From the 1 of 5 linked papers with an AI index.
5 papers
Quantum Spectral Model: Data Reuploading with Input-Conditioned Frequency Support
Peiyong Wang, Udaya Parampalli, Casey R. Myers
A central design principle in modern machine learning and artificial intelligence is to align a model's inductive bias with the structure of its input data. For matrix-valued input…
When cheap gradients fail: the measurement cost of attacking quantum classifiers
Bacui Li, Chandra Thapa, Tansu Alpcan +1
The paper shows that shot noise from finite quantum measurements creates a natural defense against gradient-based adversarial attacks on variational quantum classifiers, requiring…
Benchmarking Swarm Optimization Algorithms for Parameter Initialization in the Quantum Approximate Optimization Algorithm
Shashank Sanjay Bhat, Peiyong Wang, Udaya Parampalli
The Quantum Approximate Optimization Algorithm (QAOA) is a prominent variational algorithm for solving combinatorial optimization problems such as the Max Cut problem. A key challe…
Encoding Matters: Benchmarking Binary and D-ary Representations for Quantum Combinatorial Optimization
Shashank Sanjay Bhat, Peiyong Wang, Joseph West +1
Combinatorial optimization problems are typically formulated using Quadratic Unconstrained Binary Optimization (QUBO), where constraints are enforced through penalty terms that int…
Computable Model-Independent Bounds for Adversarial Quantum Machine Learning
Bacui Li, Tansu Alpcan, Chandra Thapa +1
By leveraging the principles of quantum mechanics, QML opens doors to novel approaches in machine learning and offers potential speedup. However, machine learning models are well-d…