papers

Publications (8)

cs.LG2023

Metropolis Sampling for Constrained Diffusion Models

Nic Fishman, Leo Klarner, Emile Mathieu +2

Denoising diffusion models have recently emerged as the predominant paradigm for generative modelling on image domains. In addition, their extension to Riemannian manifolds has fac…

cs.LG2024

Diffusion Models for Constrained Domains

Nic Fishman, Leo Klarner, Valentin De Bortoli +2

Denoising diffusion models are a novel class of generative algorithms that achieve state-of-the-art performance across a range of domains, including image generation and text-to-im…

cs.LG2022

Should attention be all we need? The epistemic and ethical implications of unification in machine learning

Nic Fishman, Leif Hancox-Li

"Attention is all you need" has become a fundamental precept in machine learning research. Originally designed for machine translation, transformers and the attention mechanisms th…

cs.LG2024

The Fragility of Fairness: Causal Sensitivity Analysis for Fair Machine Learning

Jake Fawkes, Nic Fishman, Mel Andrews +1

Fairness metrics are a core tool in the fair machine learning literature (FairML), used to determine that ML models are, in some sense, "fair". Real-world data, however, are typica…

cs.SI2023

Human mobility networks reveal increased segregation in large cities

Hamed Nilforoshan, Wenli Looi, Emma Pierson +7

A long-standing expectation is that large, dense, and cosmopolitan areas support socioeconomic mixing and exposure between diverse individuals. It has been difficult to assess this…

cs.LG2026

Generative Distribution Embeddings: Lifting autoencoders to the space of distributions for multiscale representation learning

Nic Fishman, Gokul Gowri, Peng Yin +2

Many real-world problems require reasoning across multiple scales, demanding models which operate not on single data points, but on entire distributions. We introduce generative di…