Amaury Habrard

Leveraging PAC-Bayes Theory and Gibbs Distributions for Generalization Bounds with Complexity Measures

2024 · arXiv (Cornell University)

In statistical learning theory, a generalization bound usually involves a complexity measure imposed by the considered theoretical framework. This limits the scope of such bounds, as other forms of capacity measures or regularizations are used …

Dict2vec : Learning Word Embeddings using Lexical Dictionaries

2017

Learning word embeddings on large unlabeled corpus has been shown to be successful in improving many natural language tasks. The most efficient and popular approaches learn or retrofit such representations using additional external data. Resulting …

Near-lossless Binarization of Word Embeddings

2019 · HAL (Le Centre pour la Communication Scientifique Directe)

International audience