18 citations · 22 across the 11 of their papers we have counts for
11 papers
Quantum information spreading via higher-order operator correlators
M Süzen
We provide a perspective into measuring the quantum information spreading by introducing N-operator correlators. Leveraging the idea from N-point correlation function from cosmolog…
Scrambling of Entanglement from Integrability to Chaos: Bootstrapped Time-Integrated Spread Complexity
M. Süzen
A physical relationship for the combination of scrambling via spread complexity and entanglement is characterized by the fidelity of quantum unitary dynamics. Time-integrated quant…
Wigner Cat Phases: A finely tunable system for exploring the transition to quantum chaos
M. Süzen
A quantum mechanical setting consisting of a frozen qubit composed with a fully thermalized chaotic system of N states is proposed, with potential relevance to quantum control. Obs…
Gibbs randomness-compression proposition
M Süzen
A proposition that connects randomness and compression is put forward via Gibbs entropy over set of measurement vectors associated with a lossy compression process. In building thi…
H-theorem do-conjecture
Mehmet Süzen
A pedagogical formulation of Loschmidt's paradox and H-theorem is presented with basic notation on occupancy on discrete states without invoking velocity collision operators. A con…
Equivalence in Deep Neural Networks via Conjugate Matrix Ensembles
Mehmet Süzen
A numerical approach is developed for detecting the equivalence of deep learning architectures. The method is based on generating Mixed Matrix Ensembles (MMEs) out of deep neural n…
Generalised learning of time-series: Ornstein-Uhlenbeck processes
Mehmet Süzen, Alper Yegenoglu
In machine learning, statistics, econometrics and statistical physics, cross-validation (CV) is used asa standard approach in quantifying the generalisation performance of a statis…
HARK Side of Deep Learning -- From Grad Student Descent to Automated Machine Learning
Oguzhan Gencoglu, Mark van Gils, Esin Guldogan +5
Recent advancements in machine learning research, i.e., deep learning, introduced methods that excel conventional algorithms as well as humans in several complex tasks, ranging fro…
Spectral Ergodicity in Deep Learning Architectures via Surrogate Random Matrices
Mehmet Süzen, Cornelius Weber, Joan J. Cerdà
In this work a novel method to quantify spectral ergodicity for random matrices is presented. The new methodology combines approaches rooted in the metrics of Thirumalai-Mountain (…
Anomalous diffusion in convergence to effective ergodicity
M. Süzen
The nature of diffusion is usually studied for particles or time-evolving systems. Similar in principle, such studies can be conducted by tracking how a given function of observabl…
Scaling of Ergodicity in Binary Systems
M. Süzen
Given pseudo-random binary sequence of length , assuming it consists of sub-sequences of length . We estimate how scales with growing to obtain a {\it limiting} e…