Efficiently decomposes large tensors using stochastic gradients.
problem Efficiently decomposing large tensors for multiway data analysis.
method Stochastic gradients computed via MTTKRP kernel for efficient computation.
result Advantages and scalability demonstrated for large-scale problems.
The paper shows how gradient flow on over-parametrized tensor decomposition behaves like deflation.
problem Understanding the training dynamics of gradient flow on tensor decomposition.
method Empirical observation and mathematical proof of gradient flow dynamics for orthogonally decomposable tensors.
result Gradient flow dynamics for orthogonally decomposable tensors follows a tensor deflation process, recovering all tensor components.
Gradient adversarial training improves robustness and multi-task learning.
problem Improving neural network robustness and multi-task learning.
method Leverage auxiliary network to classify gradient tensors and enforce consistency with the main network.
result Gradient adversarial training enhances robustness to adversarial attacks and improves knowledge distillation.
This paper classifies solitons under specific tensor conditions.
problem Classifying solitons under vanishing conditions on the Weyl, Cotton, and Cao-Chen tensors.
method Analyzing complete conformal gradient solitons and using tensor conditions.
result Classification of complete nontrivial locally conformally flat conformal gradient solitons.
Study on gradient ρ-Einstein solitons with radially nonnegative Bach tensor.
problem Characterizing gradient ρ-Einstein solitons with specific tensor properties.
method Analyzing the properties of Bach tensor and using local warping to classify solitons.
result Gradient ρ-Einstein solitons with radially nonnegative Bach tensor are locally warped products of an interval and an Einstein manifold.
New proof shows gradient Ricci solitons with harmonic Weyl tensor have at most three eigenvalues.
problem Classifying gradient Ricci solitons with harmonic Weyl tensor.
method Shorter proof without moving frame, focusing on eigenvalues.
result Ricci tensor has at most three distinct eigenvalues.
Gradient descent in tensor factorization favors low-rank solutions.
problem Tackling implicit regularization in tensor factorization problems.
method Gradient descent with small random initialization for overparametrized tensor factorization.
result Gradient descent leads to implicit regularization towards low tubal rank solutions.
In this paper, we will give a local version of the Hamilton-Ivey type pinching estimate of the gradient shrinking soliton with vanishing Weyl tensor, and then give a complete classification on gradient shrinking solitons with vanishing Weyl tensor.
Paper tackles anomaly detection in e-commerce using Bayesian semi-supervised tensor decomposition.
problem Detecting anomalies in seller-reviewer data in e-commerce.
method Bayesian semi-supervised tensor decomposition with Polya-Gamma data augmentation and partial natural gradient learning.
result Semi-supervised approach outperforms state-of-the-art unsupervised baselines.
New classification of gradient steady Ricci solitons with vanishing D-tensor.
problem Classifying gradient steady Ricci solitons with specific properties.
method Extending Cao-Chen's work on Bach-flat gradient Ricci solitons, proving properties for D-flat solitons. result Any n-dimensional complete noncompact gradient steady Ricci soliton with vanishing D-tensor is either Ricci-flat or isometric to the Bryant soliton. The paper classifies specific types of 3D solitons with unique properties.
problem Classifying 3D complete gradient Yamabe solitons with specific tensors.
method Analyzing properties of solitons with divergence-free Cotton tensor and nonpositive Ricci curvature.
result Classification of 3D complete gradient Yamabe solitons with divergence-free Cotton tensor.
VecHGrad solves complex tensor decomposition problems more accurately and efficiently.
problem Complex tensor decomposition with multiple matrices and diagonal tensors.
method VecHGrad algorithm using gradient, Hessian-vector product, and adaptive line search.
result VecHGrad converges faster and more accurately than existing methods.
RTC-GTNLN model recovers traffic data from missing values and noise.
problem Simultaneous missing data and noise in traffic data.
method Gradient tensor nuclear L1-L2 norm for robust tensor completion.
result RTC-GTNLN model outperforms existing methods in complex recovery scenarios.
ScaledGD algorithm estimates low-rank tensors efficiently from corrupted data.
problem Estimating meaningful information from corrupted tensor data.
method Scaled gradient descent (ScaledGD) algorithm with tailored spectral initializations.
result ScaledGD achieves linear convergence at a constant rate independent of condition number.
Study shows Sasaki solitons with harmonic Weyl tensor are spheres.
problem Characterizing gradient shrinking Sasaki-Ricci solitons.
method Integral curvature estimates and quotient analysis.
result Gradient shrinking Sasaki-Ricci solitons with harmonic Weyl tensor are finite quotients of spheres.
Gradient flows for surface energies with tensor fields are derived and analyzed.
problem Deriving consistent gradient flows for surface energies involving tensor fields.
method Introducing different gauges of surface independence and demonstrating their effects on energy decrease.
result Consistent choice of gauge and time derivative is necessary for energy decrease.
Study classifies gradient almost Ricci solitons with harmonic Weyl tensor.
problem Characterizing the local structure of gradient almost Ricci solitons with harmonic Weyl tensor.
method Local representation as multiply warped products, analysis of eigenvalues, and classification based on Weyl tensor properties.
result Classification of gradient almost Ricci solitons with harmonic Weyl tensor, extending previous results.
This paper derives new identities for the Weyl tensor on a gradient Ricci soliton, particularly in dimension four. First, we prove a Bochner-Weitzenböck type formula for the norm of the self-dual Weyl tensor and discuss its applications, including connections between geometry and topology. In the second part, we are co…
Gradient descent can find better tensor decompositions than lazy training in over-parameterized settings.
problem Finding better tensor decompositions in over-parameterized settings.
method Gradient descent on over-parameterized tensor decomposition problems.
result Gradient descent can find an approximate tensor decomposition with rank m=O∗(r2.5llogd), while lazy training requires m=Ω(dl−1). The paper extends results on Bach-flat solitons to new types.
problem Analyzing Bach-like tensors on complete gradient Ricci solitons.
method Extending previous results to new types of solitons.
result Results on Bach-flat solitons extended to new types.
Gradient descent promotes low-rank solutions in tensor completion.
problem Implicit regularization in tensor factorization using gradient descent.
method Introduced deep Tucker and TensorTrain (TT) unconstrained factorization to address tensor completion.
result Gradient descent promotes solutions with low-rank.
New tensor formulation reveals gradient flow's bias in linear neural networks.
problem Understanding implicit bias in linear neural network training.
method Tensor formulation of neural networks, including fully-connected, diagonal, and convolutional networks.
result Gradient flow on linear tensor networks converges to solutions of specific optimization problems.
New findings on shrinking Ricci solitons with vanishing Bach-like tensors.
problem Characterizing gradient shrinking Ricci solitons with vanishing Bach-like tensors.
method Defining and analyzing Bach-like tensors, proving rigidity results, and deriving variational formulas.
result Vanishing Bach-like tensors force solitons to be either Einstein or isometric to the Gaussian soliton.
In this paper, we prove that complete gradient steady Kähler-Ricci solitons with harmonic Bochner tensor are necessarily Kähler-Ricci flat, i.e., Calabi-Yau, and that complete gradient shrinking (or expanding) Kähler-Ricci solitons with harmonic Bochner tensor must be isometric to a quotient of $N^k\times \mathbb{C}^{n…
The study examines perfect fluid spacetimes and their properties.
problem Characterizing properties of perfect fluid spacetimes with concircular vector fields.
method Analyzing the conformal curvature tensor, state equation, and solitons in perfect fluid spacetimes.
result Perfect fluid spacetimes with concircular vector fields have specific properties related to the state equation and solitons.
This paper solves tensor robust principal component analysis via scaled gradient descent.
problem Extracting useful information from tensor data robust to corruptions and ill-conditioning.
method Directly recovers low-rank tensor factors via scaled gradient descent with adaptive thresholding.
result The proposed algorithm converges linearly to the true low-rank tensor at a constant rate independent of the condition number.
We show that the only complete shrinking gradient Ricci solitons with vanishing Weyl tensor are quotients of the standard ones. This gives a new proof of the Hamilton-Ivey-Perel'man classification of 3-dimensional shrinking gradient solitons. We also prove a classification for expanding gradient Ricci solitons with con…
Paper classifies Einstein-type manifolds with parallel Ricci tensor.
problem Classifying Einstein-type manifolds with specific curvature properties.
method Deduced Bochner-type identity and used it to show rigidity results.
result Found conditions for classifying Einstein-type manifolds with parallel Ricci tensor.
In this paper we prove that any complete conformal gradient soliton with nonnegative Ricci tensor is either isometric to a direct product R×Nn−1, or globally conformally equivalent to the Euclidean space Rn or to the round sphere Sn. In particular, we show that any comple…
TSGO optimizes gradients in tensor networks to avoid vanishing/exploding issues.
problem Gradient vanishing and exploding problems in deep learning models.
method TSGO rotates parameters towards gradient direction in tangent space of normalized state.
result TSGO naturally determines learning rate based on angle between parameters and gradient.
We classify complete gradient Ricci solitons satisfying a fourth-order vanishing condition on the Weyl tensor, improving previously known results. More precisely, we show that any n-dimensional (n≥4) gradient shrinking Ricci soliton with fourth order divergence-free Weyl tensor is either Einstein, or a finite q…
We prove that a gradient shrinking Ricci soliton with fourth order divergence-free Riemannian tensor is rigid. For the 4-dimensional case, we show that any gradient shrinking Ricci soliton with fourth order divergence-free Riemannian tensor is either Einstein, or a finite quotient of the Gaussian shrinking soliton $\…
Quantum Natural Gradient uses quantum geometry for optimization.
problem Optimizing variational quantum circuits efficiently.
method Quantum generalization of Natural Gradient Descent using Quantum Information Geometry.
result Efficient algorithm for computing metric tensor approximations.
NNEinFact fits any nonnegative tensor factorization quickly and accurately.
problem Limited user-friendly tools for fitting tailored nonnegative tensor factorizations.
method NNEinFact is an einsum-based multiplicative update algorithm that fits any nonnegative tensor factorization.
result NNEinFact converges to a stationary point of the loss, supports missing data, and fits tensors with hundreds of millions of entries in seconds.
New tensor recovery method improves efficiency under strict complementarity.
problem Efficiently recovering low-rank tensors using tensor nuclear norm.
method Developed strict complementarity condition for tensor nuclear norm ball and applied to gradient methods.
result Standard gradient methods achieve linear convergence and nearly linear runtime under strict complementarity.
Gradient flow on diffeomorphisms for image registration, with well-posedness proven.
problem Image registration with metric tensor deformation penalization.
method Gradient flow on Sobolev diffeomorphisms for a specific energy functional.
result Well-posedness of the gradient flow established.
We analyze stochastic gradient descent for optimizing non-convex functions. In many cases for non-convex functions the goal is to find a reasonable local minimum, and the main concern is that gradient updates are trapped in saddle points. In this paper we identify strict saddle property for non-convex problem that allo…
We present a new method for online prediction and learning of tensors (N-way arrays, N>2) from sequential measurements. We focus on the specific case of 3-D tensors and exploit a recently developed framework of structured tensor decompositions proposed in [1]. In this framework it is possible to treat 3-D tensors …
Efficiently recovers low-tubal-rank tensors from few measurements.
problem Recovering tensors with low tubal-rank from limited measurements.
method Factorization and factorized gradient descent.
result Factorized gradient descent reduces computational costs and storage requirements.
We describe the structure of the Ricci tensor on a locally homogeneous Lorentzian gradient Ricci soliton. In the non-steady case, we show the soliton is rigid in dimensions three and four. In the steady case, we give a complete classification in dimension three.
NeCPD improves online tensor decomposition using SGD with Hessian analysis and NAG.
problem Efficiently decompose multi-way tensors in online data processing.
method NeCPD solver based on SGD with Hessian analysis and NAG.
result NeCPD provides more accurate results than existing methods.
Averaged Gradient Descent improves performance in rough landscapes.
problem Minimizing strongly non-convex functions in high-dimensional estimation problems.
method Empirical average of gradients over random positions in parameter space.
result Averaged Gradient Descent outperforms existing methods in tensor PCA.
Gradient optimization improves functional tensor-train regression performance.
problem Low-rank functional regression from scattered data.
method Gradient-based optimization of functional tensor-train parameters.
result Gradient methods outperform standard ALS in low-sample number scenarios.
Paper proposes an optimal framework for tensor estimation across various applications.
problem Generalized tensor estimation problems in computational imaging, genomics, and network analysis.
method Unified projected gradient descent approach to find low-rank tensor fits under generalized parametric models.
result Achieves minimax optimal rate of convergence in estimation error for various tensor estimation problems.
The paper analyzes implicit regularization in tensor factorization using neural networks.
problem Understanding implicit regularization in tensor factorization.
method Dynamical systems perspective and gradient descent analysis.
result Gradient descent induces a form of greedy low tensor rank search.
Study rigidifies geometry of electrostatic systems with specific tensor properties.
problem Investigating rigidity in electrostatic systems with specific tensor properties.
method Analyzing static Einstein--Maxwell spacetimes with harmonic (anti-)self-dual Weyl tensor.
result Gradient of lapse function is an eigenvector of Ricci tensor and manifold is locally conformally flat.
Efficiently factorizes coupled matrix tensor data for better accuracy and speed.
problem Poor computation efficiency in existing N-CMTF algorithms.
method Column-wise element selection to prevent frequent gradient updates.
result More accurate and computationally efficient factorization.
Guaranteed convergence for tensor factorization using Riemannian gradient descent.
problem Recovering tensor train format from linear measurements.
method Optimization over left-orthogonal TT format using Riemannian gradient descent on Stiefel manifold.
result RGD converges linearly to the ground-truth tensor with polynomial error growth in tensor order.