Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Natik, Amine"'
Autor:
Davari, MohammadReza, Horoi, Stefan, Natik, Amine, Lajoie, Guillaume, Wolf, Guy, Belilovsky, Eugene
Comparing learned neural representations in neural networks is a challenging but important problem, which has been approached in different ways. The Centered Kernel Alignment (CKA) similarity metric, particularly its linear variant, has recently beco
Externí odkaz:
http://arxiv.org/abs/2210.16156
Autor:
Natik, Amine, Smith, Aaron
Consider a random graph $G$ of size $N$ constructed according to a \textit{graphon} $w \, : \, [0,1]^{2} \mapsto [0,1]$ as follows. First embed $N$ vertices $V = \{v_1, v_2, \ldots, v_N\}$ into the interval $[0,1]$, then for each $i < j$ add an edge
Externí odkaz:
http://arxiv.org/abs/2112.04408
Autor:
Tong, Alexander, Huguet, Guillaume, Shung, Dennis, Natik, Amine, Kuchroo, Manik, Lajoie, Guillaume, Wolf, Guy, Krishnaswamy, Smita
In modern relational machine learning it is common to encounter large graphs that arise via interactions or similarities between observations in many domains. Further, in many cases the target entities for analysis are actually signals on such graphs
Externí odkaz:
http://arxiv.org/abs/2107.12334
Autor:
Tong, Alexander, Huguet, Guillaume, Natik, Amine, MacDonald, Kincaid, Kuchroo, Manik, Coifman, Ronald, Wolf, Guy, Krishnaswamy, Smita
We propose a new fast method of measuring distances between large numbers of related high dimensional datasets called the Diffusion Earth Mover's Distance (EMD). We model the datasets as distributions supported on common data graph that is derived fr
Externí odkaz:
http://arxiv.org/abs/2102.12833
Autor:
Natik, Amine
Given n arbitrary objects x1, x2, ..., xn and a similarity matrix P = (pi,j ) 1≤i,j≤n, where pi,j measures the similarity between xi and xj. If the objects can be ordered along a linear chain so that the similarity decreases as the distance inc
Externí odkaz:
http://hdl.handle.net/10393/39681