Date: June 3rd, 17:30Location: Building 80 Room 00-021 The unit invites everyone interested to the next social event on June 3rd! Get ready for an engaging gathering filled with insightful discussions. A great event to connect with the AI community in Freiburg! This time, there are two ten-minute presentations. The talks are followed by a Read more…
In 2022 and 2023 we Prof. Dr. Frank Hutter, together with other postdocs and PhD students from the AutoML lab in the ELLIS Unit Freiburg, have organized the AutoML conference, the premier gathering of professionals focussed on the progressive automation of machine learning (ML), aiming to develop automated methods for Read more…
Speaker: Arber ZelaDate: 29th April 2024 Pareto front profiling in multi-objective optimization (MOO), i.e. finding a diverse set of Pareto optimal solutions, is challenging, especially with expensive objectives like neural network training. Typically, in MOO neural architecture search (NAS), we aim to balance performance and hardware metrics across devices. Prior Read more…
Samuel Müller from the Machine Learning Lab will give a talk titled “Prior-data Fitted Networks (PFNs): Use neural networks for 100x faster Bayesian predictions“. Abstract Bayesian methods can be expensive and complicated to approximate with e.g. Markov Chain Monte Carlo (MCMC) or Variational Inference (VI) approaches. Prior-data Fitted Networks (PFNs) Read more…