Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,291 papers · 148 categories

Trend · papers per month

285684112 · Jun 202019922001200920182026
48 results for Tensor Compression

Tensor regression networks improve neural network compression and regularization.

problem Improving neural network compression and regularization with low-rank tensor approximations.
method Investigating various low-rank tensor approximations in tensor regression networks.
result Tensor regression networks with Global Average Pooling layer outperformed in deep CNNs, while shallow CNNs with tensor regression and dropout achieved lower test error.

New result on tensor recovery without strong assumptions.

problem Recoverability of randomly compressed tensors with low CP rank.
method Deriving restricted isometry property (R.I.P.) via set covering techniques.
result The tensor is recoverable if the number of measurements is proportional to the model parameters.

This paper proposes a method to automatically compress neural networks using Bayesian tensor decomposition.

problem Challenges in directly applying tensor compression in neural network training.
method Bayesian tensorized neural network with automatic rank selection.
result Produces significantly more compact neural networks (7.4x to 137x) directly from training.

T-Basis represents neural network tensors with fewer parameters.

problem Efficiently representing neural network tensors with fewer parameters.
method T-Basis uses Tensor Rings to represent tensors in a neural network, parameterizing them with a small number of coefficients.
result T-Basis achieves high compression rates with minimal performance loss.

Optimizes tensor rank selection for neural network compression.

problem Finding optimal tensor rank for regression models.
method Analyzes population expressions for training-testing discrepancy under Gaussian design.
result Optimal rank minimizes prediction error and aligns with cross-validation.

HOTCAKE compresses CNNs by decomposing kernels into smaller parts.

problem Compressing deep CNNs without significant accuracy loss.
method Input channel decomposition, guided Tucker rank selection, higher order Tucker decomposition, fine-tuning.
result HOTCAKE produces highly compressed CNN models with good accuracy.

Efficiently price high-dimensional Bermudan options using tensor compression.

problem High-dimensional option pricing with computational complexity.
method Hierarchical tensor compression for Monte Carlo and dual martingale methods.
result Tensor compression alleviates the curse of dimensionality for Bermudan option pricing.

This work tackles fast and accurate low-rank factorization of compressed data.

problem Accurately and efficiently computing low-rank matrix or tensor factorizations from compressed data.
method Factorization in the compressed domain followed by reconstruction of original factors.
result Provable recovery of original factors under certain conditions.

Tensorial Neural Networks improve neural network compression and performance.

problem Efficiently compressing neural networks while maintaining or improving performance.
method Introducing tensor operations on high-order operands to solve hierarchical nonlinear tensor decomposition using stochastic gradient descent.
result TNNs achieve up to 5% test accuracy improvement on CIFAR10 compared to state-of-the-art compression methods.

New taxonomy and evaluation of neural network compression methods.

problem Efficiency of deep neural networks in real-world applications.
method Categorization and evaluation of tensor factorization and probabilistic compression methods.
result SVD and probabilistic compression methods are complementary and give the best results.

This paper introduces a new measure to identify model redundancy in compressed CNNs.

problem Identifying remaining model redundancy in compressed CNNs.
method Developed a statistical formulation of CNNs and compressed CNNs via tensor decomposition, revealing discrepancies in sample complexity and model redundancy.
result Introduced a new model redundancy measure, the K/RK/R ratio, for compressed CNNs.

Randomly shuffled kernels can be compressed efficiently.

problem Reducing storage cost of CNN parameters on resource-limited platforms.
method Randomly-shuffled tensor decomposition (RsTD) to embed kernels into random low-rank subspaces.
result CNNs can be significantly compressed even with randomly shuffled kernels, achieving more stable accuracy.

End-to-end meta-learned system for image compression.

problem Reducing the gap between training and inference conditions in image compression.
method Model-Agnostic Meta-learning approach for latent tensor overfitting and updating encoder and decoder networks.
result Meta-learned system achieves better compression performance compared to traditional methods.

This paper develops a method to train compact neural networks with reduced memory and computational costs.

problem Training large neural networks consumes excessive resources and energy.
method End-to-end training framework using Bayesian tensor decomposition with automatic rank determination.
result The method achieves significant parameter reduction and maintains or improves accuracy.

MARS automatically selects tensor decomposition ranks, improving performance in neural network tasks.

problem Determining optimal decomposition ranks in tensor decompositions.
method MARS uses binary masks to learn optimal tensor structure during training via relaxed MAP estimation.
result MARS achieves better results than previous methods in various tasks.

We introduce a new parameterization method for deep learning layers using spectral tensor train decomposition.

problem Efficiency and stability in deep learning models with weight matrix compression.
method Spectral Tensor Train Parameterization (STTP) of weight matrices.
result Improved compression and training stability in neural networks.

Tensor trains simplify solving complex PDEs efficiently.

problem Solving high-dimensional parabolic PDEs using traditional methods is computationally infeasible.
method Reformulate PDEs as backward stochastic differential equations and use tensor train format for compression and efficient computation.
result Tensor train methods achieve a good balance between accuracy and computational efficiency.

A new sketching method reduces tensor memory usage and enables efficient tensor operations.

problem Efficiently compressing and retaining tensor structure in large datasets.
method Higher-order Count Sketch (HCS) using multiple hash functions and tensor products.
result HCS achieves significant memory savings and efficient tensor operations.

This paper finds a new way to compress CNN weights, improving on pruning and quantization.

problem Improving performance and storage efficiency of CNNs.
method Identifying and exploiting repeated patterns in CNN weight tensors, using Huffman coding and block sparse matrix formats.
result Achieved compaction ratios of 1.4x to 3.1x in addition to pruning and quantization.

TEAFormers preserve multi-dimensional time series structures for better forecasting.

problem Traditional Transformers flatten multi-dimensional time series data, losing critical multi-dimensional relationships.
method Tensor-Augmented Transformer (TEAFormer) with Tensor-Augmentation (TEA) module.
result Significant performance enhancements in time series forecasting across benchmarks.

TensorShield defends images from adversarial attacks using tensor decomposition.

problem Adversarial attacks on images can fool deep neural networks.
method Tensor decomposition to find low-rank approximations of images, reducing high-frequency perturbations.
result TensorShield outperforms existing methods like SLQ by 14% against FGSM attacks.

Explores tensor products in hyperdimensional computing.

problem Understanding tensor products in hyperdimensional computing.
method Generalized results from graph embeddings to vector symbolic architectures and hyperdimensional computing.
result Tensor product is the most general and expressive representation with errorless unbinding and detection.