one, while…
Average-reward model-free reinforcement learning: a systematic review and literature mapping
Vektor Dewanto, George Dunn, Ali Eshragh +2
Reinforcement learning is important part of artificial intelligence. In this paper, we review model-free reinforcement learning that utilizes the average reward optimality criterio…
Avoiding Kernel Fixed Points: Computing with ELU and GELU Infinite Networks
Russell Tsuchida, Tim Pearce, Chris van der Heide +2
Analysing and computing with Gaussian processes arising from infinitely wide neural networks has recently seen a resurgence in popularity. Despite this, many explicit covariance fu…
Richer priors for infinitely wide multi-layer perceptrons
Russell Tsuchida, Fred Roosta, Marcus Gallagher
It is well-known that the distribution over functions induced through a zero-mean iid prior distribution over the parameters of a multi-layer perceptron (MLP) converges to a Gaussi…
Exchangeability and Kernel Invariance in Trained MLPs
Russell Tsuchida, Fred Roosta, Marcus Gallagher
In the analysis of machine learning models, it is often convenient to assume that the parameters are IID. This assumption is not satisfied when the parameters are updated through t…
Newton-ADMM: A Distributed GPU-Accelerated Optimizer for Multiclass Classification Problems
Chih-Hao Fang, Sudhir B Kylasa, Fred Roosta +2
First-order optimization methods, such as stochastic gradient descent (SGD) and its variants, are widely used in machine learning applications due to their simplicity and low per-i…