Zobrazeno 1 - 10
of 224
pro vyhledávání: '"Aguiar, Pedro M."'
First-order methods for stochastic optimization have undeniable relevance, in part due to their pivotal role in machine learning. Variance reduction for these algorithms has become an important research topic. In contrast to common approaches, which
Externí odkaz:
http://arxiv.org/abs/2109.03207
Autor:
Martins, André F. T., Treviso, Marcos, Farinhas, António, Aguiar, Pedro M. Q., Figueiredo, Mário A. T., Blondel, Mathieu, Niculae, Vlad
Exponential families are widely used in machine learning, including many distributions in continuous and discrete domains (e.g., Gaussian, Dirichlet, Poisson, and categorical distributions via the softmax transformation). Distributions in each of the
Externí odkaz:
http://arxiv.org/abs/2108.01988
Visual attention mechanisms are a key component of neural network models for computer vision. By focusing on a discrete set of objects or image regions, these mechanisms identify the most relevant features and use them to build more powerful represen
Externí odkaz:
http://arxiv.org/abs/2104.03046
Autor:
Martins, André F. T., Farinhas, António, Treviso, Marcos, Niculae, Vlad, Aguiar, Pedro M. Q., Figueiredo, Mário A. T.
Exponential families are widely used in machine learning; they include many distributions in continuous and discrete domains (e.g., Gaussian, Dirichlet, Poisson, and categorical distributions via the softmax transformation). Distributions in each of
Externí odkaz:
http://arxiv.org/abs/2006.07214
The majority of current object detectors lack context: class predictions are made independently from other detections. We propose to incorporate context in object detection by post-processing the output of an arbitrary detector to rescore the confide
Externí odkaz:
http://arxiv.org/abs/1912.12290
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
We implement several non-binary logic systems using the spin dynamics of nuclear spins in nuclear magnetic resonance (NMR). The NMR system is a suitable test system because of its high degree of experimental control; findings from NMR implementations
Externí odkaz:
http://arxiv.org/abs/1512.00521
The Discrete Cosine Transform (DCT) is widely used in lossy image and video compression schemes, e.g., JPEG and MPEG. In this paper, we show that the compression efficiency of the DCT is dependent on the edge directions within a block. In particular,
Externí odkaz:
http://arxiv.org/abs/1411.4290
In this paper we consider a network with $P$ nodes, where each node has exclusive access to a local cost function. Our contribution is a communication-efficient distributed algorithm that finds a vector $x^\star$ minimizing the sum of all the functio
Externí odkaz:
http://arxiv.org/abs/1305.1885
Autor:
Martins, Andre F. T., Figueiredo, Mario A. T., Aguiar, Pedro M. Q., Smith, Noah A., Xing, Eric P.
We propose AD3, a new algorithm for approximate maximum a posteriori (MAP) inference on factor graphs based on the alternating directions method of multipliers. Like dual decomposition algorithms, AD3 uses worker nodes to iteratively solve local subp
Externí odkaz:
http://arxiv.org/abs/1212.6550