Study proposes efficient estimators for matrix-valued linear regression under sparsity assumptions.
problem Estimation of parameters in matrix-valued linear regression models.
method Explicit optimization-free estimators for matrix-valued linear regression models with sparsity assumptions.
result Established non-asymptotic convergence rates for the proposed estimators.
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.
We propose a novel linear discriminant analysis approach for the classification of high-dimensional matrix-valued data that commonly arises from imaging studies. Motivated by the equivalence of the conventional linear discriminant analysis and the ordinary least squares, we consider an efficient nuclear norm penalized …
We propose a general matrix-valued multiple kernel learning framework for high-dimensional nonlinear multivariate regression problems. This framework allows a broad class of mixed norm regularizers, including those that induce sparsity, to be imposed on a dictionary of vector-valued Reproducing Kernel Hilbert Spaces. W…
We propose a general matrix-valued multiple kernel learning framework for high-dimensional nonlinear multivariate regression problems. This framework allows a broad class of mixed norm regularizers, including those that induce sparsity, to be imposed on a dictionary of vector-valued Reproducing Kernel Hilbert Spaces. W…
Paper improves matrix-valued data classification using nonparametric LDA.
problem Classification of matrix-valued data in neuroimaging and signal processing.
method Nonparametric LDA based on NPMLE for vectorized and scaled matrices.
result Improves classification performance across various data structures.
We extend Kyle's model to include stochastic liquidity and multiple assets.
problem Modeling informed trading with stochastic liquidity and multiple assets.
method Developed a variational formulation and derived a matrix-valued martingale depth process.
result A linear-Gaussian equilibrium with stochastic matrix-valued price impact.
Online graph learning from matrix-valued time series data.
problem Identifying dependency structure among sensors in a network.
method Extends VAR models to matrix-variate models, proposes online procedures for graph learning, and introduces Lasso-type approaches.
result Demonstrates effectiveness of online graph learning methods in both synthetic and real data.
Algorithm predicts performance of learning in multi-layer networks with matrix-valued hidden variables.
problem Signal recovery and learning in multi-layer neural networks with matrix-valued hidden variables.
method Unified approximation algorithm for MAP and MMSE inference, extending ML-VAMP to handle matrix-valued unknowns.
result Performance of ML-Mat-VAMP algorithm can be predicted in a random large-system limit.
Traditional linear methods for forecasting multivariate time series are not able to satisfactorily model the non-linear dependencies that may exist in non-Gaussian series. We build on the theory of learning vector-valued functions in the reproducing kernel Hilbert space and develop a method for learning prediction func…
Classifies contravariant matrix-valued valuations on polytopes without continuity assumptions.
problem Classifying contravariant matrix-valued valuations on polytopes without continuity assumptions.
method Complete classification of contravariant matrix-valued valuations on polytopes in Rn without continuity assumptions. result The only such valuation is the general Lutwak-Yang-Zhang matrix in dimension n≥4, and a new function in dimension 3. Transfer knowledge from multiple sources to improve matrix completion.
problem Matrix completion with noisy data.
method Aggregating singular subspaces information from multiple sources to solve a two-way PCA problem and transform into a low-dimensional linear regression.
result Guaranteed statistical efficiency in transforming the high-dimensional target matrix completion problem.
The paper extends log-Sobolev inequalities to matrix-valued settings using combinatorial methods.
problem Log-Sobolev inequalities for matrix-valued settings.
method Combining noncommutative geometry tools and combinatorial methods.
result Combinatorial methods yield computable lower bounds for matrix-valued log-Sobolev inequalities.
Classifies SL(n) covariant matrix-valued valuations on Lp-spaces.
problem Classifying SL(n) covariant matrix-valued valuations on Lp-spaces.
method Established a complete classification for continuous and SL(n) covariant matrix-valued valuations on Lp(Rn,|x|2dx), eliminating matrix symmetry assumption.
result Unique characterization of such valuations by the moment matrix in n>2, rotation matrix in 2D.
New algorithm estimates matrix-valued regression parameters efficiently.
problem High-dimensional matrix regression with limited sample size.
method KRO-PRO-FAC algorithm using Kronecker product factorization.
result Algorithm provides accurate parameter estimates without covariance estimation.
Long term optimal investment problems are studied in a factor model with matrix valued state variables. Explicit parameter restrictions are obtained under which, for an isoelastic investor, the finite horizon value function and optimal strategy converge to their long-run counterparts as the investment horizon approache…
Study finds weak solutions for complex map flows with optimal lifespan.
problem Existence of weak solutions for two-phase matrix-valued harmonic map flows.
method Modified minimizing movement scheme, discretizing time and interpolating solutions.
result Existence of weak solutions with optimal lifespan for the limiting system.
Holomorphic functions from knot complements link to quantum modular forms.
problem Analyzing holomorphic functions from knot complements.
method Matrix-valued holomorphic functions, cocycles, and quantum modularity.
result Identifies a matrix-valued holomorphic quantum modular form.
We propose a penalized likelihood method to fit the linear discriminant analysis model when the predictor is matrix valued. We simultaneously estimate the means and the precision matrix, which we assume has a Kronecker product decomposition. Our penalties encourage pairs of response category mean matrices to have equal…
Researchers developed a new Riemannian manifold for SPD matrix-valued optimal transport problems.
problem Optimal transport between SPD matrix-valued measures.
method Formulated as a generalized optimal transport problem with block SPD matrices, endowed with a novel Riemannian manifold structure.
result The novel Riemannian manifold allows solving SPD matrix-valued optimal transport problems using Riemannian optimization.
Recovering matrix valued potentials from wave equation data on stationary spacetimes.
problem Recovering a time-dependent matrix valued potential from wave equation data.
method Reduction to non-Abelian light ray transform and study of the transform.
result Sufficient conditions for solving the inverse problem on stationary spacetimes.
We consider the task of low-multilinear-rank functional regression, i.e., learning a low-rank parametric representation of functions from scattered real-valued data. Our first contribution is the development and analysis of an efficient gradient computation that enables gradient-based optimization procedures, including…
Differential privacy mechanism design has traditionally been tailored for a scalar-valued query function. Although many mechanisms such as the Laplace and Gaussian mechanisms can be extended to a matrix-valued query function by adding i.i.d. noise to each element of the matrix, this method is often suboptimal as it for…
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.
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.
New method uses nuclear and ℓ1 penalties for matrix regression, improving brain disorder detection.
problem Modeling high-dimensional matrix predictors with binary responses.
method Convex optimization with ADMM for low-rank and sparse structures.
result Effective in identifying brain disorder-related connectivity patterns.
Model liquidity premia using a risk-sharing economy with quadratic costs.
problem Understanding the cross-section of liquidity premia earned by assets with different trading costs.
method Developed a risk-sharing economy model with quadratic transaction costs, leading to matrix-valued Riccati equations for equilibrium.
result Calibrated model to time series data, revealing liquidity premia across assets with varying trading costs.
Statistical analysis of regularization in continual learning tasks.
problem Understanding how regularization affects model performance in sequential learning.
method Derivation of convergence rates, iterative update formula, and optimal hyperparameters for generalized ℓ2-regularization.
result Optimal hyperparameters balance forward and backward knowledge transfer, improving model performance.
New algorithms compute Volterra signature efficiently for time series analysis.
problem Efficient computation of Volterra signature with matrix-valued kernels.
method Decomposed Chen-type convolution relation, introduced FFT-based and exact recursion algorithms.
result Efficient algorithms for Volterra signature computation with various complexities.
Introduces HTV to measure function complexity in learning schemes.
problem Assessing the complexity of supervised-learning schemes.
method Defines Hessian-Schatten total variation (HTV) as a seminorm to quantify function complexity.
result HTV is invariant to rotations, scalings, and translations, and its minimum value is achieved for linear mappings.
Paper develops a new test for high-dimensional matrix-valued data.
problem Hypothesis testing for mean of matrix-valued data in high-dimensional settings.
method Proposes a new test statistic for high-dimensional matrix rank testing.
result Develops a novel approach for sparse singular value decomposition (SVD) estimation.
We give a complete classification of conformally covariant differential operators between the spaces of i-forms on the sphere Sn and j-forms on the totally geodesic hypersphere Sn−1. Moreover, we find explicit formulæ for these new matrix-valued operators in the flat coordinates in terms of basic operators …
This paper proposes robust matrix variate regression models with rank constraints and vector regularization.
problem High dimensional and noisy matrix-valued predictors in regression models.
method Rank constraint, vector regularization, alternating projected gradient descent algorithm.
result The proposed method achieves the minimax rate of estimation errors.
New bounds show current methods overestimate system parameter errors.
problem Current bounds overestimate parameter errors in system identification.
method Utilized asymptotic normality and second-order decomposition.
result Obtained finite-sample bounds matching optimal rates up to constants.
Let A:[0,1]→Hm (the space of Hermitian matrices) be a matrix valued function which is low rank with entries in Hölder class Σ(β,L). The goal of this paper is to study statistical estimation of A based on the regression model E(Yj∣τj,Xj)=⟨A(τj),Xj⟩, where τj …
Symplectic GP regression models Hamiltonian systems for particle tracing.
problem Efficiently modeling long-term Hamiltonian flow maps for charged particles.
method Multi-output Gaussian process regression with symplectic matrix-valued covariance function.
result Symplectic methods outperform existing approaches in learning Hamiltonian functions.
We consider a model for linear transient price impact for multiple assets that takes cross-asset impact into account. Our main goal is to single out properties that need to be imposed on the decay kernel so that the model admits well-behaved optimal trade execution strategies. We first show that the existence of such s…
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…
New method clusters matrix-valued data by latent variables.
problem Clustering matrix-valued data with hidden structure.
method Latent variable model with hierarchical clustering.
result Algorithm attains clustering consistency in high dimensions.
Stein variational gradient descent (SVGD) is a particle-based inference algorithm that leverages gradient information for efficient approximate inference. In this work, we enhance SVGD by leveraging preconditioning matrices, such as the Hessian and Fisher information matrix, to incorporate geometric information into SV…
LoRA and privacy: Random projections help but not always.
problem Ensuring differential privacy in LoRA fine-tuning.
method Wishart projection mechanism and noisy variants.
result LoRA is not inherently private, but low-rank fine-tuning can be more private.
MuonEq improves training of matrix-valued parameters by rebalancing momentum before orthogonalization.
problem Training matrix-valued parameters with orthogonalized-update optimizers like Muon.
method MuonEq introduces three lightweight pre-orthogonalization equilibration schemes: two-sided row/column normalization (RC), row normalization (R), and column normalization (C).
result Row/column normalization acts as a zeroth-order surrogate for whitening and improves the geometry seen by orthogonalization.
Researchers compute Wodzicki residue for pseudo-differential operators on compact Lie groups.
problem Computing the Wodzicki residue for pseudo-differential operators on compact Lie groups.
method Analytic continuation of traces and matrix-valued symbols.
result Main theorem complementary to [2], removing ellipticity hypothesis.
New analysis of Muon and SignSGD on matrix-valued least squares problems.
problem Understanding the behavior of Muon and SignSGD on matrix-valued least squares problems.
method Derive explicit deterministic dynamics to study learning behavior of Muon and SignSGD.
result Muon and SignSGD exhibit different optimal learning rates and convergence characteristics based on batch size and data covariance.
We investigate solutions of the elliptic sinh-Gordon equation of spectral genus g<3. These solutions are parametrized by complex matrix-valued polynomials called potentials. On the space of these potentials there act two commuting flows. The orbits of these flows are called Polynomial Killing fields and are double peri…
A new algorithm improves sampling for graph learning models.
problem Euclidean proposals struggle near the boundary of PSD matrices.
method ConeMALA, a geometry-aware Langevin algorithm.
result ConeMALA achieves higher ESS/sec and stable diagnostics.
Paper introduces a new kernel model for PSD-valued functions with theoretical guarantees and applications.
problem Enforcing positive semi-definiteness (PSD) in function models with good performance and theoretical guarantees.
method Kernel sum-of-squares model for PSD-valued functions, extending previous models for non-negative scalar functions.
result The model constitutes a universal approximator of PSD functions and can represent any smooth and strongly convex function.
Improved hypothesis testing and change-point detection using diffusion-based methods.
problem Limited power of score-based hypothesis tests and change-point detection.
method Extending score-based Fisher divergence to diffusion-divergence by multiplying score functions with a matrix-valued function or weight matrix.
result Theoretical quantification and demonstration of optimal performance of diffusion-based algorithms.