Tag
PR-Smoother is an amortized smoother for data assimilation that preserves prescribed simulators by learning future-conditioned corrections to capture non-Gaussian posteriors. It scales to high-dimensional systems and supports joint state, parameter, and sensor-bias inference from observations alone.
This paper introduces Separable Neural Architecture (SNA), a function class that combines neural approximation with tensor decomposition to efficiently solve parametric PDEs. The method achieves dramatic speedups (up to 150,000×) over traditional grid-based methods in engineering applications like laser powder bed fusion and material property prediction.
This paper presents an information-theoretic analysis of multimodal learning, revealing the need to capture sample-specific interactions, and proposes DMIL, a paradigm that explicitly models and learns from these interactions via variational decomposition and fine-tuning, achieving superior performance.