L
Lorenzo Rosasco
Researcher at University of Genoa
Publications - 294
Citations - 11455
Lorenzo Rosasco is an academic researcher from University of Genoa. The author has contributed to research in topics: Regularization (mathematics) & Kernel method. The author has an hindex of 46, co-authored 266 publications receiving 9289 citations. Previous affiliations of Lorenzo Rosasco include Massachusetts Institute of Technology & Austrian Academy of Sciences.
Papers
More filters
Proceedings Article
Holographic embeddings of knowledge graphs
TL;DR: Holographic embeddings are proposed to learn compositional vector space representations of entire knowledge graphs to outperform state-of-the-art methods for link prediction on knowledge graphs and relational learning benchmark datasets.
Journal ArticleDOI
On Early Stopping in Gradient Descent Learning
TL;DR: A family of gradient descent algorithms to approximate the regression function from reproducing kernel Hilbert spaces (RKHSs) is studied, the family being characterized by a polynomial decreasing rate of step sizes (or learning rate).
Book
Kernels for Vector-Valued Functions: A Review
TL;DR: This monograph reviews different methods to design or learn valid kernel functions for multiple outputs, paying particular attention to the connection between probabilistic and functional methods.
Journal ArticleDOI
Are loss functions all the same
TL;DR: A convexity assumption is introduced, which is met by all loss functions commonly used in the literature, and how the bound on the estimation error changes with the loss is studied.
Journal ArticleDOI
Why and When Can Deep – but Not Shallow – Networks Avoid the Curse of Dimensionality: a Review
Tomaso Poggio,Hrushikesh N. Mhaskar,Hrushikesh N. Mhaskar,Lorenzo Rosasco,Brando Miranda,Qianli Liao +5 more
TL;DR: In this article, the authors review and extend an emerging body of theoretical results on deep learning including the conditions under which it can be exponentially better than shallow learning, and a class of deep convolutional networks represent a special case of these conditions, though weight sharing is not the main reason for their exponential advantage.