Catégorie
Validation croisée
Publications associées (1 000)
High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization
This paper studies kernel ridge regression in high dimensions under covariate shifts and analyzes the role of importance re-weighting. We first derive the asymptotic expansion of high dimensional kernels under covariate shifts. By a bias-variance decomposi ...
2024Efficient local linearity regularization to overcome catastrophic overfitting
Volkan Cevher, Grigorios Chrysos, Fanghui Liu, Elias Abad Rocamora
Catastrophic overfitting (CO) in single-step adversarial training (AT) results in abrupt drops in the adversarial test accuracy (even down to 0%). For models trained with multi-step AT, it has been observed that the loss function behaves locally linearly w ...
2024Understanding generalization and robustness in modern deep learning
In this thesis, we study two closely related directions: robustness and generalization in modern deep learning. Deep learning models based on empirical risk minimization are known to be often non-robust to small, worst-case perturbations known as adversari ...
EPFL2024Towards Trustworthy Deep Learning for Image Reconstruction
The remarkable ability of deep learning (DL) models to approximate high-dimensional functions from samples has sparked a revolution across numerous scientific and industrial domains that cannot be overemphasized. In sensitive applications, the good perform ...
EPFL2024Reducing Annotation Efforts in Electricity Theft Detection Through Optimal Sample Selection
Supervised machine learning models are receiving increasing attention in electricity theft detection due to their high detection accuracy. However, their performance depends on a massive amount of labeled training data, which comes from time-consuming and ...
Piscataway2024SzCORE: A Seizure Community Open-source Research Evaluation framework for the validation of EEG-based automated seizure detection algorithms
David Atienza Alonso, Alireza Amirshahi, Jonathan Dan, Adriano Bernini, William Cappelletti, Luca Benini, Una Pale
The need for high-quality automated seizure detection algorithms based on electroencephalography (EEG) becomes ever more pressing with the increasing use of ambulatory and long-term EEG monitoring. Heterogeneity in validation methods of these algorithms in ...
2024Statistical Inference for Inverse Problems: From Sparsity-Based Methods to Neural Networks
In inverse problems, the task is to reconstruct an unknown signal from its possibly noise-corrupted measurements. Penalized-likelihood-based estimation and Bayesian estimation are two powerful statistical paradigms for the resolution of such problems. They ...
EPFL2024A Geometric Unification of Distributionally Robust Covariance Estimators: Shrinking the Spectrum by Inflating the Ambiguity Set
Daniel Kuhn, Yves Rychener, Viet Anh Nguyen
The state-of-the-art methods for estimating high-dimensional covariance matrices all shrink the eigenvalues of the sample covariance matrix towards a data-insensitive shrinkage target. The underlying shrinkage transformation is either chosen heuristically ...
2024NMR and MS reveal characteristic metabolome atlas and optimize esophageal squamous cell carcinoma early detection
Lijing Xin, Yubo Zhao, Yan Lin, Wei Ye
Metabolic changes precede malignant histology. However, it remains unclear whether detectable characteristic metabolome exists in esophageal squamous cell carcinoma (ESCC) tissues and biofluids for early diagnosis. Here, we conduct NMR- and MS-based metabo ...
Nature Portfolio2024Meta-learning to address diverse Earth observation problems across resolutions
Devis Tuia, Benjamin Alexander Kellenberger, Marc Conrad Russwurm
Earth scientists study a variety of problems with remote sensing data, but they most often consider them in isolation from each other, which limits information flows across disciplines. In this work, we present METEOR, a meta-learning methodology for Earth ...
London2024