Search Results for author: Christopher Scarvelis

Found 4 papers, 0 papers with code

Nuclear Norm Regularization for Deep Learning

no code implementations23 May 2024 Christopher Scarvelis, Justin Solomon

Our method is simple, efficient, and accurate, enabling Jacobian nuclear norm regularization to scale to high-dimensional deep learning problems.

Denoising Representation Learning

Closed-Form Diffusion Models

no code implementations19 Oct 2023 Christopher Scarvelis, Haitz Sáez de Ocáriz Borde, Justin Solomon

In this work, we instead explicitly smooth the closed-form score to obtain an SGM that generates novel samples without training.

Riemannian Metric Learning via Optimal Transport

no code implementations18 May 2022 Christopher Scarvelis, Justin Solomon

We introduce an optimal transport-based model for learning a metric tensor from cross-sectional samples of evolving probability measures on a common Riemannian manifold.

Metric Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.