Search Results for author:
Found 5 papers, 0 papers with code
Tensor network compressibility of convolutional models
We explore this by assessing how truncating the convolution kernels of dense (untensorized) CNNs impact their accuracy.
CompactifAI: Extreme Compression of Large Language Models using Quantum-Inspired Tensor Networks
Traditional compression methods such as pruning, distillation, and low-rank approximation focus on reducing the effective number of neurons in the network, while quantization focuses on reducing the numerical precision of individual weights to reduce the model size while keeping the number of neurons fixed.
Efficient tensor network simulation of IBM's largest quantum processors
Apart from simulating the original experiment for 127 qubits, we also extend our results to 433 and 1121 qubits, and for evolution times around 8 times longer, thus setting a benchmark for the newest IBM quantum machines.
Quantum-Inspired Tensor Neural Networks for Option Pricing
Recent advances in deep learning have enabled us to address the curse of dimensionality (COD) by solving problems in higher dimensions.
Quantum-Inspired Tensor Neural Networks for Partial Differential Equations
We demonstrate that TNN provide significant parameter savings while attaining the same accuracy as compared to the classical Dense Neural Network (DNN).
