Rayna Andreeva

My first first-author journal paper now featuring in The Guardian! Great collaboration with @Sarkar_Lab @RikSarkarNet @BioMedAI_CDT @InfAtEd @FoodSciLeeds 🗞️@guardianscience : theguardian.com/science/2023/d… ➡️ @SciReports : nature.com/articles/s4159…

Friends, I am beyond happy! I'm starting a new position as Full Professor of #MachineLearning at the University of Fribourg @unifr 🇨🇭! With #SwissAI and many other initiatives, I am taking my research at the intersection of #geometry, #topology, and #MachineLearning to a new level 🚀. This #SwissNationalDay will thus hold an even more special meaning for me—thanks for this wonderful chance, my dear confederates! The past few years have been a veritable roller coaster 🎢, with ups and downs. Through it all, I was sustained and supported by my family, for which I am eternally grateful. As much as we like to believe it in academia, 'no man is an island,' and I have tons of people to thank, foremost among them my postdoctoral adviser @kmborgwardt, as well as my long-term collaborators @KrishnaswamyLab and @mrguywolf. I am also indebted to my great research group at the AIDOS Lab. Working with all of you is a pleasure! 🙏 Finally, I am grateful for the advice of my mentors and role models @stefanabauer, @mmbronstein, and @guennemann (plus many others—you know who you are). It's time to give back now and make academia better! PS: 🔥I'm hiring soon! 🔥Please share widely and direct any inquiries to my e-mail or DM.

Topological Generalization Bounds for Discrete-Time Stochastic Optimization Algorithms. arxiv.org/abs/2407.08723

Over the past years, we've been exploring topological complexity measures of generalization in deep nets. It is time to announce our recent work, where we propose a novel set of rigorous and efficient topology-based bounds for the generalization gap: arxiv.org/abs/2407.08723. 👇

My latest PhD Project is now up on @medrxivpreprint: medrxiv.org/content/10.110… ! Here, we looked at the association between antidepressant exposure and DNA methylation🧬in 16,536 individuals in @genscot. A 🧵 of our main findings:

☀️I'm recruiting 2+3 year postdoc @InfAtEd, part of the #CYBER consortium led by @chofski cyber-mission.github.io Join us in wonderful #Edinburgh and build #AI & #machinelearning models for #syntheticbiology More info linkedin.com/posts/diego-oy… Apply here elxw.fa.em3.oraclecloud.com/hcmUI/Candidat…

At #ICLR2024 looking for some topology to brighten your day? Come find me at poster 204 for some topology inspired subsampling!

Do you want to know how to reuse neural components without knowing the transformations relating their latent spaces? 👀 Stop by our @iclrconf poster #239 at 10:45 to find out more! #ICLR2024

Uniform Generalization Bounds on Data-Dependent Hypothesis Sets via PAC-Bayesian Theory on Random Sets ift.tt/XyaBQPW

@LimbeckKat talking about the role of metric space magnitude in evaluating the diversity of latent-space models at the @HelmholtzMunich Foundation Model Symposium. Relevant preprint: arxiv.org/abs/2311.16054

New preprint out!🚨We performed a large scale analysis of physicochemical features extracted from over half a million AlphaFold structural models, and using data-driven methods we showed a link between these features and in vivo behaviour of proteins. Find out more below⬇️1/9

We position #TopologicalDeepLearning as an exciting research frontier, unveil open problems with a potential to transform #AI / #ML landscape, especially for irregular domains. I warmly invite the research community to join our quest: arxiv.org/abs/2402.08871.

I was interviewed for an article in December by BBC News Mundo @bbcmundo about our recent work with @Sarkar_Lab (@FoodSciLeeds) and @RikSarkarNet (@InfAtEd) about using AI and TDA to study the surface of the human tongue. The article is out now (in Spanish) ⬇️ @BioMedAI_CDT

Un grupo de investigadores aplicó aprendizaje automático para elaborar un mapa de las papilas gustativas sobre la lengua. trib.al/fz3WpP2

Il y a une "empreinte de langue" comme il y a des empreintes digitales 👉 l.sciencesetavenir.fr/rPf

Exciting article about our work with @RikSarkarNet @InfAtEd in collaboration with @Sarkar_Lab @FoodSciLeeds ! @BioMedAI_CDT @EdinburghUni 📜: nature.com/articles/s4159…

Machine learning and topological data analysis identify unique features of human papillae in 3D scans @randreeva1 @Sarkar_Lab @RikSarkarNet nature.com/articles/s4159…

Our paper covered by Indian news channel @ndtv ! @randreeva1 @Sarkar_Lab ndtv.com/food/tongues-h…

Our paper on #MachineLearning and #tda to analyse human Papillae covered in @guardian theguardian.com/science/2023/d…

A new study shows our tongues are as unique as fingerprints. AI & 3D tech reveal individual taste and touch patterns, promising advances in personalized nutrition and health. neurosciencenews.com/tongue-ai-neur… 1/2