Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

Notes

Published:

Posts

Computational Machine Learning

less than 1 minute read

Published:

The field of machine learning has witnessed a surge in research on generative models, as these models possess the ability to generate novel data similar to the training data. In this study, our primary objective is to explore various types of generative models, with a thorough analysis of their respective limitations and potential applications. Additionally, we will investigate several influence methods and explore their efficacy in addressing the issue of memorization in generative models.

portfolio

Interpretability through Training Samples: Data Attribution for Diffusion Models

Published:

Data attribution methods help interpret how neural networks behave by linking the model behavior to their training data. We extend the first-order influence approximation, TracIn, to diffusion models by incorporating the denoising timestep dynamics. We demonstrate that this influence estimation may be biased due to dominating gradient norms. To this end, Diffusion-ReTrac with a renormalization technique is introduced, enabling notably more localized influence estimation and the targeted attribution of training samples.image_tracing-1

publications

talks

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.