Xiaochuan Ding | Searcharxiv

arXiv2026

PtyRANNOSAUR: Ptychography with Robust Artificial Neural Networks Optimized for Sub-Angstrom Accuracy and Ultrafast Reconstruction

We present PtyRANNOSAUR, a data-driven neural network code that reconstructs atomic resolution electron ptychography data in seconds, 10-100x faster than standard methods. PtyRANNOSAUR uses convolutional autoencoders to map 4D-scanning transmission electron microscopy data to 2D phase images. Each model is trained on a large database of crystal structures and is tailored for a range of experimental parameters, such as accelerating voltage, convergence angle, defocus, and sample thickness. This approach yields high quality reconstructions without requiring any fine-tuning of hyperparameters. In addition, the code handles spatial partial coherence, multiple scattering, and scan position errors, which are critical for state-of-the-art electron ptychography reconstructions. By testing PtyRANNOSAUR on experimental and simulated data, we show that the neural networks accurately reconstruct atomic structures of a broad range of materials systems and can achieve high resolutions of $<0.5$ Å, comparable to the best iterative reconstructions of the same data. These advances enable near-live, state-of-the-art electron ptychography reconstructions.

cond-mat.mtrl-sci↗

arXiv2024

Classical Post-processing for Unitary Block Optimization Scheme to Reduce the Effect of Noise on Optimization of Variational Quantum Eigensolvers

Variational Quantum Eigensolvers (VQE) are a promising approach for finding the classically intractable ground state of a Hamiltonian. The Unitary Block Optimization Scheme (UBOS) is a state-of-the-art VQE method which works by sweeping over gates and finding optimal parameters for each gate in the environment of other gates. UBOS improves the convergence time to the ground state by an order of magnitude over Stochastic Gradient Descent (SGD). It nonetheless suffers in both rate of convergence and final converged energies in the face of highly noisy expectation values coming from shot noise. Here we develop two classical post-processing techniques which improve UBOS especially when measurements have large noise. Using Gaussian Process Regression (GPR), we generate artificial augmented data using original data from the quantum computer to reduce the overall error when solving for the improved parameters. Using Double Robust Optimization plus Rejection (DROPR), we prevent outlying data which are atypically noisy from resulting in a particularly erroneous single optimization step thereby increasing robustness against noisy measurements. Combining these techniques further reduces the final relative error that UBOS reaches by a factor of three without adding additional quantum measurement or sampling overhead. This work further demonstrates that developing techniques which use classical resources to post-process quantum measurement results can significantly improve VQE algorithms.

quant-ph↗