Felix Petersen Profile picture
Machine learning researcher, postdoc, 23 y/o. Investigating differentiable algorithms etc. @Stanford @StanfordAILab.

Sep 9, 2022, 13 tweets

I am excited to announce that I have successfully defended my PhD and have published my PhD thesis on “Learning with Differentiable Algorithms”. 🎉

arxiv.org/abs/2209.00616

In the thesis, I explore how we can make discrete structures like algorithms differentiable. [1/13]

By making algorithms differentiable, we can integrate them end-to-end into neural network machine learning architectures. For example, we can continuously relax sorting (github.com/Felix-Petersen…) for learning to rank. [2/13]

Apart from differentiable sorting, we also consider differentiable rendering, differentiable logic, differentiable top-k, differentiable shortest-path and many more.
The thesis is based on works we published at #NeurIPS #ICML #ICLR and #CVPR. [3/13]

All of this work builds on / has been developed in parallel to a long and exciting line of related work by @AchlioptasPanos @AdrienCorenflos @AnaderiRu @AnselmPaulus @ArnaudDoucet1 @AvilaGarcez @BabuaSpeaks @BachFrancis @BergKirkpatrick @Bertrand_Charp @COztireli [4/13]

Share this Scrolly Tale with your friends.

A Scrolly Tale is a new way to read Twitter threads with a more visually immersive experience.
Discover more beautiful Scrolly Tales like this.

Keep scrolling