Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Maziar Sanjabi"'
We propose an autoregressive entity linking model, that is trained with two auxiliary tasks, and learns to re-rank generated samples at inference time. Our proposed novelties address two weaknesses in the literature. First, a recent method proposes t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2104f4fc11ece7ad4a531bd63ea0f599
Publikováno v:
ACM Transactions on Graphics. 38:1-14
Achieving highly detailed terrain models spanning vast areas is crucial to modern computer graphics. The pipeline for obtaining such terrains is via amplification of a low-resolution terrain to refine the details given a desired theme, which is a tim
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9527df1ca27aa3fc64906e8ba377283b
https://doi.org/10.1145/3355089.3356553
https://doi.org/10.1145/3355089.3356553
To reduce a model size but retain performance, we often rely on knowledge distillation (KD) which transfers knowledge from a large "teacher" model to a smaller "student" model. However, KD on multimodal datasets such as vision-language tasks is relat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::82515cdc012e632575fd59d6db928b0c
Autor:
Yiwei Zhao, Navid Aghdaie, Harold Henry Chaput, Kazi Atif-Uz Zaman, Han Liu, Maziar Sanjabi, Jingwen Liang, Mohsen Sardari
Publikováno v:
ICIP
Generating realistic urban environments by scattering or placing buildings on maps is a challenging problem. Unlike the existing procedural methods, we employ a data-driven approach to this problem. We combine two recent advances in machine learning
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1fc57a4007a95da9663c5f42b15eb559
https://doi.org/10.1109/icip40778.2020.9190748
https://doi.org/10.1109/icip40778.2020.9190748
The min-max optimization problem, also known as the saddle point problem, is a classical optimization problem which is also studied in the context of zero-sum games. Given a class of objective functions, the goal is to find a value for the argument w
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e7f6a6dec08cef3023de5dc5dde3786a
Publikováno v:
ACSSC
Federated learning aims to jointly learn statistical models over massively distributed remote devices. In this work, we propose FedDANE, an optimization method that we adapt from DANE, a method for classical distributed optimization, to handle the pr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3b661edf9b2c9e4d5d0acf9c8a9b6b19
Publikováno v:
DSW
In recent years, Generative Adversarial Networks (GANs) have drawn a lot of attentions for learning the underlying distribution of data in various applications. Despite their wide applicability, training GANs is notoriously difficult. This difficulty
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f90bc993420f44dd82fa9bbcff10594b
https://doi.org/10.1109/dsw.2019.8755568
https://doi.org/10.1109/dsw.2019.8755568
Autor:
Mingyi Hong, Ruoyu Sun, Maziar Sanjabi, Wei-Cheng Liao, Hadi Baligh, Zhi-Quan Luo, Meisam Razaviyayn
Publikováno v:
IEEE Signal Processing Magazine. 31:56-68
To cope with the growing demand for wireless data and to extend service coverage, future fifth-generation (5G) networks will increasingly rely on the use of low-power nodes to support massive connectivity in a diverse set of applications and services
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::815349abbf09bbd53f514d1527ffdc66
https://doi.org/10.1109/msp.2014.2335237
https://doi.org/10.1109/msp.2014.2335237
Publikováno v:
Journal of the Operations Research Society of China. 2:123-141
Consider the problem of minimizing the sum of two convex functions, one being smooth and the other non-smooth. In this paper, we introduce a general class of approximate proximal splitting (APS) methods for solving such minimization problems. Methods
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6e97f2ab79f92c060ac612afc3191f44
https://doi.org/10.1007/s40305-014-0047-x
https://doi.org/10.1007/s40305-014-0047-x
Publikováno v:
IEEE Transactions on Signal Processing. 62:1950-1961
Consider a downlink MIMO heterogeneous wireless network with multiple cells, each containing many mobile users and a number of base stations with varying capabilities. A central task in the management of such a network is to assign each user to a bas
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f31a3fdccf6a5e569e3cbf4ca29be319
https://doi.org/10.1109/tsp.2014.2303946
https://doi.org/10.1109/tsp.2014.2303946