Workshop report on basic research needs for scientific machine learning: Core technologies for artificial intelligence
Scientific Machine Learning (SciML) and Artificial Intelligence (AI) will have broad use and
transformative effects across the Department of Energy. Accordingly, the January 2018 Basic …
transformative effects across the Department of Energy. Accordingly, the January 2018 Basic …
Minimal variance sampling with provable guarantees for fast training of graph neural networks
Sampling methods (eg, node-wise, layer-wise, or subgraph) has become an indispensable
strategy to speed up training large-scale Graph Neural Networks (GNNs). However, existing …
strategy to speed up training large-scale Graph Neural Networks (GNNs). However, existing …
Learning nonlocal constitutive models with neural networks
Constitutive and closure models play important roles in computational mechanics and
computational physics in general. Classical constitutive models for solid and fluid materials …
computational physics in general. Classical constitutive models for solid and fluid materials …
Optimal subsampling with influence functions
Subsampling is a common and often effective method to deal with the computational
challenges of large datasets. However, for most statistical models, there is no well-motivated …
challenges of large datasets. However, for most statistical models, there is no well-motivated …
Distributed learning systems with first-order methods
Scalable and efficient distributed learning is one of the main driving forces behind the recent
rapid advancement of machine learning and artificial intelligence. One prominent feature of …
rapid advancement of machine learning and artificial intelligence. One prominent feature of …
Safe adaptive importance sampling
Importance sampling has become an indispensable strategy to speed up optimization
algorithms for large-scale applications. Improved adaptive variants--using importance …
algorithms for large-scale applications. Improved adaptive variants--using importance …
On random embeddings and their application to optimisation
Z Shao - arXiv preprint arXiv:2206.03371, 2022 - arxiv.org
Random embeddings project high-dimensional spaces to low-dimensional ones; they are
careful constructions which allow the approximate preservation of key properties, such as …
careful constructions which allow the approximate preservation of key properties, such as …
Conditional Mixture Path Guiding for Differentiable Rendering
Z Fan, P Shi, M Guo, R Fu, Y Guo, J Guo - ACM Transactions on …, 2024 - dl.acm.org
The efficiency of inverse optimization in physically based differentiable rendering heavily
depends on the variance of Monte Carlo estimation. Despite recent advancements …
depends on the variance of Monte Carlo estimation. Despite recent advancements …
On feedback sample selection methods allowing lightweight digital predistorter adaptation
In modern communication systems advanced techniques such as digital predistortion (DPD)
are required to satisfy stringent demands on transmitter linearity and efficiency. DPD …
are required to satisfy stringent demands on transmitter linearity and efficiency. DPD …
Sampling with replacement vs Poisson sampling: a comparative study in optimal subsampling
Faced with massive data, subsampling is a commonly used technique to improve
computational efficiency, and using nonuniform subsampling probabilities is an effective …
computational efficiency, and using nonuniform subsampling probabilities is an effective …