I’m greatly enjoying the setting of this year’s #AABI symposium, thanks to NTU Singapore for hosting us!

Merry Bayesmas to those who are celebrating 🎅🏻

This was a really awesome collaboration with Tristan Cinquin, Marvin Pförtner, @philipphennig.bsky.social, and Robert Bamler!

🌊 We show that this can improve performance over standard Laplace with weight-space priors in real-world scientific tasks, such as this ocean current modeling problem

💡 In our work, we propose to use the Laplace approximation in function space! This is mathematically principled (after a bit of measure theory) and can be efficiently implemented using matrix-free linear algebra 🚀

Very honored to have been elected an @ellis.eu Scholar in the program for Robust Machine Learning: ellis.eu/programs/rob...

What better way to celebrate it than to speak at the ELLIS UnConference in Bad Teinach?

This was a super fun collaboration, led by my master's student Rayen Dhahri with Alex Immer,
@bertrand-sharp.bsky.social, and Stephan Günnemann

🤔 How efficient can sparsification be without sacrificing performance?

☝️We showcase significant computational savings while retaining high performance across different sparsity levels:
📈 Achieves up to 20x computational savings with minimal accuracy degradation

Moreover, we introduce Optimal Posterior Damage (OPD), a robust pruning criterion that:

⚡ Reuses posterior precision to guide efficient sparsification
⚡ Covers structured & unstructured pruning seamlessly
⚡ Scales well across various architectures and sparsity levels

📢 Excited to present our work at #NeurIPS2024!
📄 "Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks using the Marginal Likelihood"
Read it here: arxiv.org/abs/2402.15978

Details in 🧵