Explore the intersection of quantum computing and machine learning through this comprehensive workshop featuring leading experts from mathematics, quantum algorithms, and machine learning. Delve into cutting-edge research on how quantum computers can exponentially improve learning from quantum data, enable sampling from complex probability distributions, and accelerate machine learning subroutines. Examine the mathematical foundations underlying quantum machine learning, including quantum backpropagation, barren plateaus in parametrized quantum circuits, exponential concentration in quantum generative modeling, and quantum kernel methods. Investigate the potential of parameterized quantum circuits for machine learning applications, classical verification of quantum learning processes, and the role of data and communication in quantum learning landscapes. Learn about quantum statistical query learning, structured quantum state learning, and quantum speedups for nonconvex optimization through quantum tunneling walks. Discover applications in quantum simulation using language models, training binary neural networks in quantum superposition, and generating approximate ground states of molecules using quantum machine learning techniques. Address fundamental questions about exponential separations between classical and quantum learners, generalization in quantum machine learning, and the practical advantages of quantum systems over classical counterparts in various learning scenarios.

Syllabus

Maria Schuld - How to rethink quantum machine learning - IPAM at UCLA
Amira Abbas - On quantum backpropagation and information reuse - IPAM at UCLA
Nathan Wiebe - Quantum Machine Learning - IPAM at UCLA
Zoe Holmes - Exponential Concentration in Quantum Generative Modeling and Quantum Kernel Methods
Marco Cerezo - A Unified Theory of Barren Plateaus for Deep Parametrized Quantum Circuits
Yihui Quek - Signal and noise: learning with random quantum circuits and other agents of chaos
Jens Eisert - Do quantum computers have application in machine learning & combinatorial optimization
Roger Melko - Language Models for Quantum Simulation - IPAM at UCLA
Ryan Sweke - Should we use parameterized quantum circuits for machine learning? - IPAM at UCLA
Learning of neural networks w/ quantum computers & learning of quantum states with graphical models
Vedran Dunjko - Exponential separations between classical and quantum learners - IPAM at UCLA
Hsin-Yuan (Robert) Huang - Learning to predict arbitrary quantum processes - IPAM at UCLA
Juan Carrasquilla - Training Binary Neural Networks in Quantum Superposition - IPAM at UCLA
Matthias Caro - Classical Verification of Quantum Learning - IPAM at UCLA
Jarrod McClean - The role of data, precomputation, and communication in a quantum learning landscape
Carlos Bravo Prieto - Understanding quantum machine learning also requires rethinking generalization
Marika Maria Kieferova - Generating Approx. Ground State of Molecules Using Quantum Machine Learning
Vojtěch Havlíček - Quantum Statistical Query Learning I of II - IPAM at UCLA
Daniel Liang - Learning Beyond Stabilizer States - IPAM at UCLA
Tongyang Li - On Quantum Speedups for Nonconvex Optimization via Quantum Tunneling Walks
Louis Schatzki - Quantum Statistical Query Learning II of II - IPAM at UCLA
Srinivasan Arunachalam - Overview of learning structured quantum states - IPAM at UCLA