|
|
QTML 2023: 7TH INTERNATIONAL CONFERENCE ON QUANTUM TECHINQUES IN MACHINE LEARNING
PROGRAM
Days: Sunday, November 19th Monday, November 20th Tuesday, November 21st Wednesday, November 22nd Thursday, November 23rd Friday, November 24th Sunday, November 19th View this program: with abstractssession overviewtalk overview 10:30-13:15 Session 1A TUTORIAL 1
Speaker: Hsin-Yuan (Robert) Huang
Title: Learning theory for quantum machines
14:45-18:00 Session 2A TUTORIAL 2
Speaker: Sevag Gharibian
Title: Quantum algorithms – what’s quantum complexity theory got to do with it?
Monday, November 20th View this program: with abstractssession overviewtalk overview 12:00-13:15 Session 7: Quantum Learning and Quantum Advantage | 12:00 | Classical Verification of Quantum Learning | | 12:30 | Learning bounds and guarantees for testing (quantum) hypotheses | | 12:45 | Exponential separations between classical and quantum learners | | 13:00 | Classical simulations of noisy variational quantum circuits |
14:45-16:00 Session 8: Quantum Models and Data | 14:45 | Non-IID Quantum Federated Learning with One-shot Communication Complexity | | 15:00 | Quantum models and data through a precomputation lens | | 15:30 | Demystify Problem-Dependent Power of Quantum Neural Networks on Multi-Class Classification |
16:00-17:30 Session 9: Generalisation | 16:00 | Transition role of entangled data in quantum machine learning | | 16:30 | The power and limitations of learning quantum dynamics incoherently | | 17:00 | Understanding generalization with quantum geometry | | 17:15 | Understanding quantum machine learning also requires rethinking generalization |
Tuesday, November 21st View this program: with abstractssession overviewtalk overview 09:15-10:45 Session 10: Architectures for QML 1 | 09:15 | Let Quantum Neural Networks Choose Their Own Frequencies | | 09:30 | Extending Graph Transformers with Quantum Computed Aggregation | | 09:45 | QResNet: a variational entanglement skipping algorithm | | 10:00 | A General Approach for Dropout in Quantum Neural Networks | | 10:15 | Hierarchical quantum circuit representations for neural architecture search | | 10:30 | Applying Genetic Algorithms to Optimize the Generalization Ability of Variational Quantum Circuits |
14:45-17:00 Session 13: Trainability of Quantum Architectures | 14:45 | Trainability barriers and opportunities in quantum generative modeling | | 15:15 | On the Sample Complexity of Quantum Boltzmann Machine Learning | | 15:45 | On the Absence of Barren Plateaus in Quantum Generative Adversarial Networks | | 16:15 | Deep quantum neural networks form Gaussian processes | | 16:45 | Splitting and Parallelizing of Quantum Convolutional Neural Networks for Learning Translationally Symmetric Data |
Wednesday, November 22nd View this program: with abstractssession overviewtalk overview 12:00-13:15 Session 17: Machine learning for quantum science | 12:00 | Machine learning continuously monitored systems: estimating parameters | | 12:15 | Deep Learning of Quantum Correlations for Quantum Parameter Estimation of Continuously Monitored Systems | | 12:30 | Channel tomography for quantum noise characterization and mitigation | | 12:45 | Explainable Representation Learning of Small Quantum States |
Thursday, November 23rd View this program: with abstractssession overviewtalk overview 09:00-10:45 Session 21: Quantum Algorithms | 09:00 | Quadratic Speedup in Quantum Zero-Sum Games via Single-Call Mirror-Prox Matrix Methods | | 09:30 | Constant-depth circuits for Uniformly Controlled Gates and Boolean functions with application to quantum memory circuits | | 10:00 | Quantum Distance Calculation for ε-Graph Construction | | 10:15 | Gibbs Sampling of Periodic Potentials on a Quantum Computer |
12:00-13:15 Session 23: Quantum Kernels | 12:00 | A Topological Features Based Quantum Kernel | | 12:15 | Expressivity and Generalization Ability of Trace-induced Quantum Kernels | | 12:45 | A Multi-Class Quantum Kernel-Based Classifier | | 13:00 | Neural Quantum Embedding: Pushing the Limits of Quantum Supervised Learning |
15:30-17:00 Session 25: QML for Physics | 15:30 | Quantum anomaly detection in the latent space of proton collision events at the LHC | | 15:45 | Quantum data learning for quantum simulations in high-energy physics | | 16:00 | Ab initio Quantum Simulation of Strongly Correlated Materials with Quantum Embedding | | 16:15 | Detection of quantum phase transitions with quantum machine learning techniques | | 16:30 | Simulating dynamics of large quantum systems on small quantum devices using circuit knitting | | 16:45 | Complete quantum-inspired framework for simulations of flows past immersed bodies |
Friday, November 24th View this program: with abstractssession overviewtalk overview 12:00-13:15 Session 29: Reinforcement Learning and Robust Learning | 12:00 | Quantum adaptive agents with efficient long-term memories | | 12:30 | Self-Correcting Quantum Many-Body Control using Reinforcement Learning with Tensor Networks | | 12:45 | Quantum machine learning with enhanced adversarial robustness | | 13:00 | Quantum algorithm for robust optimization via stochastic-gradient online learning |
15:30-16:15 Session 31: Quantum Optimization | 15:30 | On The Performance And Limitation Of Quantum Approximate Optimization | | 15:45 | Quantum optimization of Binary Neural Networks | | 16:00 | Performance Analysis and Comparative Study of Quantum Approximate Optimization Algorithm Variants |
16:15-17:00 Session 32: Quantum Reservoir Computing | 16:15 | Hybrid quantum-classical reservoir computing for solving chaotic systems | | 16:30 | Next Generation Quantum Reservoir Computing: An Efficient Quantum Algorithm for Forecasting Quantum Dynamics | | 16:45 | Time-series quantum reservoir computing with weak and projective measurements |
|
|