← Search

Shashank Subramanian

2 accepted papers

2024

Data-Efficient Operator Learning via Unsupervised Pretraining and In-Context Learning

NeurIPS 2024poster

Recent years have witnessed the promise of coupling machine learning methods and physical domain-specific insights for solving scientific problems based on partial differential equations (PDEs). However, being data-intensive, these methods still require a large amount of PDE data. This reintroduces…

2023

Towards Foundation Models for Scientific Machine Learning: Characterizing Scaling and Transfer Behavior

NeurIPS 2023poster

Pre-trained machine learning (ML) models have shown great performance for a wide range of applications, in particular in natural language processing (NLP) and computer vision (CV). Here, we study how pre-training could be used for scientific machine learning (SciML) applications, specifically in the…

Cited by 85SourcePDFScholar