S
Sanae Lotfi
Researcher at École Polytechnique de Montréal
Publications - 4
Citations - 35
Sanae Lotfi is an academic researcher from École Polytechnique de Montréal. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 1, co-authored 2 publications receiving 1 citations.
Papers
More filters
Proceedings Article
Bayesian Model Selection, the Marginal Likelihood, and Generalization
TL;DR: It is shown how marginal likelihood can be negatively correlated with generalization, with implications for neural architecture search, and can lead to both underfitting and overfitting in hyperparameter learning.
Proceedings ArticleDOI
PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization
Sanae Lotfi,Marc Finzi,Sanyam Kapoor,Andres Potapczynski,Micah Goldblum,Andrew Gordon Wilson +5 more
TL;DR: The authors developed a compression approach based on quantizing neural network parameters in a linear subspace to provide state-of-the-art generalization bounds on a variety of tasks, including transfer learning.
Posted ContentDOI
Stochastic Damped L-BFGS with Controlled Norm of the Hessian Approximation
TL;DR: This work empirically demonstrates that VARCHEN is more robust than SdLBFGS-VR and SVRG on a modified DavidNet problem, and their performance is comparable on a logistic regression problem and a nonconvex support-vector machine problem.
Posted Content
Adaptive First- and Second-Order Algorithms for Large-Scale Machine Learning.
TL;DR: In this paper, both first-and second-order techniques for continuous optimization problems arising in machine learning have been proposed and evaluated on well-known deep learning datasets and exhibit promising performance.