1 citations · 1 across the 7 of their papers we have counts for
9 papers
Loss Curvature as a Sampling-Free Proxy for Memorization in Diffusion Models
Shashank Sule, Xinyue Yu, Boonam Shin +3
Understanding the mechanism behind why diffusion models memorize their training data remains an open question in generative modeling. In this paper, we examine this question from t…
Neural collapse in the orthoplex regime
James Alcala, Rayna Andreeva, Vladimir A. Kobzar +4
When training a neural network for classification, the feature vectors of the training set are known to collapse to the vertices of a regular simplex, provided the dimension of…
Learning collective variables that respect permutational symmetry
Jiaxin Yuan, Shashank Sule, Yeuk Yin Lam +1
In addition to translational and rotational symmetries, clusters of identical interacting particles possess permutational symmetry. Coarse-grained models for such systems are instr…
Learning collective variables that preserve transition rates
Shashank Sule, Arnav Mehta, Maria K. Cameron
Collective variables (CVs) play a crucial role in capturing rare events in high-dimensional systems, motivating the continual search for principled approaches to their design. In t…
Neumann eigenmaps for landmark embedding
Shashank Sule, Wojciech Czaja
We present Neumann eigenmaps (NeuMaps), a novel approach for enhancing the standard diffusion map embedding using landmarks, i.e distinguished samples within the dataset. By interp…
Input layer regularization and automated regularization hyperparameter tuning for myelin water estimation using deep learning
Mirage Modi, Shashank Sule, Jonathan Palumbo +4
We propose a novel deep learning method which combines classical regularization with data augmentation for estimating myelin water fraction (MWF) in the brain via biexponential ana…
Sharp error estimates for target measure diffusion maps with applications to the committor problem
Shashank Sule, Luke Evans, Maria Cameron
We obtain asymptotically sharp error estimates for the consistency error of the Target Measure Diffusion map (TMDmap) (Banisch et al. 2020), a variant of diffusion maps featuring i…
On the limits of neural network explainability via descrambling
Shashank Sule, Richard G. Spencer, Wojciech Czaja
We characterize the exact solutions to neural network descrambling--a mathematical model for explaining the fully connected layers of trained neural networks (NNs). By reformulatin…
Sobolev Orthogonal Polynomials on the Sierpinski Gasket
Qingxuan Jiang, Tian Lan, Kasso Okoudjou +4
We develop a theory of Sobolev orthogonal polynomials on the Sierpiński gasket (). These orthogonal polynomials arise through the Gram-Schmidt orthogonalisation process applied…