Tag
This paper proposes a method to accelerate DNN training for high-dimensional functions by introducing contextual features, including rank-1 features and tensor features from decomposed pretrained DNNs, using randomized tensor decomposition to reduce storage costs by orders of magnitude.
A research paper presenting a learning-to-rank framework for selecting efficient tensor-network contraction plans for GPU-accelerated quantum circuit simulation, using gradient-boosted rankers trained from GPU measurements.