Spectral flow connects manifold geometry to rigidity criteria.
problem Tackling rigidity of simply-connected closed manifolds.
method Spectral deformation flow and invariant-based approach.
result Spherical profile is the unique manifold-compatible asymptotic realization.
This paper explores saturation effects in spectral algorithms over large dimensions.
problem Saturation effects in spectral algorithms over large dimensions.
method Improved minimax lower bound and gradient flow with early stopping strategy.
result Exact convergence rates of spectral algorithms in large dimensional settings.
Introduces a new spectral geometry framework with dissipative data.
problem Deforming spectral triples with dissipative Lindblad operators.
method Lindblad-deformed spectral geometry framework with heat-kernel asymptotics.
result First nontrivial dissipative effect appears at order gamma^4.
Geometrically computes superpotentials for certain 4D N=2 theories.
problem Computing effective twisted superpotentials for 4D N=2 theories.
method Spectral networks and abelianization to compute generating functions of brane opers.
result Geometric recipe for computing effective twisted superpotentials.
Study local geometry of mixture models via spectral theory, revealing transitions in training dynamics.
problem Understanding the local geometry of high-dimensional mixture models.
method Spectral theory of Hessian and information matrices, focusing on i.i.d. Gaussian mixtures.
result Exact formulas for limits of spectral distribution and outlier eigenvalues, connecting training dynamics to effective dynamics.
Simplicial complexes are increasingly used to study complex system structure and dynamics including diffusion, synchronization and epidemic spreading. The spectral dimension of the graph Laplacian is known to determine the diffusion properties at long time scales. Using the renormalization group here we calculate the s…
Study shows how to effectively predict functions on manifolds using kernel methods.
problem Regression on manifolds with limited data.
method Reproducing kernel Hilbert space methods, Weyl law, effective dimension.
result Kernel regression estimator yields minimax-optimal error bounds controlled by effective dimension.
For random graphs distributed according to stochastic blockmodels, a special case of latent position graphs, adjacency spectral embedding followed by appropriate vertex classification is asymptotically Bayes optimal; but this approach requires knowledge of and critically depends on the model dimension. In this paper, w…
Study bandit problem on smooth graph functions for recommender systems.
problem Online learning problems involving graphs, like content-based recommendation.
method Introduced spectral bandit problem and two algorithms that scale linearly in effective dimension.
result Learned user preferences for thousands of items from just tens nodes evaluations.
The paper shows how to recover true node positions from a graph or similarity matrix.
problem Recovering true distances and positions from a graph or similarity matrix.
method Two steps: matrix factorisation followed by nonlinear dimension reduction.
result Nonlinear dimension reduction can recover latent positions close to a manifold where geodesic distance is encoded.
Study on elasticity with mixed boundary conditions, proving spectral asymptotics.
problem Analyzing spectral asymptotics for linear elasticity with mixed boundary conditions.
method Established two-term spectral asymptotics for linear elasticity on smooth compact manifolds.
result Verification of general formulae through explicit examples in 2D and 3D.
Minimal spectral radii found for specific matrix types.
problem Finding smallest spectral radii for certain matrix classes.
method Analyzing skew-reciprocal integer matrices of fixed even dimensions.
result Most classes of matrices have smaller spectral radii than their reciprocal counterparts.
We consider the problem of learning regression functions from pairwise data when there exists prior knowledge that the relation to be learned is symmetric or anti-symmetric. Such prior knowledge is commonly enforced by symmetrizing or anti-symmetrizing pairwise kernel functions. Through spectral analysis, we show that …
Spectral gradient methods outperform Euclidean in certain deep learning scenarios.
problem When do spectral gradient updates outperform Euclidean in deep learning?
method Layerwise condition comparing squared nuclear-to-Frobenius ratio to stable rank of activations.
result Spectral updates can be more effective than Euclidean in deep networks and transformers.
New method for triclustering with reduced arbitrariness.
problem Need for reduced arbitrariness in specifying cluster size.
method Spectral decomposition of tensor slices and intersection of clusters.
result Effective triclustering on synthetic and real-world data.
The paper tackles a bandit problem on graphs with smooth functions, aiming to recommend items with high expected ratings.
problem Online learning problems involving graphs, such as content-based recommendation.
method Introduced the notion of effective dimension and proposed two algorithms for solving the problem.
result The algorithms can learn good estimators of user preferences from just tens of nodes evaluations.
This paper provides a general framework to study the effect of sampling properties of training data on the generalization error of the learned machine learning (ML) models. Specifically, we propose a new spectral analysis of the generalization error, expressed in terms of the power spectra of the sampling pattern and t…
New estimates show spectral gap stability in RCD spaces, close to Beta distribution.
problem Stability of spectral gap bounds in metric-measure spaces.
method Combines L1-functional inequality and Stein's method. result Sharp quantitative estimate for spectral gap stability.
Bayesian method uses data spectra to estimate non-sparse high-dimensional models.
problem Handling many parameters in high-dimensional Bayesian statistics.
method Data-adaptive Gaussian prior aligned with leading eigenvectors of sample covariance.
result Posterior contraction rates reveal the effect of spectral mass on prediction error.
New proof of Llarull's rigidity theorem in odd dimensions via spectral flow.
problem Rigidity of smooth maps from compact spin manifolds to spheres.
method Spectral flow argument for odd dimensions, generalization to convex hypersurfaces.
result Generalization of Llarull's theorem to arbitrary smooth strictly convex hypersurfaces.
Study characterizes cryospheric spectral feature space using joint PC+t-SNE approach.
problem Characterize cryospheric spectral feature space for remote sensing applications.
method Compare and contrast two approaches for identifying feature space basis vectors via dimensionality reduction (PCA and t-SNE).
result Joint characterization reveals distinct continua and clusters of ice reflectance properties.
New lattice Dirac operator index method for curved boundaries.
problem Defining Dirac operator indices for curved boundaries and gravitational backgrounds.
method Employing K-theory and spectral flow to classify Wilson Dirac operator.
result Mod-2 index defined in both even and odd dimensions.
In this work we prove that every locally symmetric smooth submanifold gives rise to a naturally defined smooth submanifold of the space of symmetric matrices, called spectral manifold, consisting of all matrices whose ordered vector of eigenvalues belongs to the locally symmetric manifold. We also present an explicit f…
Novel model captures high-dimensional copulas with spectral dynamics and regularization.
problem Modeling time-varying, asymmetric, tail-dependent copulas in high dimensions.
method Score-driven dynamics for eigenvalues, non-linear shrinkage for biases, parsimonious and scalable.
result Model outperforms recent alternatives in capturing co-movements and diversification potential.
The study shows how geometric Weyl bulk-density exponent rigidifies spectral encodings in O-regularly varying classes.
problem Understanding spectral encodings under Weyl growth conditions.
method Analyzing geometric Weyl bulk-density exponent and proving spectral rigidity.
result The geometric Weyl bulk-density exponent (d−2)/2 rigidifies spectral encodings in the O-regularly varying class, leading to unique admissible exponents and scaling laws. New machine learning method classifies companies effectively.
problem Classifying companies for financial analysis.
method Unsupervised machine learning with t-SNE and spectral clustering.
result Improved portfolio performance through better company classification.
Computes spectral Einstein functional for Witten deformation on even-dimensional spin manifolds.
problem Calculating the spectral Einstein functional for a specific deformation.
method Computes the spectral Einstein functional for the Witten deformation on even-dimensional spin manifolds.
result Computed the spectral Einstein functional for the Witten deformation on even-dimensional spin manifolds.
This paper explains spectral clustering and its equivalence to PCA, breaking it into fully connected and multi-connected cases.
problem Understanding the mathematics behind spectral clustering and its equivalence to PCA.
method Dividing spectral clustering into two categories based on graph connectivity and proving the equivalence to PCA.
result Spectral clustering and PCA are equivalent, with specific proofs for fully connected and multi-connected graphs.
The paper establishes a continuous embedding between two types of Barron spaces in neural networks.
problem Understanding the relationship between two types of Barron spaces in neural networks.
method Introduced a continuous embedding inequality between Barron and spectral Barron spaces.
result The embedding inequality holds for any function in the spaces, with constants independent of the input dimension.
Introduces relative information gain for improving Gaussian process regression rates.
problem Improving the sample complexity of estimating or maximizing unknown functions.
method Introduces relative information gain, interpolates between effective dimension and information gain, and proves PAC-Bayesian bounds.
result Obtains minimax-optimal rates of convergence through the relative information gain.
Enhanced spectral clustering for geometric graphs improves clustering accuracy.
problem Ineffective standard spectral clustering for geometric graphs.
method Higher-order spectral clustering using higher-order eigenvectors.
result Established weak and strong consistency for Soft Geometric Block Model.
Unified framework explains why overfitting is benign in interpolating learning.
problem Understanding why overfitting is benign in highly overparameterized models.
method Spectral-transport stability framework.
result Sharp benign-overfitting criterion and explicit phase-transition rates.
We construct spectral triples in a sense of noncommutative differential geometry, associated with a Riemannian foliation on a compact manifold, and describe its dimension spectrum.
This paper proposes a new approach to construct high quality space-filling sample designs. First, we propose a novel technique to quantify the space-filling property and optimally trade-off uniformity and randomness in sample designs in arbitrary dimensions. Second, we connect the proposed metric (defined in the spatia…
Proves certain Calabi-Yau varieties are projective.
problem Compact Calabi-Yau varieties with isolated singularities are not always projective.
method Analysis and Ohsawa's degenerate spectral sequence in higher dimensions.
result Proves compact Calabi-Yau varieties with certain isolated singularities are projective.
New spectral clustering method for graphs with uneven node degrees.
problem Challenges in community detection for graphs with heterogeneous degree distributions.
method Spectral clustering on spherical coordinates with degree correction.
result Improved performance in representing computer networks.
Graph Laplacians adapt to different manifold dimensions, while Dirichlet energies converge to a tensorized Dirichlet energy.
problem Understanding machine learning methods for data with varying intrinsic dimensions.
method Γ-convergence of graph Dirichlet energies and spectral convergence of graph Laplacians on intersecting manifolds of varying dimensions.
result Normalized Dirichlet energy converges to a tensorized Dirichlet energy that adapts to all dimensions simultaneously.
EigenBayes: A fast, adaptive Bayesian shrinkage approach for high-dimensional matrix factorization
problem Choosing the latent dimension k in factor models method Adaptive spectral shrinkage and empirical Bayes calibration
result Adapts to signal-to-noise ratio and shrinks superfluous components
This paper improves sample efficiency in noisy inductive matrix completion with side-information.
problem Improving sample efficiency in noisy inductive matrix completion with side-information.
method Nonconvex projected gradient descent algorithm with spectral initialization.
result Achieves linear convergence and stable recovery at a sample complexity governed by the effective side-information dimension.
Spectral deconfounding improves machine learning models by reducing hidden confounding effects.
problem Machine learning models can be misled by hidden confounders, leading to unreliable predictions.
method Develops a nonlinear spectral deconfounding framework for gradient boosting that modifies boosting dynamics to slow down in confounding-aligned directions.
result Spectrally deconfounded boosting improves estimation of the target function under hidden confounding and is more scalable.
Extends spectral torus band inequalities for compact manifolds with scalar curvature bounds.
problem Proving upper bounds for the width of compact manifolds with boundary.
method Utilizes spacetime harmonic functions, μ-bubbles, and spinorial Callias operators.
result Generalizes Schoen-Yau black hole existence theorem to higher dimensions.
We first show that hypergeometric functions appear naturally as spectral functions when applying pseudo-differential calculus to decipher heat kernel asymptotic in the situation where the symbol algebra is noncommutative. Such observation leads to a unified (works for arbitrary dimension) method of computing the modula…
Study reveals learning curves and benign overfitting in spectral algorithms for large dimensions.
problem Understanding learning curves and benign overfitting in spectral algorithms for large-dimensional data.
method Analysis of learning curves and benign overfitting in spectral algorithms for inner-product kernels on the sphere and general domains.
result Characterization of three distinct regimes: over-regularized, under-regularized, and interpolation regimes, revealing benign overfitting across both under-regularized and interpolation regimes.
Formula derived for FUP exponent in quasi-Fuchsian groups.
problem Quantifying the fractal uncertainty principle in higher dimensions.
method Explicit formula derivation for FUP exponent, dependence on porosity parameter quantified.
result Explicit essential spectral gap for quasi-Fuchsian groups in higher dimensions.
Study spectral properties on manifolds with conical singularities, proving new inequalities.
problem Analyzing spectral properties and geometric inequalities on manifolds with conical singularities.
method Develops new inequalities for manifolds with conical singularities, not covered by existing methods.
result Proves a Bakry-Émery inequality, Hardy inequality, and spectral gap estimate.
Study on spectral asymptotics in elasticity on smooth manifolds.
problem Analyzing spectral asymptotics in linear elasticity on smooth manifolds.
method Established two-term spectral asymptotics for boundary value problems in linear elasticity.
result Corrected erroneous results in previous studies.
To each non-isotropic almost-complex immersion of a 2-torus into S6 we associate an algebraic curve, called the spectral curve, and a linear flow in the intersection of two Prym varieties on this spectral curve. We show that generically the spectral curve is smooth and compute the dimension of the moduli space o…
This paper improves spectral embedding for multipartite networks, revealing latent subspaces and providing consistent node representations.
problem Improving spectral embedding for multipartite networks to better represent node types.
method Developed a follow-on step to spectral embedding that recovers node representations in their intrinsic rather than ambient dimension, proving consistency under a specific model.
result Node representations in multipartite networks lie near type-specific subspaces, and the proposed method recovers these representations consistently.