← Search

Brendon G. Anderson

2 accepted papers

2024

Transport of Algebraic Structure to Latent Embeddings

ICML 2024spotlight

Machine learning often aims to produce latent embeddings of inputs which lie in a larger, abstract mathematical space. For example, in the field of 3D modeling, subsets of Euclidean space can be embedded as vectors using implicit neural representations. Such subsets also have a natural algebraic str…

2023

Asymmetric Certified Robustness via Feature-Convex Neural Networks

NeurIPS 2023poster

Real-world adversarial attacks on machine learning models often feature an asymmetric structure wherein adversaries only attempt to induce false negatives (e.g., classify a spam email as not spam). We formalize the asymmetric robustness certification problem and correspondingly present the feature-c…