13 citations · 17 across the 10 of their papers we have counts for
10 papers
The Double Descent Behavior in Two Layer Neural Network for Binary Classification
Chathurika S Abeykoon, Aleksandr Beknazaryan, Hailin Sang
Recent studies observed a surprising concept on model test error called the double descent phenomenon, where the increasing model complexity decreases the test error first and then…
On the integrated mean squared error of wavelet density estimation for linear processes
Aleksandr Beknazaryan, Hailin Sang, Peter Adamic
Let be a linear process with density function . We study wavelet density estimation of . Under some regular conditions on the characterist…
Shallow neural network representation of polynomials
Aleksandr Beknazaryan
We show that -variate polynomials of degree can be represented on as shallow neural networks of width . Also, by SNN representation of localized Taylor p…
Nonparametric regression with modified ReLU networks
Aleksandr Beknazaryan, Hailin Sang
We consider regression estimation with modified ReLU neural networks in which network weight matrices are first modified by a function before being multiplied by input vectors.…
Function approximation and nonparametric regression with binary and ternary ReLU networks
Aleksandr Beknazaryan
We show that deep binary ReLU networks and deep sparse ternary ReLU networks can approximate -Hölder functions on . We also show that deep sparse ternary ReLU networks…
Neural networks with superexpressive activations and integer weights
Aleksandr Beknazaryan
An example of an activation function is given such that networks with activations , integer weights and a fixed architecture depending on approx…
Analytic function approximation by path norm regularized deep networks
Aleksandr Beknazaryan
We show that neural networks with absolute value activation function and with the path norm, the depth, the width and the network weights having logarithmic dependence on $1/\varep…
Function approximation by deep neural networks with parameters
Aleksandr Beknazaryan
In this paper it is shown that -smooth functions can be approximated by deep neural networks with ReLU activation function and with parameters $\{0,\pm \frac{1}{2}, \pm 1, 2\}…
Cramér Type Moderate Deviations for Random Fields
Aleksandr Beknazaryan, Hailin Sang, Yimin Xiao
We study the Cramér type moderate deviation for partial sums of random fields by applying the conjugate method. The results are applicable to the partial sums of linear random fiel…
On mutual information estimation for mixed-pair random variables
Aleksandr Beknazaryan, Xin Dang, Hailin Sang
We study the mutual information estimation for mixed-pair random variables. One random variable is discrete and the other one is continuous. We develop a kernel method to estimate…