6 papers
Flow Annealing Posterior Sampling for Function-Space Regression and Inverse Problems
Yaozhong Shi, Zachary E. Ross, Yisong Yue
Principled regression for stochastic processes is a long-standing challenge with deep connections to scientific inverse problems. We introduce Flow Annealing Posterior Sampling (FA…
Enforcing Reciprocity in Operator Learning for Seismic Wave Propagation
Caifeng Zou, Yaozhong Shi, Zachary E. Ross +2
Accurate and efficient wavefield modeling underpins seismic structure and source studies. Traditional methods comply with physical laws but are computationally intensive. Data-driv…
Large-Scale 3D Ground-Motion Synthesis with Physics-Inspired Latent Operator Flow Matching
Yaozhong Shi, Grigorios Lavrentiadis, Konstantinos Tsalouchidis +5
Earthquake hazard analysis and design of spatially distributed infrastructure, such as power grids and energy pipeline networks, require scenario-specific ground-motion time histor…
Mesh-Informed Neural Operator : A Transformer Generative Approach
Yaozhong Shi, Zachary E. Ross, Domniki Asimaki +1
Generative models in function spaces, situated at the intersection of generative modeling and operator learning, are attracting increasing attention due to their immense potential…
Stochastic Process Learning via Operator Flow Matching
Yaozhong Shi, Zachary E. Ross, Domniki Asimaki +1
Expanding on neural operators, we propose a novel framework for stochastic process learning across arbitrary domains. In particular, we develop operator flow matching (OFM) for lea…
Universal Functional Regression with Neural Operator Flows
Yaozhong Shi, Angela F. Gao, Zachary E. Ross +1
Regression on function spaces is typically limited to models with Gaussian process priors. We introduce the notion of universal functional regression, in which we aim to learn a pr…