SeQuant introduces a graph-theoretic tensor network canonicalizer for efficient symbolic manipulation and numerical evaluation of tensors over commutative and non-commutative rings, with support for noncovariant and nested tensors.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Multi-task autoencoders with outlier detection and federated SVDD loss filter noisy samples in non-IID federated learning, yielding accuracy gains up to 7% on CIFAR-10.
citing papers explorer
-
SeQuant Framework for Symbolic and Numerical Tensor Algebra. I. Core Capabilities
SeQuant introduces a graph-theoretic tensor network canonicalizer for efficient symbolic manipulation and numerical evaluation of tensors over commutative and non-commutative rings, with support for noncovariant and nested tensors.
-
Sample Selection Using Multi-Task Autoencoders in Federated Learning with Non-IID Data
Multi-task autoencoders with outlier detection and federated SVDD loss filter noisy samples in non-IID federated learning, yielding accuracy gains up to 7% on CIFAR-10.