A layer-by-layer classical variational disentanglement algorithm compiles preparation circuits for matrix product states by minimizing bipartite entanglement to reduce bond dimensions.
Miles and Schwab, David J
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
abstract
Tensor networks are efficient representations of high-dimensional tensors which have been very successful for physics and mathematics applications. We demonstrate how algorithms for optimizing such networks can be adapted to supervised learning tasks by using matrix product states (tensor trains) to parameterize models for classifying images. For the MNIST data set we obtain less than 1% test set classification error. We discuss how the tensor network form imparts additional structure to the learned model and suggest a possible generative interpretation.
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 7roles
background 2polarities
background 2representative citing papers
TI MPS with permutational symmetry (entanglement similar across bipartitions) are shown to be trivial (product states or few superpositions); extends to generic MPS and states like W and Dicke approximately.
Compositional interpretability defines explanations as commuting syntactic-semantic mapping pairs grounded in compositionality and minimum description length, with compressive refinement and a parsimony theorem guaranteeing concise human-aligned decompositions.
A MERA-based autoencoder supplies a locality-aware hierarchical inductive bias that improves reconstruction-based anomaly detection for collider jets, with disentanglers providing benefit at strong compression bottlenecks.
TensorFlow-backed TensorNetwork implementation of MERA for critical 1D Ising model with conformal data extraction and 200x GPU acceleration reported.
A hybrid tensor network framework interpolates between classical and quantum models via controllable post-selection, with a trainable hyperparameter that complements bond dimension to enhance quantum machine learning.
A survey of variational quantum algorithms, quantum neural networks, and tensor networks for addressing scalability challenges in computational fluid dynamics.
citing papers explorer
-
Preparation Circuits for Matrix Product States by Classical Variational Disentanglement
A layer-by-layer classical variational disentanglement algorithm compiles preparation circuits for matrix product states by minimizing bipartite entanglement to reduce bond dimensions.
-
The product structure of MPS-under-permutations
TI MPS with permutational symmetry (entanglement similar across bipartitions) are shown to be trivial (product states or few superpositions); extends to generic MPS and states like W and Dicke approximately.
-
From Mechanistic to Compositional Interpretability
Compositional interpretability defines explanations as commuting syntactic-semantic mapping pairs grounded in compositionality and minimum description length, with compressive refinement and a parsimony theorem guaranteeing concise human-aligned decompositions.
-
Quantum-Inspired Tensor Network Autoencoders for Anomaly Detection: A MERA-Based Approach
A MERA-based autoencoder supplies a locality-aware hierarchical inductive bias that improves reconstruction-based anomaly detection for collider jets, with disentanglers providing benefit at strong compression bottlenecks.
-
TensorNetwork on TensorFlow: Entanglement Renormalization for quantum critical lattice models
TensorFlow-backed TensorNetwork implementation of MERA for critical 1D Ising model with conformal data extraction and 200x GPU acceleration reported.
-
Entanglement is Half the Story: Post-Selection vs. Partial Traces
A hybrid tensor network framework interpolates between classical and quantum models via controllable post-selection, with a trainable hyperparameter that complements bond dimension to enhance quantum machine learning.
-
A review of quantum machine learning and quantum-inspired applied methods to computational fluid dynamics
A survey of variational quantum algorithms, quantum neural networks, and tensor networks for addressing scalability challenges in computational fluid dynamics.