Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Vilucchio, Matteo"'
Regularization, whether explicit in terms of a penalty in the loss or implicit in the choice of algorithm, is a cornerstone of modern machine learning. Indeed, controlling the complexity of the model class is particularly important when data is scarc
Externí odkaz:
http://arxiv.org/abs/2410.16073
This work investigates adversarial training in the context of margin-based linear classifiers in the high-dimensional regime where the dimension $d$ and the number of data points $n$ diverge with a fixed ratio $\alpha = n / d$. We introduce a tractab
Externí odkaz:
http://arxiv.org/abs/2402.05674
Publikováno v:
Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, PMLR 238:811-819, 2024
We study robust linear regression in high-dimension, when both the dimension $d$ and the number of data points $n$ diverge with a fixed ratio $\alpha=n/d$, and study a data model that includes outliers. We provide exact asymptotics for the performanc
Externí odkaz:
http://arxiv.org/abs/2305.18974
HyperParameter Optimization (HPO) aims at finding the best HyperParameters (HPs) of learning models, such as neural networks, in the fastest and most efficient way possible. Most recent HPO algorithms try to optimize HPs regardless of the model that
Externí odkaz:
http://arxiv.org/abs/2109.14925