Model complexity is an important factor to consider when selecting among graphical models. When all variables are observed, the complexity of a model can be measured by its standard dimension, i.e. the number of independent parameters. When hidden variables are present, however, standard dimension might no longer be ap…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,657 papers · 148 categories
Trend · papers per month
48 results for “model dimension”
Study on CR structures in 7D, proving maximal symmetry dimension.
problem Proving symmetry dimension bound for CR structures in 7D.
method Investigating homogeneous models and proving uniqueness.
result 8 is the maximal symmetry dimension of 3-nondegenerate CR structures in 7D.
Minimal dimension equivariant embeddings of real and complex flag manifolds into Euclidean spacesmath.DG
Minimal dimensions found for flag manifolds embeddings.
problem Finding the smallest dimensions for flag manifolds embeddings.
method Equivariant embeddings of orthogonal and unitary groups acting on real and complex flag manifolds.
result Minimal dimensions achieved at isospectral models.
Investigates CR structures in 7D, showing 8 is max symmetry dimension.
problem CR structures in 7D with intransitive symmetry.
method Various methods to bound symmetry dimension, demonstrating existence of non-equivalent models.
result Existence of infinitely many non-equivalent submaximally symmetric models.
VC dimension of ellipsoidsmath.CO
We will establish that the VC dimension of the class of d-dimensional ellipsoids is (d^2+3d)/2, and that maximum likelihood estimate with N-component d-dimensional Gaussian mixture models induces a geometric class having VC dimension at least N(d^2+3d)/2. Keywords: VC dimension; finite dimensional ellipsoid; Gaussian m…
New research shows that the dimension gap between intrinsic and ambient dimensions affects adversarial vulnerability of machine learning models.
problem The mystery of adversarial attacks on machine learning models.
method Introducing two types of adversarial attacks and proving their relationship to the dimension gap.
result The dimension gap between intrinsic and ambient dimensions makes clean-trained models more vulnerable to off-manifold adversarial perturbations.
An efficient algorithm selects the correct number of latent dimensions in multidimensional probit models.
problem Determining the correct number of latent dimensions in multidimensional probit graded response models.
method Adaptive Bayesian dimension selection framework using cumulative ordered spike-and-slab (COSS) prior and Albert--Chib latent response augmentation.
result The proposed method accurately recovers latent structures and avoids repeated model fitting.
New method corrects Laplace/BIC errors in singular models, revealing effective dimension.
problem Laplace/BIC errors in singular models due to incorrect effective dimension assumption.
method RLCT (real log canonical threshold) to correct effective dimension in linear models.
result Correct evidence slope and effective dimension estimation in linear settings.
Study proposes local effective dimension to measure model capacity and generalization error.
problem Capturing the generalization power of machine learning models.
method Proposes local effective dimension as a capacity measure.
result Local effective dimension bounds the generalization error and correlates well with it.
Generative model handles varying data dimensions using jump diffusion processes.
problem Handling data of varying dimensionality in generative models.
method Formulated as a jump diffusion process, learning to approximate the process with a novel evidence lower bound.
result Effective sampling of data of varying dimensionality, better compatibility with test-time diffusion guidance imputation tasks.
NGD models have higher effective dimension than SGD models.
problem Measuring model complexity accurately.
method Comparison of NGD and SGD models using effective dimension measures.
result NGD models have a higher effective dimension than SGD models.
SGD generalizes well in high dimensions without regularization.
problem Generalization of overparameterized models in high dimensions.
method Stochastic Gradient Descent (SGD) for convex and locally convex loss functions.
result Generalization error is independent of the ambient dimension under certain conditions.
A diffusion model estimates data manifold dimension by tracking likelihood increases.
problem Estimating the intrinsic dimension of data manifolds.
method Trained diffusion model approximates score function, revealing manifold directionality.
result Diffusion model provides an approximation of the tangent space's dimension.
Classifies maximal symmetry models of CR dimension 1.
problem Classifying maximal symmetry models of CR manifolds.
method Classification based on Bloom-Graham and Tanaka types, coordinate realization, and extension principle.
result Classification and coordinate realization of maximal symmetry models.
Study shows how many domains are needed for generalization, using a new measure called domain shattering dimension.
problem How many domains are needed for domain generalization?
method Introduced a new combinatorial measure called the domain shattering dimension to model domain sample complexity.
result Established a tight quantitative relationship between domain shattering dimension and classic VC dimension.
It is shown that two Levi-Tanaka and infinitesimal CR automorphism algebras, associated with a totally nondegenerate model of CR dimension one are isomorphic. As a result, the model surfaces are maximally homogeneous and standard. This gives an affirmative answer in CR dimension one to a certain question formulated by …
Projection pursuit model improves Gaussian process regression for high-dimensional data.
problem Scalability issues with traditional Gaussian process models in high dimensions.
method Additive Gaussian process regression with dimension expansion and gradient descent.
result The proposed method approximates more complex functions and outperforms traditional models.
A new tree-based model for varying coefficients using CGBM.
problem Modeling varying coefficients with high dimensionality and complex interactions.
method Tree-based varying coefficient model with CGBM for varying coefficients, dimension-wise early stopping, and feature importance scores.
result The model produces comparable out-of-sample loss to neural networks, demonstrating effectiveness.
Inexistence of Non-Product Hessian Rank 1 Affinely Homogeneous Hypersurfaces in in Dimension math.DG
No non-product Hessian rank 1 affine homogeneous hypersurfaces exist in dimensions 5 and above.
problem Identifying non-product Hessian rank 1 affine homogeneous hypersurfaces in higher dimensions.
method Developed a normal form for hypersurfaces under the affine group, up to order ≤ n+5, in any dimension n ≥ 2.
result Non-existence of non-product Hessian rank 1 affine homogeneous hypersurfaces in dimensions 5 and above.
A Kronecker product model is the set of visible marginal probability distributions of an exponential family whose sufficient statistics matrix factorizes as a Kronecker product of two matrices, one for the visible variables and one for the hidden variables. We estimate the dimension of these models by the maximum rank …
The article calculates the minimal model dimensions for classifying spaces of surface braid groups.
problem Classifying spaces for families of virtually abelian subgroups of surface braid groups.
method Analyzes the pure and full braid groups of surfaces with at least one boundary component or one puncture, proving analogous results for amenable subgroups.
result Minimal dimensions of models for classifying spaces are equal to the virtual cohomological dimension plus the rank of virtually abelian subgroups.
Unified model for interactive estimation with improved learnability measure.
problem Improving learnability in interactive estimation models.
method Introducing a combinatorial measure (dissimilarity dimension) and a general algorithm with polynomial bounds.
result Unified model subsumes statistical-query learning and structured bandits.
The paper provides statistical guarantees for generative models using dimension reduction.
problem Improving the quality of generative models without increasing dimensionality.
method Modeling generative devices as smooth transformations of a lower-dimensional space and using integral probability metrics.
result Established a risk bound showing the impact of dimension reduction on generative model error.
Survey classifies singularity models in 3D Ricci flow.
problem Understanding singularity formation in 3D Ricci flow.
method Analysis of ancient κ-solutions and steady gradient Ricci solitons.
result Complete classification of singularity models in 3D.
Enhances SDR via Hellinger correlation for better data dependency understanding.
problem Improving sufficient dimension reduction in single-index models.
method Developed a new method using Hellinger correlation for detecting the dimension reduction subspace.
result Significantly enhances and outperforms existing SDR methods through deeper data dependency understanding.
Paper develops a fractal dimension-based generalization measure.
problem Developing a robust generalization measure for machine learning models.
method Analyzes decision boundaries using fractal dimension concept.
result Developed a generalization measure based on fractal dimension.
Principal component analysis balancing prediction and approximation accuracy for spatial datastat.ME
New algorithm balances spatial data approximation and prediction accuracy.
problem Lack of methods considering spatial correlation and downstream modeling in dimension reduction.
method Formalizes approximation and modeling utility as metrics, proposes a balanced algorithm.
result Optimal trade-off between approximation accuracy and downstream modeling utility.
Develops robust methods for infinite-dimensional stochastic processes.
problem Measuring covariations in stochastic evolution equations in infinite dimensions.
method Asymptotic theory for jump robust measurement of covariations.
result Identifies scaling limits for realized covariations.
We study the algebraic dimension a(X) of a compact hyperkaehler manfold of dimension 2n. We show that a(X) is at most n unless X is projective. If a compact Kaehler manifold with algebraic dimension 0 and Kodaira dimension 0 has a minimal model, then only the values 0,n and 2n are possible. In case of middle dimension,…
Low-dimensional structure in images helps deep learning models generalize better.
problem Understanding the intrinsic dimensionality of images for better model performance.
method Applied dimension estimation tools to popular image datasets and used GANs to manipulate intrinsic dimensionality.
result Natural image datasets have very low intrinsic dimensionality, which aids neural networks in learning and generalizing.
Deep generative modeling using flows has gained popularity owing to the tractable exact log-likelihood estimation with efficient training and synthesis process. However, flow models suffer from the challenge of having high dimensional latent space, the same in dimension as the input space. An effective solution to the …
We consider partially observed multiscale diffusion models that are specified up to an unknown vector parameter. We establish for a very general class of test functions that the filter of the original model converges to a filter of reduced dimension. Then, this result is used to justify statistical estimation for the u…
Develops a new method for nonlinear dimension reduction using random features.
problem Statistical challenges in generalizing Gaussian process-based latent variable models to non-Gaussian data.
method Random feature latent variable models (RFLVMs) that approximate nonlinear relationships with linear functions of random features.
result RFLVMs produce comparable results to state-of-the-art methods on various data types.
Paper shows graphs can be embedded in lower dimensions than expected.
problem Choosing the right embedding dimension for graph analysis.
method Utilizes hidden manifold structure to predict lower-dimensional embedding.
result Graphs can be embedded in much lower dimensions than previously thought.
We consider the problem of clustering data points in high dimensions, i.e. when the number of data points may be much smaller than the number of dimensions. Specifically, we consider a Gaussian mixture model (GMM) with non-spherical Gaussian components, where the clusters are distinguished by only a few relevant dimens…
The paper explores Kähler-Ricci solitons with maximal symmetry in complex dimension two.
problem Characterizing Kähler-Ricci solitons with maximal symmetry.
method Analyzes the isometry group and uses cohomogeneity one and Sasakian models.
result In complex dimension two, every non-trivial gradient Kähler-Ricci soliton has maximal symmetry.
We prove that any holomorphic locally homogeneous geometric structure on a complex torus, modelled on a complex homogeneous surface, is translation invariant. We conjecture that this result is true is any dimension. In higher dimension we prove it here for nilpotent models. We also prove that in any dimension the trans…
Study on dimensions of mapping class groups of non-orientable surfaces.
problem Determining dimensions of mapping class groups for non-orientable surfaces.
method Analyzing cohomological, geometric, and virtual dimensions.
result Equal dimensions for when .
New insights on eluder dimension for function approximation in machine learning.
problem Complexity measure for online bandits and reinforcement learning with function approximation.
method Study the relationship between eluder dimension and generalized rank for different activation functions.
result Eluder dimension can be exponentially smaller or larger than generalized rank depending on the activation function.
The study reveals optimal early stopping behaviors in deep learning models.
problem Understanding optimal early stopping in deep learning models.
method Theoretical analysis of linear models and experimental validation.
result Two distinct behaviors of optimal early stopping time depending on model dimension relative to dataset features.
The grand arc graph's asymptotic dimension is shown to be infinite.
problem Determining the asymptotic dimension of the grand arc graph.
method Using Gromov-hyperbolic and cocompact arc and curve models, the asymptotic dimension is shown to be infinite for a broad class of surfaces.
result The asymptotic dimension of the grand arc graph is infinite.
Augmented KRnet improves flow-based generative modeling by maintaining exact invertibility.
problem Maintaining exact invertibility in flow-based generative models.
method Integrates augmented dimensions into KRnet to achieve full nonlinear updates in two iterations, keeping exact invertibility.
result Augmented KRnet achieves full nonlinear updates in two iterations, maintaining exact invertibility.
We introduce a notion of "effective dimension" of a statistical model based on the number of cubes of size needed to cover the model space when endowed with the Fisher Information Matrix as metric, being the number of observations. The number of observations fixes a natural scale or resolution. The eff…
Study finds a linear lower bound on conformal dimension for random hyperbolic groups.
problem Understanding conformal dimension in random hyperbolic groups.
method Building undistorted round trees from lower density groups.
result Achieves a linear lower bound in at all densities .
RMFGP combines multi-fidelity models for efficient uncertainty quantification.
problem Efficiently infer quantities of interest with limited high-fidelity data.
method Rotated multi-fidelity Gaussian process with dimension reduction and Bayesian active learning.
result RMFGP model improves accuracy and efficiency in high-dimensional problems.
To model high dimensional data, Gaussian methods are widely used since they remain tractable and yield parsimonious models by imposing strong assumptions on the data. Vine copulas are more flexible by combining arbitrary marginal distributions and (conditional) bivariate copulas. Yet, this adaptability is accompanied b…
This paper evaluates fractal dimension and persistent homology for neural network generalization.
problem Bounding and predicting the generalization gap of neural networks.
method Empirical evaluation of fractal dimension and persistent homology as generalization measures.
result Fractal dimension and persistent homology fail to predict generalization of models trained from poor initializations.
Study on metric bubbles in complex dimensions 1 and 2.
problem Understanding degenerations of Kähler-Einstein metrics.
method Investigation of metric bubble trees for non-collapsing cases.
result Description of a conjectural higher-dimensional picture.