Umut Şimşekli
4 papers in the PaperMetrix corpus
Papers by this author
-
Quantitative Propagation of Chaos for SGD in Wide Neural Networks
2020 · HAL (Le Centre pour la Communication Scientifique Directe)
International audience
-
Hausdorff Dimension, Heavy Tails, and Generalization in Neural Networks
2020 · HAL (Le Centre pour la Communication Scientifique Directe)
Despite its success in a wide range of applications, characterizing the generalization properties of stochastic gradient descent (SGD) in non-convex deep learning problems is still an important challenge. While modeling the trajectories of SGD via …
-
Heavy Tails in SGD and Compressibility of Overparametrized Neural Networks.
2021 · HAL (Le Centre pour la Communication Scientifique Directe)
International audience
-
Generalization Guarantees via Algorithm-dependent Rademacher Complexity
2023 · arXiv (Cornell University)
Algorithm- and data-dependent generalization bounds are required to explain the generalization behavior of modern machine learning algorithms. In this context, there exists information theoretic generalization bounds that involve (various forms of) mutual information, as well …