Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Crabbé, Jonathan"'
Tabular data is one of the most ubiquitous modalities, yet the literature on tabular generative foundation models is lagging far behind its text and vision counterparts. Creating such a model is hard, due to the heterogeneous feature spaces of differ
Externí odkaz:
http://arxiv.org/abs/2406.17673
Autor:
Huynh, Nicolas, Berrevoets, Jeroen, Seedat, Nabeel, Crabbé, Jonathan, Qian, Zhaozhi, van der Schaar, Mihaela
Identification and appropriate handling of inconsistencies in data at deployment time is crucial to reliably use machine learning models. While recent data-centric methods are able to identify such inconsistencies with respect to the training set, th
Externí odkaz:
http://arxiv.org/abs/2402.17599
Fourier analysis has been an instrumental tool in the development of signal processing. This leads us to wonder whether this framework could similarly benefit generative modelling. In this paper, we explore this question through the scope of time ser
Externí odkaz:
http://arxiv.org/abs/2402.05933
Autor:
Zeni, Claudio, Pinsler, Robert, Zügner, Daniel, Fowler, Andrew, Horton, Matthew, Fu, Xiang, Shysheya, Sasha, Crabbé, Jonathan, Sun, Lixin, Smith, Jake, Nguyen, Bichlien, Schulz, Hannes, Lewis, Sarah, Huang, Chin-Wei, Lu, Ziheng, Zhou, Yichi, Yang, Han, Hao, Hongxia, Li, Jielan, Tomioka, Ryota, Xie, Tian
The design of functional materials with desired properties is essential in driving technological advances in areas like energy storage, catalysis, and carbon capture. Generative models provide a new paradigm for materials design by directly generatin
Externí odkaz:
http://arxiv.org/abs/2312.03687
Data quality is crucial for robust machine learning algorithms, with the recent interest in data-centric AI emphasizing the importance of training data characterization. However, current data characterization methods are largely focused on classifica
Externí odkaz:
http://arxiv.org/abs/2310.18970
What distinguishes robust models from non-robust ones? This question has gained traction with the appearance of large-scale multimodal models, such as CLIP. These models have demonstrated unprecedented robustness with respect to natural distribution
Externí odkaz:
http://arxiv.org/abs/2310.13040
Interpretability methods are valuable only if their explanations faithfully describe the explained model. In this work, we consider neural networks whose predictions are invariant under a specific symmetry group. This includes popular architectures,
Externí odkaz:
http://arxiv.org/abs/2304.06715
Despite their success with unstructured data, deep neural networks are not yet a panacea for structured tabular data. In the tabular domain, their efficiency crucially relies on various forms of regularization to prevent overfitting and provide stron
Externí odkaz:
http://arxiv.org/abs/2303.05506
Ensembles of machine learning models have been well established as a powerful method of improving performance over a single model. Traditionally, ensembling algorithms train their base learners independently or sequentially with the goal of optimizin
Externí odkaz:
http://arxiv.org/abs/2301.11323
High model performance, on average, can hide that models may systematically underperform on subgroups of the data. We consider the tabular setting, which surfaces the unique issue of outcome heterogeneity - this is prevalent in areas such as healthca
Externí odkaz:
http://arxiv.org/abs/2210.13043