A unified theory of quantum neural network loss landscapes
ER Anschuetz - ar** Out Classical Components
Artificial Intelligence (AI), with its multiplier effect and wide applications in multiple areas,
could potentially be an important application of quantum computing. Since modern AI …
could potentially be an important application of quantum computing. Since modern AI …
Unconditionally separating noisy from bounded polynomial threshold circuits of constant depth
We study classes of constant-depth circuits with gates that compute restricted polynomial
threshold functions, recently introduced by [Kum23] as a family that strictly generalizes …
threshold functions, recently introduced by [Kum23] as a family that strictly generalizes …
Quantum Machine Learning: A Hands-on Tutorial for Machine Learning Practitioners and Researchers
This tutorial intends to introduce readers with a background in AI to quantum machine
learning (QML)--a rapidly evolving field that seeks to leverage the power of quantum …
learning (QML)--a rapidly evolving field that seeks to leverage the power of quantum …
Quantum Theory and Application of Contextual Optimal Transport
Optimal Transport (OT) has fueled machine learning (ML) applications across many
domains. In cases where paired data measurements ($\mu $, $\nu $) are coupled to a …
domains. In cases where paired data measurements ($\mu $, $\nu $) are coupled to a …
Quantifying the Limits of Classical Machine Learning Models Using Contextuality
Classical machine learning models struggle with learning and prediction tasks on data sets
exhibiting long-range correlations. To quantify this observation we introduce a new quantity …
exhibiting long-range correlations. To quantify this observation we introduce a new quantity …