Introduces a new model for mapping matrices to matrices, subsuming linear regression.
problem Learning matrix-to-matrix mappings from data.
method Partial trace regression model, leveraging quantum information theory.
result Relevance demonstrated in matrix-to-matrix regression and positive semidefinite matrix completion.
New method estimates matrix trace using machine learning with fewer vectors.
problem Estimating matrix trace when explicit form is not known.
method Uses machine learning to determine a small number of probing vectors for matrix multiplication to a vector.
result Precision of trace estimates with 10 probing vectors is similar to 10000 random vectors.
Develops a new nonparametric trace regression model for high-dimensional data.
problem Violation of known functional form and global low-rank structure assumptions in trace regression.
method Structured sign series representations for nonparametric trace regression models.
result Establishes excess risk bounds and sample complexities for the proposed model.
We present a formula for the trace of any symmetric power of a n×n matrix (with coefficients in a field) in terms of the ordinary powers of the matrix, an arbitrarily chosen linear function which vanishes on the identity matrix, and n−2 polynomial functions defined recursively.
We introduce a new family of matrix norms, the "local max" norms, generalizing existing methods such as the max norm, the trace norm (nuclear norm), and the weighted or smoothed weighted trace norms, which have been extensively used in the literature as regularizers for matrix reconstruction problems. We show that this…
Link invariants explained using HOMFLYPT polynomials and Yokonuma-Hecke algebras.
problem Link invariants constructed using Markov traces on Yokonuma-Hecke algebras.
method Description of link invariants in terms of HOMFLYPT polynomials and linking matrix.
result Link invariants explained completely using HOMFLYPT polynomials and Yokonuma-Hecke algebras.
A new method for optimizing deep neural networks using TKFAC.
problem Optimizing deep neural networks with second-order methods.
method Proposes Trace-restricted Kronecker-factored Approximate Curvature (TKFAC) for Fisher information matrix approximation.
result TKFAC improves performance on deep network architectures compared to state-of-the-art algorithms.
We consider the problem of approximately reconstructing a partially-observed, approximately low-rank matrix. This problem has received much attention lately, mostly using the trace-norm as a surrogate to the rank. Here we study low-rank matrix reconstruction using both the trace-norm, as well as the less-studied max-no…
Derives a sharp inequality for trace-free matrices with applications to hypersurfaces.
problem Classifying conformally flat hypersurfaces and characterizing rotational hypersurfaces.
method Derives a sharp inequality relating eigenvalues of trace-free matrices and applies it to hypersurfaces.
result New proof of the classification of conformally flat hypersurfaces and construction of a functional for rotational hypersurfaces.
Paper tackles clipped matrix recovery from scientific areas with theoretical and practical methods.
problem Recovering low-rank matrices from clipped observations in scientific areas.
method Trace-norm minimization algorithm and squared hinge loss with a novel regularization term.
result Theoretical guarantee and practical algorithms for exact recovery of clipped matrix completion.
Develops interpolation methods for matrix functions in statistics and machine learning.
problem Estimating matrix functions in statistics and machine learning.
method Interpolates log-determinant and trace of matrix powers using modified sharp bounds.
result Accuracy and performance demonstrated in numerical examples.
Estimates matrix trace optimization with statistical learning theory.
problem Optimizing trace of parameter-dependent matrices.
method Monte Carlo estimator with bounds derived from epsilon nets and generic chaining.
result Predicts small sampling amount for matrices with small off-diagonal mass.
We propose a novel hierarchical model for multitask bipartite ranking. The proposed approach combines a matrix-variate Gaussian process with a generative model for task-wise bipartite ranking. In addition, we employ a novel trace constrained variational inference approach to impose low rank structure on the posterior m…
Paper analyzes and improves non-convex optimization for low rank matrix factorization.
problem Non-convex optimization of trace norm regularization for low rank matrices.
method Characterizes all critical points, provides efficient criterion for global minimizers, and offers an iterative meta-algorithm.
result Algorithm converges to global minimizers, improving upon standard optimization methods.
Proposes a new method for hyperspectral image dimensionality reduction.
problem Highly correlated noisy hyperspectral images.
method Trace Lasso-L1 Graph Cut method using L1-norm for robustness and sparsity.
result Optimal projection matrix maximizing between-class dispersion to within-class dispersion.
GL-LowPopArt improves minimax-optimal estimation for trace regression.
problem Minimizing estimation error in generalized low-rank trace regression.
method Two-stage approach: nuclear norm regularization followed by matrix Catoni estimation.
result Achieves instance-wise optimal error bounds up to condition number.
Paper develops DP methods for low-rank matrix estimation with near-optimal performance.
problem Estimating a low-rank matrix under differential privacy constraints.
method Introduced computationally efficient DP-initialization and Riemannian optimization-based DP-RGrad algorithm.
result DP-RGrad achieves near-optimal convergence rate under weak differential privacy constraints.
Study elliptic isometries on a matrix manifold with specific metrics.
problem Differential-geometric properties of fixed point loci.
method Explicit description and De Rham decomposition of fixed point loci.
result Explicit description and De Rham decomposition of fixed point loci.
This paper develops source traces for faster TD learning.
problem Improving temporal difference learning speed and generalization.
method Introduces source traces as a backward view of successor representations, enabling TD errors to be propagated to potential causal states.
result Demonstrates faster generalization and improved performance of source traces compared to previous methods.
Stochastic trace estimation with tensor train random vectors
problem Stochastic trace estimation for large-scale matrices
method Gaussian random tensor train vectors
result Median-of-means variant achieves dimension-independent guarantees
Early training phase affects deep neural network optimization and generalization.
problem The choice of learning rate influences generalization in deep learning models.
method Showed that SGD implicitly penalizes the trace of the Fisher Information Matrix (FIM) from the start of training, and explicitly penalizing the trace of FIM improves generalization.
result Catastrophic Fisher explosion (large trace of FIM early in training) is linked to poor generalization.
Spectral regularization simplifies sequence models by focusing on grammatical simplicity.
problem Sequence modeling challenges in learning tasks.
method Introduces spectral regularization based on Hankel matrices and trace norm, addressing bi-infinite matrices with an unbiased estimator.
result Demonstrates spectral regularization's potential benefits on Tomita grammars.
Proposes GTTN for discovering all low-rank structures in deep multi-task learning.
problem Discovering all low-rank structures among tasks in deep multi-task models.
method Introduces GTTN, a convex combination of matrix trace norms of all tensor flattenings, to automatically determine the importance of components.
result Demonstrates the effectiveness of GTTN on real-world datasets.
We classify isotopy classes of irreducible Heegaard splittings of solvmanifolds. If the monodromy of the solvmanifold can be expressed as a 2 x 2 matrix with 0 in the lower right hand corner (as always is true when the absolute value of the trace is 3), then any irreducible splitting is strongly irreducible and of genu…
Matrix completion has been well studied under the uniform sampling model and the trace-norm regularized methods perform well both theoretically and numerically in such a setting. However, the uniform sampling model is unrealistic for a range of applications and the standard trace-norm relaxation can behave very poorly …
Over the past few years, trace regression models have received considerable attention in the context of matrix completion, quantum state tomography, and compressed sensing. Estimation of the underlying matrix from regularization-based approaches promoting low-rankedness, notably nuclear norm regularization, have enjoye…
A distributed algorithm for learning low-rank matrices from large datasets.
problem Learning high-dimensional low-rank matrices from distributed data with trace norm constraint.
method DFW-Trace, a distributed Frank-Wolfe algorithm using power method approximations.
result DFW-Trace achieves sublinear convergence to optimal solutions with few power iterations.
Bayesian approach estimates log-determinant with uncertainty quantification.
problem Intractable computation of log-determinant in large kernel matrices.
method Reinterpreting as Bayesian inference with prior bounds and evidence.
result Probabilistic estimates of log-determinant and uncertainty.
Using the ℓ1-norm to regularize the estimation of the parameter vector of a linear model leads to an unstable estimator when covariates are highly correlated. In this paper, we introduce a new penalty function which takes into account the correlation of the design matrix to stabilize the estimation. This norm, ca…
Convex norms improve coupled matrix and tensor completion.
problem Efficiently complete coupled matrices and tensors with shared information.
method Proposed convex norms and completion algorithm.
result Excess risk bounds show improved performance compared to uncoupled norms.
We derive exponential tail inequalities for sums of random matrices with no dependence on the explicit matrix dimensions. These are similar to the matrix versions of the Chernoff bound and Bernstein inequality except with the explicit matrix dimensions replaced by a trace quantity that can be small even when the dimens…
Global analysis of Dixmier traces and Wodzicki residues on compact Lie groups.
problem Computing Dixmier traces and Wodzicki residues on compact Lie groups.
method Global quantisation approach, using global symbols and representation theory.
result Explicit formulae for Dixmier traces and Wodzicki residues on compact Lie groups.
We prove optimal subspace embedding conjecture up to sub-polylogarithmic factors.
problem Optimal dimension and sparsity of subspace embeddings.
method Iterative decoupling technique to analyze higher-order trace moment bounds.
result Sub-polylogarithmic factors in dimension and sparsity of subspace embeddings.
The paper proposes pricing methods for multi-asset generalized variance swaps.
problem Hedging risk in financial markets with complex asset structures.
method Proposes pricing methods for two new measures of generalized variance (maximum eigen-value and trace of covariance matrix) under Markov-modulated volatilities.
result Demonstrates pricing results for three stocks, highlighting the usefulness of these swaps in commodity risk management.
We theoretically and experimentally investigate tensor-based regression and classification. Our focus is regularization with various tensor norms, including the overlapped trace norm, the latent trace norm, and the scaled latent trace norm. We first give dual optimization methods using the alternating direction method …
The paper proves new Harnack inequalities for various nonlinear heat equations on manifolds.
problem Analyzing and proving new Harnack inequalities for nonlinear heat equations.
method Proving constrained trace, matrix, and interpolated Harnack inequalities for specific nonlinear heat equations.
result Derives new differential Harnack inequalities with time-exponential correction terms.
New techniques for faster and more compact speech recognition models.
problem Efficiency and compactness in speech recognition neural networks.
method Trace norm regularization for low rank factoring and ARM optimized kernels for faster inference.
result 3x to 7x speed up in inference on ARM processors compared to gemmlowp.
Unified formula for higher traces of linear maps on finite-dimensional normed spaces.
problem Unified trace-average formula for higher traces of linear maps.
method Unified trace-average formula for the k-th higher trace of a linear operator A on a finite-dimensional normed space.
result Unified trace-average formula holds for all A if and only if the operator-valued average equals the identity.
Using geometric quantization, we represent curve operators in the TQFT of Witten-Reshetikhin-Turaev with jauge group SU_2 as Toeplitz operators with symbols corresponding to trace functions. As an application, we show that eigenvectors of these operators are concentrated near the level sets of these trace functions, an…
We generalize Hamilton's matrix Li-Yau-type Harnack estimate for the Ricci flow by considering the space of all LYH (Li-Yau-Hamilton) quadratics that arise as curvature tensors of space-time connections satisfying the Ricci flow with respect to the natural space-time degenerate metric. As a special case, we employ scal…
New GCNs solve graph embedding problems efficiently and interpretably.
problem Graph embedding for scalable and interpretable machine learning.
method Proposed two GCNs: CAFE-GCN and sphere-GCN, based on constrained optimization.
result Both GCNs yield good approximations of dominant eigenvectors and perform dimensionality reduction.
Groups of matrices with integer-like entries are studied.
problem Characterizing groups of matrices with algebraic integer entries.
method Analyzing traces and subgroups of matrices in number fields.
result Irreducible or completely reducible subgroups with algebraic integer traces are numerical.
Matrix formulas for knot invariants derived from Tait graphs.
problem Computing knot invariants for alternating links.
method Squarefree matrix extraction from Tait graph vertices.
result Explicit formulas for CWRk for k≥4. Recovering low-rank and sparse matrices from incomplete or corrupted observations is an important problem in machine learning, statistics, bioinformatics, computer vision, as well as signal and image processing. In theory, this problem can be solved by the natural convex joint/mixed relaxations (i.e., l_{1}-norm and tr…
This paper optimizes matrix-based Renyi's entropy computation for large datasets.
problem Efficiently calculating matrix-based Renyi's entropy for large-scale applications.
method Develops randomized approximations for matrix-based Renyi's entropy with arbitrary α orders.
result Achieves a significant reduction in time complexity from O(n^3) to O(n^2sm), where s, m << n.
Shampoo optimizes tensor spaces with faster convergence.
problem Optimizing models over tensor spaces with large matrices.
method Structure-aware preconditioning for stochastic tensor optimization.
result Shampoo converges faster than existing optimizers.
Unified approach for robust low rank matrix estimation with adversaries.
problem Robust low rank matrix estimation in the presence of adversaries.
method Unified approach combining Huber loss and nuclear norm penalization.
result Sharp estimation error bounds for matrix compressed sensing and completion.
New method estimates log-determinant using trace powers, avoiding classical limitations.
problem Estimating log-determinant of large matrices efficiently and accurately.
method Interpolating moment-generating function and its derivative at zero using trace powers.
result No continuous estimator using finite moments can be uniformly accurate over unbounded conditioning.