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.
Tensor Neural Networks solve high-dimensional PDEs for financial pricing.
problem High-dimensional PDEs in financial pricing.
method Tensor Neural Networks (TNN) and Tensor Network Initializer (TNN Init).
result TNN provides significant parameter savings and faster training than DNN.
Twin neural network regression predicts differences between two data points.
problem Traditional regression methods are inaccurate for certain data sets.
method TNN regression predicts differences between two data points and averages predictions from an ensemble of all training data points.
result TNN regression yields more accurate predictions compared to other methods.
TNN models enforce safety constraints in neural networks for autonomous control.
problem Ensuring safety in neural networks for autonomous control.
method Incorporating rule-based safety constraints into neural network models through multi-headed structures and constrained optimization.
result TNN models improve safety and performance in autonomous control tasks.
Tensor Neural Networks improve regression accuracy and efficiency.
problem Nonparametric regression problems with complex, high-dimensional functions.
method Integrates statistical regression and numerical integration within a tensor neural network framework.
result Superior performance in approximation accuracy and generalization capacity compared to FFNs and RBNs.
Bayesian inference for deep neural networks using trace-class priors and MLMC.
problem Efficient Bayesian inference for deep neural networks.
method Trace-class neural network priors and Multilevel Monte Carlo method.
result Optimal computational complexity for Bayesian inference of TNN models.
This work proves exact low tubal rank tensor recovery from Gaussian measurements.
problem Low rank tensor recovery from Gaussian measurements.
method Careful choice of atomic set and computation of Gaussian width for atomic norm.
result Exact recovery of tensors with tubal rank r from O(r(n1+n2−r)n3) Gaussian measurements. A new tensor p-shrinkage nuclear norm improves low-rank tensor completion.
problem Estimating tensors from partial observations with low rank.
method Proposed tensor p-shrinkage nuclear norm (p-TNN) and an efficient algorithm.
result Upper bound of recovery error provided for the LRTC model.
Paper proposes a new model for imputing missing spatiotemporal traffic data.
problem Missing data and sparsity in spatiotemporal traffic data.
method Low-rank tensor completion (LRTC) framework with truncated nuclear norm (TNN).
result The proposed model outperforms state-of-the-art imputation models in various scenarios.
Dual-Channel Tensor Neural Network (DC-TNN) decomposes tensor data into low-rank and sparse components for better estimation and inference.
problem Tensor-valued data with multilinear dependencies are challenging to process due to loss of multiway geometry under vectorization.
method DC-TNN decomposes tensors into a low-rank core and a sparse refinement, processing them through coupled neural channels.
result Established non-asymptotic risk bounds and developed structure-aware conformal ROC and AUC confidence bands.
Proposes tensor Q-rank for better tensor rank recovery in complex data.
problem Improving tensor rank recovery for complex data with low sampling rate.
method Introduces tensor Q-rank and two selection methods for Q, proposing VMTQN and MOTQN models. result Demonstrates superior performance in tensor completion problems compared to TNN-based methods.
Estimates spatio-temporal Hawkes processes using tensor recovery.
problem Estimating influence functions for spatio-temporal Hawkes processes.
method Formulates influence function as a tensor kernel, assumes low-rank structure, solves as convex optimization problem.
result Provides theoretical guarantees and demonstrates efficiency with simulations.
SKI speeds up Toeplitz Neural Networks by avoiding explicit decay bias and using frequency response.
problem Efficiently compute and update Toeplitz matrices in neural networks.
method Sparse plus low-rank decomposition, asymmetric SKI, frequency response modeling.
result Achieved significant speedup with minimal performance loss.