Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Skean, Oscar"'
Self-supervised learning (SSL) is a popular paradigm for representation learning. Recent multiview methods can be classified as sample-contrastive, dimension-contrastive, or asymmetric network-based, with each family having its own approach to avoidi
Externí odkaz:
http://arxiv.org/abs/2310.02903
Autor:
Skean, Oscar, Osorio, Jhoan Keider Hoyos, Brockmeier, Austin J., Giraldo, Luis Gonzalo Sanchez
We introduce an information-theoretic quantity with similar properties to mutual information that can be estimated from data without making explicit assumptions on the underlying distribution. This quantity is based on a recently proposed matrix-base
Externí odkaz:
http://arxiv.org/abs/2301.08164
Shellsort is a sorting method that is attractive due to its simplicity, yet it takes effort to analyze its efficiency. The heart of the algorithm is the gap sequence chosen a priori and used during sorting. The selection of this gap sequence affects
Externí odkaz:
http://arxiv.org/abs/2301.00316
Autor:
Osorio, Jhoan Keider Hoyos, Skean, Oscar, Brockmeier, Austin J., Giraldo, Luis Gonzalo Sanchez
We introduce a divergence measure between data distributions based on operators in reproducing kernel Hilbert spaces defined by kernels. The empirical estimator of the divergence is computed using the eigenvalues of positive definite Gram matrices th
Externí odkaz:
http://arxiv.org/abs/2112.01583