New model encodes multivariate signals more efficiently with sparsity and low-rank constraints.
problem Efficiently encoding multivariate signals with sparsity and low-rank constraints.
method Multivariate convolutional sparse coding with tensor algebra, CP decomposition, and alternating optimization.
result Proves model closely related to Kruskal tensor regression problem with theoretical guarantees.
A new feature coding method for invariant features using tensor products.
problem Learning invariant features for transformations represented by orthogonal matrices.
method Group-invariant feature vector using tensor-product representations of basic representations.
result Group-invariant feature vector contains sufficient discriminative information for linear classifiers.
New CSC model extracts EEG signals with low noise sensitivity.
problem Analyzing noisy EEG signals during anesthesia.
method Kruskal CSC model using Kruskal decomposition for low-rank tensor activations.
result TC-FISTA efficiently extracts robust, sparse, and interpretable EEG encodings.
OpEvo automates tensor operator optimization for better efficiency.
problem Manual optimization of tensor operators is inefficient and limited.
method OpEvo uses evolutionary computation with topology-aware mutation.
result OpEvo finds optimal configurations with less effort and variance.
swTVM optimizes deep learning code for Sunway processors.
problem Efficiently compiling deep learning models for Sunway processors.
method Extends TVM to support Sunway, leveraging architecture features.
result 1.79x improvement on average across benchmarks.
To ensure interpretability of extracted sources in tensor decomposition, we introduce in this paper a dictionary-based tensor canonical polyadic decomposition which enforces one factor to belong exactly to a known dictionary. A new formulation of sparse coding is proposed which enables high dimensional tensors dictiona…
A new framework improves tensor completion accuracy by considering numerical priors.
problem Tensor completion accuracy loss due to ignoring numerical priors.
method Generalized CP Decomposition Tensor Completion (GCDTC) framework incorporating numerical priors.
result GCDTC framework outperforms state-of-the-arts in non-negative tensor completion.
SimTensor is a multi-platform, open-source software for generating artificial tensor data (either with CP/PARAFAC or Tucker structure) for reproducible research on tensor factorization algorithms. SimTensor is a stand-alone application based on MATALB. It provides a wide range of facilities for generating tensor data w…
Paper derives formulas for higher-order curvature derivatives of framed space curves.
problem Deriving exact formulas for higher-order derivatives of curvature of framed space curves.
method Parametrizing rotation tensor using Gibbs vector, deriving closed-form formulas for derivatives, and formulating a linearized updating algorithm.
result Closed-form formulas and a linearized updating algorithm for curvature and its derivatives of framed space curves.
Unsupervised framework learns latent codes for controllable generation.
problem Challenging to achieve controllable generation with GANs.
method Self-training iterative feedback from discriminator to generator.
result Better disentanglement and semantic meaningful latent codes.
The present article proposes a partial answer to the explicit inversion of the tensor tomography problem in two dimensions, by proving injectivity over certain kinds of tensors and providing reconstruction formulas for them. These tensors are symmetric differentials of any order as well as other types obtained after ta…
A new kernel simplifies deep learning code and boosts performance.
problem Complex and hard-to-maintain DL codebases.
method Introducing a batch-reduce GEMM kernel for deep learning.
result Deep learning algorithms can be implemented with just 3K lines of code.
This paper improves financial simulations using Tensor Processing Units and Tensorflow.
problem Estimating sensitivities in financial models efficiently.
method Utilizing Tensor Processing Units and Tensorflow for fast and automated differentiation.
result Single line of code for estimating sensitivities in financial models.
New framework constructs holographic tensor networks using hyperbolic buildings.
problem Building holographic tensor networks for non-integer dimensions and fractal spaces.
method Introducing a unifying framework based on hyperbolic buildings and dualities.
result Constructs a family of bulk regions satisfying complementary recovery and Ryu-Takayanagi formula.
Ansor generates high-performance tensor programs for deep learning.
problem Generating high-performance tensor programs for deep learning on various hardware platforms is challenging.
method Ansor uses a hierarchical representation of the search space, sampling programs, and evolutionary search with a learned cost model to find high-performance programs.
result Ansor improves deep neural network execution performance up to 3.8x on Intel CPU, 2.6x on ARM CPU, and 1.7x on NVIDIA GPU.
Most popular word embedding techniques involve implicit or explicit factorization of a word co-occurrence based matrix into low rank factors. In this paper, we aim to generalize this trend by using numerical methods to factor higher-order word co-occurrence based arrays, or \textit{tensors}. We present four word embedd…
Paper develops a method to robustly cluster tensors with outliers.
problem Clustering tensors contaminated by outliers or sample-specific corruptions.
method Transformed Tensor Low-Rank Representation (OR-TLRR) method.
result Provably recovers row space of clean data and detects outliers.
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.
The study evaluates memory and capacity of graph embedding methods.
problem Assessing the memory and capacity of graph embedding methods.
method Not specified in the abstract provided.
result Not specified in the abstract provided.
Proposes a new graph representation method using tensor products.
problem Dynamic graph representation and theoretical properties.
method Bind-and-sum approach in hyperdimensional computing (HDC), tensor product as binding operation.
result Memory vs. size analysis of graph representation size scaling.
Develops a tensor decomposition method with side information.
problem Identifying the relationship between a high-dimensional tensor and side information.
method Supervised tensor decomposition incorporating multiple feature matrices.
result Captures effective dimension reduction of the data tensor in feature space.
Learning an encoding of feature vectors in terms of an over-complete dictionary or a information geometric (Fisher vectors) construct is wide-spread in statistical signal processing and computer vision. In content based information retrieval using deep-learning classifiers, such encodings are learnt on the flattened la…
Recent advances suggest that a wide range of computer vision problems can be addressed more appropriately by considering non-Euclidean geometry. This paper tackles the problem of sparse coding and dictionary learning in the space of symmetric positive definite matrices, which form a Riemannian manifold. With the aid of…
Method learns topological states from randomized measurements.
problem Detecting topologically ordered two-dimensional states on quantum processors.
method Variational tensor network tomography with randomized measurements.
result Demonstrated ability to learn ground states of surface code and quantum spin liquid states.
Kjolstad et. al. proposed a tensor algebra compiler. It takes expressions that define a tensor element-wise, such as fij(a,b,c,d)=exp[−∑k=04((aik+bjk)2cii+di+k3)], and generates the corresponding compute kernel code. For machine learning, especially deep learni…
Bayesian method for imputing missing values in tensor data.
problem Missing data in multi-way arrays (tensors) in biomedical studies.
method Flexible Bayesian framework with conjugate priors for CP factorization.
result Accurately captures uncertainty in microbiome profiles at missing timepoints.
FunBaT extends Tucker decomposition to handle continuous-indexed tensor data.
problem Handling continuous-indexed tensor data that doesn't fit traditional Tucker decomposition.
method FunBaT treats continuous-indexed data as interactions between a core tensor and a group of latent functions modeled by Gaussian processes (GP). It converts each GP into a state-space prior and uses advanced message-passing techniques for scalable inference.
result FunBaT effectively handles real-world data with continuous indexes, demonstrating its advantage in synthetic and real-world applications.
Proposes polynomial neural networks for improved function approximation in various tasks.
problem Improving function approximation in various tasks like image generation, face verification, and 3D mesh representation learning.
method Introduces polynomial neural networks (Π-Nets) and three tensor decompositions to reduce parameter count and enhance expressiveness. result Demonstrates that Π-Nets can produce state-of-the-art results in challenging tasks without non-linear activation functions. DEMOTE uses neural diffusion-reaction processes to capture temporal dynamics in sparse tensor data.
problem Sparse and temporally associated tensor data with limited structural knowledge.
method Develops a neural diffusion-reaction process to estimate dynamic embeddings for tensor modes.
result Captures both commonalities and personalities in evolving tensor entries.
We provide guarantees for learning latent variable models emphasizing on the overcomplete regime, where the dimensionality of the latent space can exceed the observed dimensionality. In particular, we consider multiview mixtures, spherical Gaussian mixtures, ICA, and sparse coding models. We provide tight concentration…
KTVGL models tensor time series data for interpretable dynamic network estimation.
problem Estimating time-varying dependencies in multi-mode tensor time series data.
method Kronecker Time-Varying Graphical Lasso (KTVGL) for mode-specific dynamic network estimation.
result KTVGL produces interpretable modeling results and higher edge estimation accuracy than existing methods.
This work tackles sparse coding in DLRA for interpretable multiway data.
problem Sparse coding in DLRA for interpretable multiway data.
method Proposes a new sparse-coding subproblem (MSC) and several algorithms to solve it.
result DLRA extends low-rank approximations, reducing variance and enhancing interpretability.
We give a new approach to the dictionary learning (also known as "sparse coding") problem of recovering an unknown n×m matrix A (for m≥n) from examples of the form \[ y = Ax + e, \] where x is a random vector in Rm with at most τm nonzero coordinates, and e is a random noise vector in …
Enhanced Transformer solves math problems better with explicit relation encoding.
problem Improving Transformer models for solving math word problems.
method Integrates Tensor-Product Representations and TP-Attention mechanism.
result Sets new state of the art on the Mathematics Dataset.
Knowledge graphs contain knowledge about the world and provide a structured representation of this knowledge. Current knowledge graphs contain only a small subset of what is true in the world. Link prediction approaches aim at predicting new links for a knowledge graph given the existing links among the entities. Tenso…
We consider N-way data arrays and low-rank tensor factorizations where the time mode is coded as a sparse linear combination of temporal elements from an over-complete library. Our method, Shape Constrained Tensor Decomposition (SCTD) is based upon the CANDECOMP/PARAFAC (CP) decomposition which produces r-rank appr…
New tensor kernels reduce mismatch between clustering and reconstruction objectives in deep learning.
problem Objective Function Mismatch in deep clustering.
method Proposed Unsupervised Companion Objectives (UCOs) with tensor kernels to address mismatch.
result Reduced OFM between clustering and reconstruction objectives, leading to improved clustering performance.
Bayesian learning from variable-length sequences using Gaussian processes with signature covariances.
problem Learning from sequences of varying lengths and complex sequential structures.
method Gaussian processes with signature kernels, sparse variational approach, combining with LSTM/GRU models.
result Effective learning from sequences of different lengths and complex structures.
Proposes a new model for clustering passenger trajectories with graphs.
problem Hierarchical trip structure, inaccurate clustering number, and lack of spatial semantic graphs.
method Tensor Dirichlet Process Multinomial Mixture model with graphs and a tensor version of Collapsed Gibbs Sampling.
result Automatic determination of the number of clusters and better cluster quality.
MEI model improves knowledge graph completion by efficiently modeling interactions between embeddings.
problem Efficiently modeling interactions between knowledge graph embeddings to predict missing links.
method MEI divides embeddings into partitions and uses Tucker and block term formats to model interactions efficiently.
result Achieves state-of-the-art performance on link prediction tasks.
Derdzinski and Shen's theorem on the restrictions posed by a Codazzi tensor on the Riemann tensor holds more generally when a Riemann-compatible tensor exists. Several properties are shown to remain valid in this broader setting. Riemann compatibility is equivalent to the Bianchi identity of the new "Codazzi deviation …
Given a space it is easy to obtain the system of geodesic equations on it. In this paper the inverse problem of reconstructing the space from the geodesic equations is addressed. A procedure is developed for obtaining the metric tensor from the Christoffel symbols. The procedure is extended for determining if a second …
Specialized Deep Learning (DL) acceleration stacks, designed for a specific set of frameworks, model architectures, operators, and data types, offer the allure of high performance while sacrificing flexibility. Changes in algorithms, models, operators, or numerical systems threaten the viability of specialized hardware…
The paper defines minimal norm tensors for curvature and divergence tensors, explaining Weyl and Cotten tensors.
problem Understanding curvature tensors and their minimal norm.
method Analyzing minimal norm tensors for third and fourth covariant tensors, including Riemannian curvature and divergence.
result Weyl tensor and Cotten tensor are identified as minimal norm tensors of Riemannian curvature and divergence tensors, respectively.
The paper proves compactness theorems for specific types of tensors.
problem Proving compactness theorems for Riemannian manifolds with specific tensors.
method Using h-almost Ricci tensors and generalized quasi-Einstein tensors, the paper extends previous theorems. result Theorems are extended to cases where h has at most linear growth. Paper studies second order symmetric parallel tensors in generalized f.pk-space forms.
problem Exploring properties of second order symmetric parallel tensors in generalized f.pk-space forms.
method Analyzes the properties of second order symmetric parallel tensors and deduces the existence or non-existence of certain tensors and hypersurfaces.
result There does not exist second order skew-symmetric parallel tensor in f.pk-space form. There is no parallel hypersurface in a generalized f.pk-space form but there is semi-parallel hypersurface.
A new method learns dynamic graph representations from time-varying data.
problem Learning dynamic graph representations from time-varying data.
method Higher-order skip-gram with negative sampling (HOSGNS) for tensor factorization.
result HOSGNS outperforms state-of-the-art methods in downstream tasks.
SLM models code syntax as trees to generate any programming language code.
problem Generating any piece of code in a given language without restrictions.
method Structural language modeling (SLM) decomposes code into ASTs and estimates probabilities over nodes.
result SLM model generates arbitrary code in any language, outperforming previous methods.