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.
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.
168,695 papers · 148 categories
Trend · papers per month
48 results for “matrix-product”
The paper analyzes stability of random matrix products with Markovian noise.
problem Analyzing stability of random matrix products with Markovian noise.
method Using a super-Lyapunov drift condition and controlled growth of matrix-valued functions, the paper provides an exponential stability result for the p-th moment of random matrix product.
result Finite-time p-th moment bounds for linear stochastic approximation and TD learning algorithms.
Shortcut Matrix Product States and its applicationscond-mat.stat-mech
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 in various applications such as compressing high-dimensional data, supervised kernel linear classifie…
The study explores how Matrix Product States can represent boolean and continuous functions.
problem Representing arbitrary boolean and continuous functions using Matrix Product States.
method Developed a construction method for MPS to represent boolean gates and proved density in continuous function space.
result MPS can accurately represent arbitrary boolean functions and continuous functions densely.
Study on Gaussian ensemble of matrix products with mixed moments computed.
problem Understanding the statistical properties of matrix products of Gaussian matrices.
method Analysis of a multi-Wishart ensemble and enumeration of non-crossing pairings.
result Mixed moments of the product matrix are computed and found to be weighted by Fuss-Catalan numbers at large .
Study on Neural Tangent Kernel of Matrix Product States and their convergence.
problem Understanding the convergence of Neural Tangent Kernel of Matrix Product States.
method Analyzing the Neural Tangent Kernel of Matrix Product States and proving its convergence in the infinite bond dimensional limit.
result The Neural Tangent Kernel of Matrix Product States converges to a constant matrix during training.
Study examines large deviations in random walks on hyperbolic spaces.
problem Large deviations in random walks on Gromov-hyperbolic spaces.
method Established large deviations results for distance and translation length of random walks.
result Deduced a special case of a conjecture regarding spectral radii of random matrix products.
Sketch Tomography improves quantum state estimation accuracy.
problem Efficiently estimating quantum states, especially MPS states.
method Hybridizes classical shadow protocol with tensor train ansatz.
result Proven convergence with quadratic sample complexity.
Curious structure of special orthogonal, unitary, and symplectic groups as products of Grassmannians discovered.
problem Understanding the structure of special orthogonal, unitary, and symplectic groups.
method Expressing these groups as products of Grassmannians realized as involution matrices.
result Special orthogonal, special unitary, and symplectic groups can be expressed as products of their corresponding Grassmannians.
MPSTime uses matrix-product states for efficient time-series ML.
problem Learning complex correlations in time-series data.
method Developed an MPS-based algorithm for joint probability distribution learning.
result MPSTime efficiently learns time-series probability distributions.
This paper introduces matrix product state (MPS) decomposition as a new and systematic method to compress multidimensional data represented by higher-order tensors. It solves two major bottlenecks in tensor compression: computation and compression quality. Regardless of tensor order, MPS compresses tensors to matrices …
Tensor networks and RNNs are equivalent, improving wave function encoding.
problem Efficiently encoding quantum states in neural networks.
method Generalized RNN architecture for tensor networks, supporting polynomial time wave function evaluation.
result Tensorial RNNs can encode quantum states with lower bond dimensions and higher accuracy.
Tensor networks for unsupervised machine learningcond-mat.stat-mech
Tensor networks improve unsupervised learning performance.
problem Improving unsupervised machine learning models.
method Autoregressive Matrix Product States (AMPS) combining quantum and machine learning.
result AMPS significantly outperforms existing tensor network models and neural networks.
A new MPS model for both classification and generation.
problem Efficiently representing and manipulating complex, high-dimensional data.
method Inspired by Matrix Product States (MPS) used in quantum computing, applies them in a classical machine learning setting.
result Dual functionality in a supervised learning framework enhances traditional training and generates more realistic samples.
Tensor Network for Anomaly Detection in the Latent Space of Proton Collision Events at the LHChep-ph
Tensor networks improve anomaly detection at LHC for new physics.
problem Identifying new phenomena in proton collision events at LHC.
method Tensor network-based anomaly detection using Matrix Product State with an isometric feature map.
result Tensor networks outperform established quantum methods in identifying new phenomena.
New method compresses LSTM networks using MPS tensor trains.
problem Challenges in maintaining performance of compressed RNNs.
method Use of MPS tensor trains for LSTM network compression.
result MPS tensor trains outperform MPOs in storage and inference time.
A new algorithm speeds up matrix multiplication without actual multiplication.
problem Efficiently multiplying matrices in machine learning.
method Learning-based algorithm that uses hashing, averaging, and byte shuffling.
result Often runs 100x faster than exact matrix products and 10x faster than current approximate methods.
Efficiently predicts long-time dynamics of quantum spin models using MLP regression.
problem Challenges in calculating long-time expectation values for quantum spin models.
method Utilized a multi-layer perceptron (MLP) model for regression on matrix product states (MPS) expectation values.
result Significantly reduced computational cost for generating long-time dynamics while maintaining high accuracy.
Unsupervised Generative Modeling Using Matrix Product Statescond-mat.stat-mech
Generative modeling, which learns joint probability distribution from data and generates samples according to it, is an important task in machine learning and artificial intelligence. Inspired by probabilistic interpretation of quantum physics, we propose a generative model using matrix product states, which is a tenso…
Paper proposes algorithms for BMF using integer programming.
problem Approximating binary input matrix as product of two smaller binary factors.
method Alternating optimization strategy using integer programming to solve subproblems and combine solutions.
result Proposed algorithms outperform state of the art on medium-scale problems.
A new tensor network method for image classification reduces computation cost.
problem Efficiently classifying images in high-dimensional spaces.
method Proposes a multi-layered tensor network (MLTN) that performs one MPS operation per layer, reducing computation cost.
result Reduces computation cost without degrading performance.
NG+ method improves deep learning efficiency and accuracy.
problem Efficiency and accuracy in deep learning models.
method Proposes NG+ method using matrix-product natural gradient approach.
result Established global convergence and provided regret bound.
Tensor networks improve sequence modeling with efficient sampling and parallelism.
problem Efficient probabilistic modeling of sequence data.
method Uniform matrix product state (u-MPS) model for sequence data.
result u-MPS enable efficient sampling and parallel evaluation of sequences.
A new algorithm POGO optimizes thousands of orthogonal matrices efficiently.
problem Optimizing thousands of orthogonal constraints at scale is computationally expensive.
method Revisits Landing algorithm, uses modern adaptive optimizers, reduces hyperparameters.
result POGO optimizes thousands of orthogonal matrices in minutes, outperforming alternatives.
Quantum computing for option pricing using MPS states.
problem Efficiently generating time series for path-dependent options on quantum computers.
method Proposes a Matrix Product State (MPS) model for time series generation and trains it for the Heston model.
result Demonstrates the MPS model's capability to generate paths in the Heston model for path-dependent option pricing.
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…
Linear representations help embed manifolds into matrix spaces.
problem Embedding manifolds into matrix spaces with effective bounds.
method Defining linear representations of -manifolds as maps into matrix spaces, encoding -actions as matrix products.
result Explicit bounds for Mostow-Palais -equivariant embeddings of -manifolds into -modules , showing for compact .
Paper proves existence of a universal codebook for low-precision quantization.
problem Optimizing low-precision approximation of matrix products in machine learning.
method Develops a universal codebook that is near-optimal for all possible statistics of input data.
result Proves existence of a universal codebook with a 0.11 bit per dimension reduction in rate.
No free lunch theorem formalized for tensor network models.
problem Understanding limitations of tensor network machine learning models.
method Formalized rigorous no-free-lunch theorem for specific tensor network models.
result Revealed intrinsic limitations of tensor network-based learning models.
Inspired by the possibility that generative models based on quantum circuits can provide a useful inductive bias for sequence modeling tasks, we propose an efficient training algorithm for a subset of classically simulable quantum circuit models. The gradient-free algorithm, presented as a sequence of exactly solvable …
The increasing needs of clustering massive datasets and the high cost of running clustering algorithms poses difficult problems for users. In this context it is important to determine if a data set is clusterable, that is, it may be partitioned efficiently into well-differentiated groups containing similar objects. We …
We demonstrate the use of tensor networks for image classification with the TensorNetwork open source library. We explain in detail the encoding of image data into a matrix product state form, and describe how to contract the network in a way that is parallelizable and well-suited to automatic gradients for optimizatio…
We consider stochastic partial differential equations appearing as Markovian lifts of matrix valued (affine) Volterra type processes from the point of view of the generalized Feller property (see e.g., \cite{doetei:10}). We introduce in particular Volterra Wishart processes with fractional kernels and values in the con…
We develop efficient algorithms to train -regularized linear classifiers with large dimensionality of the feature space, number of classes , and sample size . Our focus is on a special class of losses that includes, in particular, the multiclass hinge and logistic losses. Our approach combines several…
This work introduces 'Artificial Entanglement' to understand LLMs' fine-tuning effectiveness.
problem Understanding the effectiveness of parameter-efficient fine-tuning methods for large language models.
method Adopting a quantum-information-inspired perspective, the study measures 'Artificial Entanglement' in neural networks.
result LoRA and FFT induce distinct internal entanglement signatures but not external ones, suggesting a 'no-hair' property.
In this paper we present a new algorithm for computing a low rank approximation of the product by taking only a single pass of the two matrices and . The straightforward way to do this is to (a) first sketch and individually, and then (b) find the top components using PCA on the sketch. Our algori…
Transformers become faster by linearizing self-attention.
problem Quadratic complexity of transformers makes them slow for long sequences.
method Expressed self-attention as a linear dot-product and used matrix product associativity to reduce complexity.
result Linear transformers are up to 4000x faster on long sequences.
A new matrix concentration inequality for random products of matrices.
problem Understanding the behavior of random matrix products under bounded independent positive semidefinite matrices.
method Developed a non-asymptotic concentration inequality for the product of matrices.
result The inequality provides a bound on the deviation of the matrix product from its expected value.
Tensorized Rademacher projections outperform Gaussian projections in reducing tensor dimensions.
problem Reducing the dimension of high-dimensional tensors for machine learning.
method Tensorized Rademacher random projections using Tensor Train decomposition.
result Tensorized Rademacher projections can replace Gaussian projections in tensor compression.
We quantify uncertainty in Oja's algorithm's leading eigenvector estimation.
problem Estimating the error of Oja's algorithm's leading eigenvector from streaming data.
method Combining U-statistics, high-dimensional central limit theorems, and multiplier bootstrap.
result Established a weighted χ² approximation for the error between the eigenvector and algorithm output.
Improves tensor networks for classifying medical images.
problem Classifying 2D and 3D medical images efficiently.
method Develops LoTeNet, a tensor network that treats small image regions as orderless and aggregates local representations hierarchically.
result LoTeNet achieves comparable or superior performance to other methods with less computational resources.
Generalisation of a deep neural network (DNN) is one major concern when employing the deep learning approach for solving practical problems. In this paper we propose a new technique, named approximated orthonormal normalisation (AON), to improve the generalisation capacity of a DNN model. Considering a weight matrix W …
Random walks on hyperbolic spaces follow predictable large deviation principles.
problem Understanding the behavior of random walks on hyperbolic spaces.
method Large deviation principles for displacement and translation distances.
result Translation and displacement distances satisfy large deviation principles with the same rate function.
We present an algorithm for supervised learning using tensor networks, employing a step of preprocessing the data by coarse-graining through a sequence of wavelet transformations. We represent these transformations as a set of tensor network layers identical to those in a multi-scale entanglement renormalization ansatz…
Wasserstein Dictionary Learning: Optimal Transport-based unsupervised non-linear dictionary learningstat.ML
This paper introduces a new nonlinear dictionary learning method for histograms in the probability simplex. The method leverages optimal transport theory, in the sense that our aim is to reconstruct histograms using so-called displacement interpolations (a.k.a. Wasserstein barycenters) between dictionary atoms; such at…
New matrix ensembles better match deep neural network spectral densities.
problem Theoretical spectral density models for deep networks do not match empirical observations.
method Introduced new matrix ensemble classes to better fit observed spectral densities.
result Theoretical models for deep networks are significantly flawed.
New method compresses non-Gaussian distributions exponentially.
problem Efficiently representing and computing non-Gaussian probability distributions.
method Tensor-Network Fourier Methods using QTT representation.
result Exponential compression of non-Gaussian distributions.
Matrix product states (MPS), a tensor network designed for one-dimensional quantum systems, has been recently proposed for generative modeling of natural data (such as images) in terms of `Born machine'. However, the exponential decay of correlation in MPS restricts its representation power heavily for modeling complex…