Tensor-Train Decomposition
PulseAugur coverage of Tensor-Train Decomposition — every cluster mentioning Tensor-Train Decomposition across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
MetaTT introduces parameter-efficient fine-tuning via Tensor Train adapters
Researchers have introduced MetaTT, a novel framework for parameter-efficient fine-tuning of pre-trained transformer models. MetaTT utilizes a Tensor Train (TT) adapter to factorize transformer sub-modules, allowing for…
-
New Graph Transformer Improves Inference in Graphical Models
Researchers have developed In-Context Graphical Inference (ICG-I), a novel autoregressive Graph Transformer designed to improve marginal inference in discrete graphical models. This new method mimics the Variable Elimin…
-
Tensor train algorithms offer new approach to anomaly detection
Researchers have developed new algorithms for anomaly detection using tensor network representations, specifically the Tensor Train format. These methods work by compressing normal data while effectively discarding anom…
-
New algorithms offer efficient finite initialization for tensorized neural networks
Researchers have developed novel algorithms for initializing layers in tensorized neural networks and tensor network algorithms. These methods utilize partial computations of Frobenius norms and positive lineal entrywis…