| Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation A Ranjan, V Jampani, L Balles, K Kim, D Sun, J Wulff, MJ Black Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2019 | 774 | 2019 |
| Limitations of the empirical fisher approximation for natural gradient descent F Kunstner, P Hennig, L Balles Advances in neural information processing systems 32, 2019 | 300 | 2019 |
| Dissecting Adam: The Sign, Magnitude and Variance of Stochastic Gradients L Balles, P Hennig Proceedings of the 35th International Conference on Machine Learning (ICML …, 2018 | 249 | 2018 |
| Coupling Adaptive Batch Sizes with Learning Rates L Balles, J Romero, P Hennig Proceedings of the Thirty-Third Conference on Uncertainty in Artificial …, 2017 | 160 | 2017 |
| Early stopping without a validation set M Mahsereci, L Balles, C Lassner, P Hennig arXiv preprint arXiv:1703.09580, 2017 | 155 | 2017 |
| DeepOBS: A Deep Learning Optimizer Benchmark Suite F Schneider, L Balles, P Hennig Seventh International Conference on Learning Representations (ICLR), 2019 | 92 | 2019 |
| The Geometry of Sign Gradient Descent L Balles, F Pedregosa, N Le Roux arXiv preprint arXiv:2002.08056, 2020 | 32 | 2020 |
| Continual learning with low rank adaptation M Wistuba, PT Sivaprasad, L Balles, G Zappella arXiv preprint arXiv:2311.17601, 2023 | 30 | 2023 |
| PASHA: Efficient HPO and NAS with progressive resource allocation O Bohdal, L Balles, M Wistuba, B Ermis, C Archambeau, G Zappella arXiv preprint arXiv:2207.06940, 2022 | 27 | 2022 |
| u-P: The Unit-Scaled Maximal Update Parametrization C Blake, C Eichenberg, J Dean, L Balles, LY Prince, B Deiseroth, ... arXiv preprint arXiv:2407.17465, 2024 | 21 | 2024 |
| Hierarchical autoregressive transformers: Combining byte-and word-level processing for robust, adaptable language models P Neitemeier, B Deiseroth, C Eichenberg, L Balles arXiv preprint arXiv:2501.10322, 2025 | 8 | 2025 |
| Gradient-matching coresets for rehearsal-based continual learning L Balles, G Zappella, C Archambeau arXiv preprint arXiv:2203.14544, 2022 | 8 | 2022 |
| Renate: A library for real-world continual learning M Wistuba, M Ferianc, L Balles, C Archambeau, G Zappella arXiv preprint arXiv:2304.12067, 2023 | 7 | 2023 |
| Self-tuning stochastic optimization with curvature-aware gradient filtering RTQ Chen, D Choi, L Balles, D Duvenaud, P Hennig PMLR, 2020 | 7 | 2020 |
| Choice of peft technique in continual learning: Prompt tuning is not all you need M Wistuba, PT Sivaprasad, L Balles, G Zappella arXiv preprint arXiv:2406.03216, 2024 | 6 | 2024 |
| Holographic and other point set distances for machine learning L Balles, T Fischbacher | 6 | 2019 |
| Automating stochastic optimization with gradient variance estimates L Balles, M Mahsereci, P Hennig ICML AutoML Workshop, 13, 2017 | 4 | 2017 |
| On the choice of learning rate for local SGD L Balles, C Archambeau Transactions on Machine Learning Research, 2024 | 3 | 2024 |
| Gradient-matching coresets for continual learning L Balles, G Zappella, C Archambeau arXiv preprint arXiv:2112.05025, 2021 | 2 | 2021 |
| Concept shift detection and correction using probabilistic models and learned feature representations LS BALLES, G Zappella, CP Archambeau US Patent 12,423,960, 2025 | | 2025 |
Philipp HennigUniversity of Tübingen, Tübingen AI CenterVerified email at uni-tuebingen.de
