paper-with-me

홈 › Papers

Language as a matrix product state

2017-11-04 · Vasily Pestun, John Terilla, Yiannis Vlassopoulos

We propose a statistical model for natural language that begins by considering language as a monoid, then representing it in complex matrices with a compatible translation invariant probability measure. We interpret the probability measure as arising via the Born rule from a translation invariant matrix product state.

📄 PDF Abstract BibTeX arXiv:1711.01416

Code (0)

등록된 구현이 없습니다.

Tasks

Translation

Similar Papers 제목 키워드 기반

Doping: A technique for efficient compression of LSTM models using sparse structured additive matrices

2021-02-14 · Urmish Thakker, Paul N. Whatmough, ZhiGang Liu, Matthew Mattina 외

Structured matrices, such as those derived from Kronecker products (KP), are effective at compressing neural networks, but can lead to unacceptable accuracy loss when applied to large models. In this paper, we propose th…

KOALA++: Efficient Kalman-Based Optimization of Neural Networks with Gradient-Covariance Products

2025-06-04 · Zixuan Xia, Aram Davtyan, Paolo Favaro

We propose KOALA++, a scalable Kalman-based optimization algorithm that explicitly models structured gradient uncertainty in neural network training. Unlike second-order methods, which rely on expensive second order grad…

image-classificationImage ClassificationLanguage ModelingLanguage Modelling+1

Compressing Language Models using Doped Kronecker Products

2020-01-24 · Urmish Thakker, Paul N. Whatmough, Zhi-Gang Liu, Matthew Mattina 외

Kronecker Products (KP) have been used to compress IoT RNN Applications by 15-38x compression factors, achieving better results than traditional compression methods. However when KP is applied to large Natural Language P…

Language ModelingLanguage ModellingLarge Language Model

Shortcut Matrix Product States and its applications

2018-12-13 · Zhuan Li, Pan Zhang

Matrix Product States (MPS), also known as Tensor Train (TT) decomposition in mathematics, has been proposed originally for describing an (especially one-dimensional) quantum system, and recently has found applications i…

Computational Efficiency

Tensor train decompositions on recurrent networks

2020-06-09 · Alejandro Murua, Ramchalam Ramakrishnan, Xinlin Li, Rui Heng Yang 외

Recurrent neural networks (RNN) such as long-short-term memory (LSTM) networks are essential in a multitude of daily live tasks such as speech, language, video, and multimodal learning. The shift from cloud to edge compu…