Alex Hägele

I am excited to announce that I will join the University of Zurich as an assistant professor in August this year! I am looking for PhD students and postdocs starting from the fall.

My research interests include optimization, federated learning, machine learning, privacy, and unlearning.

06.03.2025 02:17 — 👍 28    🔁 5    💬 1    📌 1

🤗Thanks a lot @haeggee.bsky.social and @mjaggi.bsky.social for having me in the MLO group at EPFL @icepfl.bsky.social to present "Large Language Models as Markov Chains".

Slides are available on my website (link in thread).

🎉 New experiments with Llama and Gemma models in the updated paper!

28.02.2025 13:03 — 👍 4    🔁 2    💬 1    📌 0

The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training We show that learning-rate schedules for large model training behave surprisingly similar to a performance bound from non-smooth convex optimization theory. We provide a bound for the constant schedul...

Learning rate schedules seem mysterious? Why is the loss going down so fast during cooldown?
Turns out that this behaviour can be described with a bound from *convex, nonsmooth* optimization.

A short thread on our latest paper 🚞

arxiv.org/abs/2501.18965

05.02.2025 10:13 — 👍 31    🔁 6    💬 2    📌 0

oh wow, thanks so much 🥹

22.11.2024 16:10 — 👍 2    🔁 0    💬 0    📌 0

Hi there 👋 Happy to join Bluesky!

We are the EPFL AI Center - EPFL's hub for artificial intelligence, shaping a future where AI works for everyone through cutting-edge research, education, and collaborations the private and public sector.

ai.epfl.ch

22.11.2024 09:13 — 👍 16    🔁 2    💬 1    📌 2