ManyFairHPO: A Human-in-the-Loop Fairness-Aware Model Selection Framework for Complex Fairness Objective Landscapes

Posted on October 21, 2024 by Noor Awad

arXiv Fairness in AI is a complex and evolving challenge that continues to spark intense debate and research in the tech community. As we grapple with the ethical implications of AI decision-making, we proposed a new approach called ManyFairHPO, offering a fresh perspective on this critical issue. While not a silver bullet, this innovative framework […]

Dreaming of Many Worlds: Learning Contextual World Models Aids Zero-Shot Generalization

Posted on September 29, 2024 by Karim Farid

Authors: Sai Prasanna Raman, Karim Farid, Raghu Rajan, André Biedenkapp Zero-shot generalization (ZSG) to unseen dynamics is a major challenge for creating generally capable embodied agents. To address the broader challenge, we start with the simpler setting of contextual reinforcement learning (cRL), assuming observability of the context values that parameterize the variation in the system’s […]

Introducing Hypersweeper: Bridging the HPO Gap Between AutoML Research and ML Practitioners

Posted on September 25, 2024 by Theresa Eimer

The lack of widespread adoption of AutoML tools in the broader ML community has been a recurring topic of discussion within the field. Is this due to a lack of trust in these systems? Do our benchmarks fail to reflect real-world use cases? Or is it simply too difficult to find and implement state-of-the-art methods? […]

One-Shot Neural Architecture Search for Time Series Forecasting

Posted on August 23, 2024 by Difan Deng

Authors: Difan Deng and Marius Lindauer TL;DR In our paper, we present a one-shot neural architecture search space for time series forecasting tasks. Our search space contains a hybrid network that contains a Seq Net (for instance, transformers and RNNs that process sequences directly) and a Flat Net (for instance, MLPs that handle each variable […]

Incorporating Structure in Deep Reinforcement Learning

Posted on July 18, 2024 by Aditya Mohan

Authors: Aditya Mohan, Amy Zhang, Marius Lindauer Deep Reinforcement Learning (RL) has significantly advanced in various fields, from playing complex games to controlling robotic systems. However, its application in real-world scenarios still faces numerous challenges, such as poor data efficiency, limited generalization, and a lack of safety guarantees. This work provides a comprehensive overview of […]

Position: A Call to Action for a Human-Centered AutoML Paradigm

Posted on by Marius Lindauer

Paper Authors Marius Lindauer, Florian Karl, Anne Klier, Julia Moosbauer, Alexander Tornede, Andreas Mueller, Frank Hutter, Matthias Feurer, Bernd Bischl Motivation Automated Machine Learning (AutoML) has significantly transformed the machine learning landscape by automating the creation and optimization of ML models. This has opened up a path towards democratized ML, making it accessible to a […]

Review of the Year 2023 – AutoML Hannover

Posted on December 20, 2023 by Marius Lindauer

by the AutoML Hannover Team The year 2023 was the most successful for us as a (still relatively young) AutoML group in Hannover. With the start of several big projects, including the ERC starting grant on interactive and explainable AutoML and a BMUV-funded project on Green AutoML, the group has grown and we were able […]

New Horizons in Parameter Regularization: A Constraint Approach

Posted on December 12, 2023 by Jörg Franke

Authors: Jörg Franke, Michael Hefenbrock, Gregor Koehler, Frank Hutter Introduction We present in our recent preprint a novel approach to parameter regularization for deep learning: Constrained Parameter Regularization (CPR). It is an alternative to traditional weight decay. Instead of applying a constant penalty uniformly to all parameters, we enforce an upper bound on a statistical […]

Rethinking Performance Measures of RNA Secondary Structure Problems

Posted on December 11, 2023 by Frederic Runge

TL;DR In our NeurIPS workshop paper , we analyze different performance measures for the evaluation of RNA secondary structure prediction algorithms, showing that commonly used measures are flawed in certain settings. We then propose the Weisfeiler-Lehman graph kernel as a competent measure for performance assessment in the field. RNA Secondary Structure Prediction Ribonucleic acid (RNA) […]

LC-PFN: Efficient Bayesian Learning Curve Extrapolation using Prior-Data Fitted Networks

Posted on December 8, 2023 by Steven Adriaensen

Authors: Steven Adriaensen*, Herilalaina Rakotoarison*, Samuel Müller, and Frank Hutter TL;DR In our paper, we propose LC-PFN, a novel method for Bayesian learning curve extrapolation. LC-PFN is a prior-data-fitted network (PFN), a transformer trained on synthetic learning curve data capable of doing Bayesian learning curve extrapolation in a single forward pass. We show that our […]