Concept
Early stopping
Related publications (47)
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 ...
2024Gradient boosting with extreme-value theory for wildfire prediction
This paper details the approach of the team Kohrrelation in the 2021 Extreme Value Analysis data challenge, dealing with the prediction of wildfire counts and sizes over the contiguous US. Our approach uses ideas from extreme-value theory in a machine lear ...
2023Data-Driven Control and Optimization under Noisy and Uncertain Conditions
Control systems operating in real-world environments often face disturbances arising from measurement noise and model mismatch. These factors can significantly impact the perfor- mance and safety of the system. In this thesis, we aim to leverage data to de ...
EPFL2023Federated Learning under Covariate Shifts with Generalization Guarantees
Volkan Cevher, Grigorios Chrysos, Fanghui Liu, Thomas Michaelsen Pethick
This paper addresses intra-client and inter-client covariate shifts in federated learning (FL) with a focus on the overall generalization performance. To handle covariate shifts, we formulate a new global model training paradigm and propose Federated Impor ...
2023Classification of fall directions via wearable motion sensors
Effective fall-detection and classification systems are vital in mitigating severe medical and economical consequences of falls to people in the fall risk groups. One class of such systems is based on wearable sensors. While there is a vast amount of acade ...
ACADEMIC PRESS INC ELSEVIER SCIENCE2022The very knotty lenser: Exploring the role of regularization in source and potential reconstructions using Gaussian process regression
Reconstructing lens potentials and lensed sources can easily become an underconstrained problem, even when the degrees of freedom are low, due to degeneracies, particularly when potential perturbations superimposed on a smooth lens are included. Regulariza ...
OXFORD UNIV PRESS2022ADAGRAD Avoids Saddle Points
Kimon Antonakopoulos, Xiao Wang
Adaptive first-order methods in optimization are prominent in machine learning and data science owing to their ability to automatically adapt to the landscape of the function being optimized. However, their convergence guarantees are typically stated in te ...
2022ADAGRAD Avoids Saddle Points
Kimon Antonakopoulos, Xiao Wang
Adaptive first-order methods in optimization are prominent in machine learning and data science owing to their ability to automatically adapt to the landscape of the function being optimized. However, their convergence guarantees are typically stated in te ...
JMLR-JOURNAL MACHINE LEARNING RESEARCH2022Semantic Perturbations with Normalizing Flows for Improved Generalization
Martin Jaggi, Sebastian Urban Stich, Tatjana Chavdarova
Data augmentation is a widely adopted technique for avoiding overfitting when training deep neural networks. However, this approach requires domain-specific knowledge and is often limited to a fixed set of hard-coded transformations. Recently, several work ...
IEEE2021KPC: Learning-Based Model Predictive Control with Deterministic Guarantees
Colin Neil Jones, Yuning Jiang, Paul Scharnhorst, Emilio Maddalena
We propose Kernel Predictive Control (KPC), a learning-based predictive control strategy that enjoys deterministic guarantees of safety. Noise-corrupted samples of the unknown system dynamics are used to learn several models through the formalism of non-pa ...
2021