19 citations · 34 across the 4 of their papers we have counts for
6 papers
Statistical and Algorithmic Insights for Semi-supervised Learning with Self-training
Samet Oymak, Talha Cihad Gulcu
Self-training is a classical approach in semi-supervised learning which is successfully applied to a variety of machine learning problems. Self-training algorithm generates pseudo-…
Stronger Convergence Results for Deep Residual Networks: Network Width Scales Linearly with Training Data Size
Talha Cihad Gulcu
Deep neural networks are highly expressive machine learning models with the ability to interpolate arbitrary datasets. Deep nets are typically optimized via first-order methods and…
Comments on "Deep Neural Networks with Random Gaussian Weights: A Universal Classification Strategy?"
Talha Cihad Gulcu, Alper Gungor
In a recently published paper [1], it is shown that deep neural networks (DNNs) with random Gaussian weights preserve the metric structure of the data, with the property that the d…
Attack vulnerability of power systems under an equal load redistribution model
Talha Cihad Gulcu, Vaggos Chatziafratis, Yingrui Zhang +1
This paper studies the vulnerability of flow networks against adversarial attacks. In particular, consider a power system (or, any system carrying a physical flow) consisting of $N…
Achieving Secrecy Capacity of the Wiretap Channel and Broadcast Channel with a Confidential Component
Talha Cihad Gulcu, Alexander Barg
The wiretap channel model of Wyner is one of the first communication models with both reliability and security constraints. Capacity-achieving schemes for various models of the wir…
Interactive Function Computation via Polar Coding
Talha Cihad Gulcu, Alexander Barg
In a series of papers N. Ma and P. Ishwar (2011-13) considered a range of distributed source coding problems that arise in the context of iterative computation of functions, charac…