Federated learning supports exact support recovery with minimal communication.
problem Learning the exact support of sparse linear regression in federated learning.
method One-shot communication algorithm for exact support recovery without optimization.
result Polynomial sample complexity and logarithmic number of clients required.
Support vector regression (SVR) has been widely used to reduce the high computational cost of computer simulation. SVR assumes the input parameters have equal sample sizes, but unequal sample sizes are often encountered in engineering practices. To solve this issue, a new prediction approach based on SVR, namely as hig…
The paper tackles sampling from Gibbs measures with constrained support, providing a sampling guarantee.
problem Sampling from Gibbs measures with constrained support, especially in the pre-asymptotic regime.
method Analyzing the spectral gap of Langevin dynamics to provide a non-asymptotic sampling guarantee.
result The low-temperature Gibbs distribution concentrates on a neighborhood of its mode in the pre-asymptotic regime.
Regularized EM algorithm improves GMM clustering in low sample settings.
problem Numerical instability and convergence issues in EM-GMM for low sample support.
method Regularized EM algorithm that maximizes penalized GMM likelihood, ensuring positive definiteness and structured covariance matrices.
result The regularized EM algorithm leads to better performing EM for structured covariance matrix models or low sample settings.
A simple method for estimating PMF on large supports, preserving structure and suppressing noise.
problem Nonparametric estimation of multi-modal, heavy-tailed PMF on large discrete support.
method Data-dependent low-pass filtering on a line graph Laplacian.
result Smooth, multi-modal estimate of PMF that preserves coarse structure and suppresses noise.
MAGT generates data efficiently by aligning to manifold structure.
problem Efficiently generating data near a low-dimensional structure embedded in high-dimensional space.
method MAGT is a flow-like generator that learns a one-shot, manifold-aligned transport from a low-dimensional base distribution to the data space, using a fixed Gaussian smoothing level and self-normalized importance sampling.
result MAGT samples in a single forward pass, concentrates probability near the learned support, and induces an intrinsic density with respect to the manifold volume measure, enabling principled likelihood evaluation for generated samples.
In this paper, we consider asymptotic properties of the support vector machine (SVM) in high-dimension, low-sample-size (HDLSS) settings. We show that the hard-margin linear SVM holds a consistency property in which misclassification rates tend to zero as the dimension goes to infinity under certain severe conditions. …
The study examines how much data is needed for generative and vision-language models to make reliable predictions.
problem Ensuring reliable predictions with low data for models used in medical decision support.
method Analyzes uniform convergence bounds for VLM-induced classifiers under low-dimensional semantic representations.
result Finite-sample uniform convergence bounds for accuracy and calibration functionals of VLM-induced classifiers.
Improved few-shot learning with LSSVM and transductive modules.
problem Few-shot learning with limited data and samples.
method Introducing LSSVM as a base learner and transductive modules to enhance classification accuracy.
result FSLSTM achieves state-of-the-art performance on miniImageNet and CIFAR-FS benchmarks.
LMC improves sampling from complex distributions using quasi-random sequences.
problem Sampling from complex high-dimensional distributions with high accuracy.
method Using completely uniformly distributed (CUD) sequences in Langevin Monte Carlo (LMC) to generate Gaussian perturbations.
result LMC with low-discrepancy CUD sequences achieves smaller estimation error than standard LMC.
Support vector machine (SVM) is a particularly powerful and flexible supervised learning model that analyzes data for both classification and regression, whose usual algorithm complexity scales polynomially with the dimension of data space and the number of data points. To tackle the big data challenge, a quantum SVM a…
Paper examines how income support affects retirement decisions for low-income individuals.
problem Retirement decisions of low-income individuals affected by income disaster.
method Modeling consumption/savings, investment, and retirement choices with income support.
result Optimal retirement decision depends on the level of income support provided.
Proposes a method to compare noisy high-dimensional datasets with low-dimensional manifolds.
problem Comparing distributions on manifolds in noisy high-dimensional datasets.
method Linking low-rank structure to manifold geometry, developing a scale-invariant distance measure.
result Superior robustness and statistical power compared to existing methods.
New algorithms reduce computational burden for principal support vector machines.
problem High computational cost of principal support vector machines for large datasets.
method Two distributed estimation algorithms for principal support vector machines.
result Statistical efficiency is maintained with distributed algorithms.
This paper improves diffusion models for low-dimensional data.
problem Theoretical foundations of diffusion models are lacking for low-dimensional data.
method Score approximation, estimation, and distribution recovery of diffusion models on low-dimensional data.
result Sample complexity bounds for distribution estimation using diffusion models are provided.
We stabilize the Kumaraswamy distribution for efficient sampling and differentiation.
problem Numerical instabilities in the Kumaraswamy distribution's inverse CDF and log-pdf.
method Identified and resolved numerical issues, introduced a stabilized KS distribution.
result Stabilized Kumaraswamy distribution supports efficient sampling and differentiation.
We consider the problem of estimation of a low-rank matrix from a limited number of noisy rank-one projections. In particular, we propose two fast, non-convex \emph{proper} algorithms for matrix recovery and support them with rigorous theoretical analysis. We show that the proposed algorithms enjoy linear convergence a…
Introduces t-CCS for flexible tensor sampling.
problem Lack of flexibility in tensor sampling methods.
method Tensor Cross-Concentrated Sampling (t-CCS).
result Effective tensor recovery from t-CCS samples.
Study shows how diffusion models learn on low-dimensional manifolds.
problem Learning efficiency of diffusion models on manifolds.
method Analyzes denoising score matching with random feature neural networks.
result Sample complexity scales linearly with intrinsic dimension, not ambient dimension.
Real world data often exhibit low-dimensional geometric structures, and can be viewed as samples near a low-dimensional manifold. This paper studies nonparametric regression of Hölder functions on low-dimensional manifolds using deep ReLU networks. Suppose n training data are sampled from a Hölder function in $\mathc…
We present a machine learning based method for noise classification using a low-power and inexpensive IoT unit. We use Mel-frequency cepstral coefficients for audio feature extraction and supervised classification algorithms (that is, support vector machine and k-nearest neighbors) for noise classification. We evaluate…
We consider the problem of efficiently approximating and encoding high-dimensional data sampled from a probability distribution ρ in RD, that is nearly supported on a d-dimensional set M - for example supported on a d-dimensional Riemannian manifold. Geometric Multi-Resolution Analysis (GM…
Low-rank matrix completion (LRMC) problems arise in a wide variety of applications. Previous theory mainly provides conditions for completion under missing-at-random samplings. This paper studies deterministic conditions for completion. An incomplete d×N matrix is finitely rank-r completable if there are at …
When optimizing against the mean loss over a distribution of predictions in the context of a regression task, then even if there is a distribution of targets the optimal prediction distribution is always a delta function at a single value. Methods of constructing generative models need to overcome this tendency. We con…
We simplify SSL by approximating redundant structural components with low-rank factorization.
problem Improving self-supervised learning performance with limited labeled data.
method Low-rank approximation of structural redundancy, introducing ε_s to measure approximation quality.
result The proposed method enhances SSL performance, as shown by theoretical and experimental validations.
Stochastic Gradient Descent (SGD) is a popular optimization method which has been applied to many important machine learning tasks such as Support Vector Machines and Deep Neural Networks. In order to parallelize SGD, minibatch training is often employed. The standard approach is to uniformly sample a minibatch at each…
UAPCA projects uncertain data to low dimensions using GMMs.
problem Uncertain multidimensional data not well described by normal distributions.
method Model data with Gaussian mixture models, derive UAPCA projection from general formulation.
result Low-dimensional projections better represent multidimensional distributions.
We study signal recovery on graphs based on two sampling strategies: random sampling and experimentally designed sampling. We propose a new class of smooth graph signals, called approximately bandlimited, which generalizes the bandlimited class and is similar to the globally smooth class. We then propose two recovery s…
Proposes a novel classification criterion for high-dimensional data with few samples.
problem Challenges in classifying high-dimensional data with limited samples.
method Tolerance similarity criterion and No-separated Data Maximum Dispersion classifier (NPDMD).
result NPDMD outperforms state-of-the-art methods in various real-world applications.
Robust STAP with coprime arrays reduces clutter using sparse modeling.
problem Limited performance due to training samples support in practical applications.
method Two-stage approach: 1) RD virtual snapshot, 2) RD sparse measurement modeling with OMP-like recovery.
result Robust to prior knowledge errors, good clutter suppression performance.
RFSVM uses learned RF similarity for HDLSS classification.
problem High dimension, low sample size classification problems.
method Transposes RFD approach to HDLSS classification using RF similarity as SVM kernel.
result RFSVM outperforms existing methods for HDLSS problems.
Improved sample complexity for Gaussian process approximations.
problem Efficiently approximating Gaussian processes with sparse spectrum.
method Improved sample complexity analysis and auto-encoding algorithm.
result Gaussian process predictions and model evidence can be well-approximated with low sample complexity.
New diffusion models learn distributions from samples with improved error bounds.
problem Statistical guarantees for score-based diffusion models on low-dimensional data.
method Derive finite-sample error bounds for Wasserstein-p distance. result Error bounds scale as n−1/dp,q∗(μ) for diffusion models. We explain theoretically a curious empirical phenomenon: "Approximating a matrix by deterministically selecting a subset of its columns with the corresponding largest leverage scores results in a good low-rank matrix surrogate". To obtain provable guarantees, previous work requires randomized sampling of the columns wi…
Generative models learn complex data from low-dimensional manifolds.
problem Theoretical justification for generative models on manifold structures.
method Prove statistical guarantees of generative networks under Wasserstein-1 loss, considering intrinsic dimensionality.
result Generative networks converge to zero at a fast rate depending on intrinsic dimensionality, not ambient data dimension.
A new method classifies color images using quaternion algebra.
problem Classifying color images with preserved intrinsic relationships.
method LSQMM model with quaternion nuclear norm regularization and ADMM algorithm.
result LSQMM outperforms state-of-the-art methods in classification accuracy and efficiency.
New classifiers for HDLSS data classify without tuning, robustly.
problem Classification of high-dimensional data with small samples.
method Data-adaptive energy distance classifiers, free of tuning parameters.
result Perfect classification in HDLSS asymptotic regime under general conditions.
Paper explores how Rectified Flow adapts to low-dimensional data.
problem Improving sampling efficiency in low-dimensional data.
method Investigates Rectified Flow's adaptation to low-dimensional support and introduces a stochastic version.
result Shows improved sampling efficiency with O(k/ε) complexity. Indoor localization is a supporting technology for a broadening range of pervasive wireless applications. One promis- ing approach is to locate users with radio frequency fingerprints. However, its wide adoption in real-world systems is challenged by the time- and manpower-consuming site survey process, which builds a …
No GANs can learn disconnected manifolds precisely.
problem Learning disconnected manifolds is challenging due to unimodal latent distributions.
method Formalized a no free lunch theorem and derived a rejection sampling method.
result Upper bound on the precision of the targeted disconnected manifold distribution.
The Nyström methods have been popular techniques for scalable kernel based learning. They approximate explicit, low-dimensional feature mappings for kernel functions from the pairwise comparisons with the training data. However, Nyström methods are generally applied without the supervision provided by the training labe…
Low-precision training reduces computational cost and produces efficient models. Recent research in developing new low-precision training algorithms often relies on simulation to empirically evaluate the statistical effects of quantization while avoiding the substantial overhead of building specific hardware. To suppor…
We study the problem of learning latent variables in Gaussian graphical models. Existing methods for this problem assume that the precision matrix of the observed variables is the superposition of a sparse and a low-rank component. In this paper, we focus on the estimation of the low-rank component, which encodes the e…
Deep neural networks can estimate Q-values efficiently on low-dimensional state-action spaces.
problem Estimating the performance of a reinforcement learning policy using data from a different policy.
method Deep fitted Q-evaluation method leveraging manifold structure and convolutional neural networks.
result Sharp error bound for fitted Q-evaluation depends on intrinsic dimension and function space mismatch.
This paper studies binary classification problem associated with a family of loss functions called large-margin unified machines (LUM), which offers a natural bridge between distribution-based likelihood approaches and margin-based approaches. It also can overcome the so-called data piling issue of support vector machi…
Compressing data helps learn Mahalanobis metrics effectively.
problem Learning Mahalanobis metrics in high-dimensional spaces.
method Randomly compress data to train a full-rank metric in a reduced feature space.
result Theoretical guarantees on error for Mahalanobis metric learning, independent of ambient dimension.
We study the problem of recovering the structure underlying large Gaussian graphical models or, more generally, partial correlation graphs. In high-dimensional problems it is often too costly to store the entire sample covariance matrix. We propose a new input model in which one can query single entries of the covarian…
The paper proposes a novel tensor-based method for non-parametric density estimation.
problem Effective non-parametric density estimation in high-dimensional multivariate data.
method Tensor factorization and low-rank model of characteristic tensor for improved density estimation.
result The method significantly improves density estimation especially for high-dimensional data and/or sample-starved regimes.