PhD Student
Fabio Ferreira
![](http://ml.informatik.uni-freiburg.de/wp-content/uploads/2022/06/IMG_3088-231x300.jpg)
Postal address
Institut für InformatikAlbert-Ludwigs-Universität Freiburg
Sekretariat Hutter/Maschinelles Lernen
Georges-Köhler-Allee 074
79110 Freiburg, Germany
Fax
+49 761 203-74217Office
Building 74, Room 00-014About
In 2020 I joined the Machine Learning Lab as a PhD student under the supervision of Frank Hutter. Before that I joined the Stanford AI Lab for my master’s thesis to work in Jeannette Bohg’s IPRL group on robotic manipulation. As a student research assistant, I also worked at Tamim Asfour’s H2T Lab with focus on robot perception. I hold a M. Sc. from KIT in CS/Machine Learning and am alumnus of the German National Academic Scholarship Foundation.
Research Interests
- Meta-Learning
- Self-supervised Learning
- Transfer Learning
Student Supervision
Getting in touch
If you are a very good student and interested in working with me on the above mentioned research interests, please feel free to reach out via email. In order to assess a good fit, please answer the questions listed on this webpage. Also, if you have any nice material such as code, figures, paper summaries, work results or a paper in which you had major contributions in please attach them to your email.
Current project offerings:
- Learning to learn finetuning (Hiwi / Project / Thesis, preferred MSc Project or MSc Thesis)
Former project offerings
- Adversarial Image Transformations for Self-Supervised Learning (Hiwi / Project / Thesis, preferred MSc Project or MSc Thesis)
- Extension of our “Zero-Shot AutoML with Pretrained Models” Work (Hiwi / Project / Thesis)
- Extension of our “Learning Synthetic Environments” Work (Hiwi / Project / Thesis)
Publications
2024 |
Quick-Tune-Tool: A Practical Tool and its User Guide for Automatically Finetuning Pretrained Models Workshop Forthcoming AutoML Conference 2024 (Workshop Track), Forthcoming. |
Quick-Tune: Quickly Learning Which Pretrained Model to Finetune and How Inproceedings In: The Twelfth International Conference on Learning Representations (ICLR), 2024, (Oral Presentation). |
2023 |
Hard View Selection for Contrastive Learning Conference Forthcoming Forthcoming. |
MDP Playground: An Analysis and Debug Testbed for Reinforcement Learning Journal Article In: Journal of Artificial Intelligence Research (JAIR), vol. 77, pp. 821-890, 2023. |
Quick-Tune: Quickly Learning Which Pretrained Model to Finetune and How Conference Forthcoming Forthcoming. |
2022 |
On the Importance of Hyperparameters and Data Augmentation for Self-Supervised Learning Workshop ICML Pre-training Workshop, 2022. |
Zero-shot AutoML with Pretrained Models Inproceedings In: International Conference on Machine Learning (ICML), 2022. |
Learning Synthetic Environments and Reward Networks for Reinforcement Learning Inproceedings In: 10th International Conference on Learning Representations (ICLR), OpenReview.net, 2022. |
2021 |
MDP Playground: A Design and Debug Testbed for Reinforcement Learning Inproceedings In: arXiv:1909.07750, 2021. |
Learning Synthetic Environments for Reinforcement Learning with Evolution Strategies Journal Article In: AAAI workshop on Meta-Learning Challenges, 2021. |
2020 |
Winning Solutions and Post-Challenge Analyses of the ChaLearn AutoDL Challenge 2019 Journal Article In: IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 43, no. 9, pp. 3108-3125, 2020. |