Proves Kastler-Kalau-Walze theorem for spectral Einstein functional on low-dimensional manifolds.
problem Proving Kastler-Kalau-Walze type theorems for spectral Einstein functional.
method Defining spectral Einstein functional associated with Dirac operator and proving theorem for low-dimensional manifolds.
result Proves Kastler-Kalau-Walze type theorem for spectral Einstein functional on low-dimensional manifolds with boundary.
We consider the ability of deep neural networks to represent data that lies near a low-dimensional manifold in a high-dimensional space. We show that deep networks can efficiently extract the intrinsic, low-dimensional coordinates of such data. We first show that the first two layers of a deep network can exactly embed…
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.
Unified framework for 3D and 4D manifold and knot theory.
problem Unified understanding of manifold and knot theory.
method Unified correspondence between different subfields of low-dimensional topology.
result Unified algebraic manifestations of 3D and 4D manifold and knot theory.
We study low-dimensional representations of matrix groups over general rings, by considering group actions on CAT(0) spaces, spheres and acyclic manifolds.
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…
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.
Investigates flat bundles over low-dimensional manifolds and their cobordism classes.
problem The cobordism of flat bundles over low-dimensional manifolds.
method Study of flat M-bundles over low-dimensional manifolds, comparing a finite dimensional Lie group G with extDiff0(G) and localizing the holonomy. result Flat M-bundles over low-dimensional manifolds are cobordant to a flat M-bundle. Cryo-em images are found to be low-dimensional.
problem Understanding the geometric structure of cryo-em data.
method Applied manifold learning techniques to CryoSBI representations.
result Cryo-em data inherently populate low-dimensional manifolds.
The paper analyzes side effects of learning from low-dimensional data embedded in a Euclidean space.
problem Learning from data distributed in a linear subspace of high-dimensional space.
method Derives estimates on the variation of the learning function and studies regularization effects.
result Potential regularization effects associated with network depth and noise in codimension of data manifold.
The paper proves compactness of scalar-flat metrics on low-dimensional manifolds with umbilic boundary.
problem Finding scalar-flat metrics with specific boundary conditions.
method Analyzing compact Riemannian manifolds with umbilic boundaries and proving compactness of scalar-flat metrics under certain conditions.
result Scalar-flat metrics are a compact set in low-dimensional manifolds (n=6,7,8) when the Weyl tensor is non-zero on the boundary.
This paper improves causal inference using deep neural networks for low-dimensional covariates.
problem Improving causal inference with deep learning for high-dimensional covariates.
method Doubly robust off-policy learning with deep neural networks on low-dimensional manifolds.
result Nonasymptotic regret bounds for finite- and continuous-action scenarios, converging at a fast rate depending on intrinsic manifold dimension.
ConvResNets approximate Besov functions and classify on low-dimensional manifolds.
problem Lack of statistical theories for deep learning on high-dimensional data.
method Exploits low-dimensional geometric structures of real-world data sets using ConvResNets.
result ConvResNets can approximate Besov functions and learn classifiers with optimal excess risk.
Random projections are able to perform dimension reduction efficiently for datasets with nonlinear low-dimensional structures. One well-known example is that random matrices embed sparse vectors into a low-dimensional subspace nearly isometrically, known as the restricted isometric property in compressed sensing. In th…
Study on rigidity with non-negative intermediate curvature on low-dimensional manifolds.
problem Extending non-existence theorem of positive scalar curvature to product manifolds.
method Introduced intermediate curvature and studied rigidity conditions.
result Rigidity when intermediate curvature is non-negative in low dimensions.
For manifold learning, it is assumed that high-dimensional sample/data points are embedded on a low-dimensional manifold. Usually, distances among samples are computed to capture an underlying data structure. Here we propose a metric according to angular changes along a geodesic line, thereby reflecting the underlying …
Nonlinear dimensionality reduction or, equivalently, the approximation of high-dimensional data using a low-dimensional nonlinear manifold is an active area of research. In this paper, we will present a thematically different approach to detect the existence of a low-dimensional manifold of a given dimension that lies …
Generative flows learn distributions on low-dimensional manifolds robustly via Wasserstein proximals.
problem Learning distributions supported on low-dimensional manifolds robustly.
method Combining Wasserstein-1 and Wasserstein-2 proximal operators to formulate well-posed continuous-time generative flows.
result The combination of Wasserstein-1 and Wasserstein-2 proximals ensures the well-posedness of generative flows, leading to unique and robust learning.
NPMD uses CNNs to optimize policies on low-dimensional manifolds, reducing sample complexity.
problem Explaining the effectiveness of deep policy gradient methods in high-dimensional RL.
method Neural policy mirror descent (NPMD) with CNNs, considering state spaces as low-dimensional manifolds.
result NPMD finds ε-optimal policies with O(ε^(-d/α-2)) samples, leveraging low-dimensional structure.
Derives a method to optimize high-dimensional functions on low-dimensional manifolds.
problem High-dimensional derivative-free optimization with high sample complexity.
method Online learning approach that learns the manifold while optimizing the function.
result Significantly reduces sample complexity compared to existing methods.
We prove a Livsic type theorem for cocycles taking values in groups of diffeomorphisms of low-dimensional manifolds. The results hold without any localization assumption and in very low regularity. We also obtain a general result (in any dimension) which gives necessary and sufficient conditions to be a coboundary.
A new framework detects anomalies in structured data.
problem Detecting anomalies in samples not conforming to low-dimensional manifolds.
method Preference Isolation Forest (PIF) framework combining adaptive isolation methods and preference embedding.
result Anomalies identified as isolated points in a high-dimensional preference space.
Kernel-spectral embedding learns low-dim. structures from noisy data.
problem Learning low-dimensional nonlinear structures from high-dimensional noisy data.
method Adaptive bandwidth spectral embedding using integral operators.
result Convergence to noiseless embeddings and eigenfunctions of integral operators.
Manifold learning has been successfully applied to a variety of medical imaging problems. Its use in real-time applications requires fast projection onto the low-dimensional space. To this end, out-of-sample extensions are applied by constructing an interpolation function that maps from the input space to the low-dimen…
Isometry regularizer improves autoencoder performance on manifold learning.
problem Bad generalization in autoencoders, especially extrinsic and intrinsic issues.
method Introduces an isometry regularizer that encourages the decoder to be an isometry and the encoder to be its pseudo-inverse.
result Isometry regularizer leads to better generalization and useful low-dimensional data representations.
Scientific and engineering processes deliver massive high-dimensional data sets that are generated as non-linear transformations of an initial state and few process parameters. Mapping such data to a low-dimensional manifold facilitates better understanding of the underlying processes, and enables their optimization. I…
Explains how knots relate to 4D shapes.
problem Understanding 4D shapes through knot theory.
method Combines knot theory with 4D manifold topology.
result Connects 4D shapes to knot theory and other geometries.
VAEs struggle with low-dimensional data; this paper shows they can learn the correct manifold.
problem Training VAEs on low-dimensional data.
method Two-stage training algorithm based on conjecture of 0 variance generator.
result VAEs can learn generators with support equal to the ground truth manifold.
Study finds metrics with positive intermediate Ricci curvature on specific low-dimensional manifolds.
problem Existence of invariant metrics with positive intermediate Ricci curvature on low-dimensional cohomogeneity one manifolds.
method Construction of invariant metrics with positive intermediate Ricci curvature on specific manifolds.
result Invariant metrics with positive 4th-intermediate Ricci curvature exist but not for 3rd-intermediate Ricci curvature on certain manifolds.
We give a characterisation of Bieberbach manifolds which are geodesic boundaries of a compact flat manifold, and discuss the low dimensional cases, up to dimension 4.
SGMs can generate samples from low-dimensional data manifolds.
problem Understanding the conditions under which SGMs can produce samples from a low-dimensional data manifold.
method Analyzing the conditions for SGMs to approximate the scores and generate samples from a manifold.
result Precise conditions for SGMs to generate samples from a low-dimensional data manifold.
In this paper we provide the small-time heat kernel asymptotics at the cut locus in three relevant cases: generic low-dimensional Riemannian manifolds, generic 3D contact sub-Riemannian manifolds (close to the starting point) and generic 4D quasi-contact sub-Riemannian manifolds (close to a generic starting point). As …
In this paper we give a characterization of the possible homology groups that can occur for compact simply connected cohomogeneity one manifolds in dimensions seven and lower.
We study the approximate nearest neighbour method for cost-sensitive classification on low-dimensional manifolds embedded within a high-dimensional feature space. We determine the minimax learning rates for distributions on a smooth manifold, in a cost-sensitive setting. This generalises a classic result of Audibert an…
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.
Improved likelihood estimation for singular distributions using deep models.
problem Estimating singular distributions using deep generative models.
method Data perturbation to avoid singularity issues in likelihood estimation.
result Consistent estimation of target distribution with desirable rates.
The local linear embedding algorithm (LLE) is a non-linear dimension-reducing technique, widely used due to its computational simplicity and intuitive approach. LLE first linearly reconstructs each input point from its nearest neighbors and then preserves these neighborhood relations in the low-dimensional embedding. W…
The paper refutes the manifold hypothesis for image data and proposes the union of manifolds hypothesis.
problem The manifold hypothesis fails to capture the structure of image data.
method Empirical verification of the union of manifolds hypothesis on image datasets.
result Image data lies on a disconnected set with varying intrinsic dimensions.
Deep networks can adapt to intrinsic dimensionality beyond domain constraints.
problem Approximating functions on low-dimensional manifolds with high-dimensional data.
method Two-layer compositions with ReLU activation, using dimensionality reducing feature maps.
result Near optimal approximation rates depend on the complexity of the dimensionality reducing map, not the ambient dimension.
The paper explores low-dimensional solenoidal manifolds and their properties.
problem Characterizing and understanding solenoidal manifolds of dimensions 1, 2, and 3.
method Survey and new results about solenoidal manifolds, using theorems of A. Clark and S. Hurder.
result Topologically homogeneous, compact solenoidal manifolds are McCord solenoids and behave like laminated versions of compact manifolds.
We present a novel kernel-based machine learning algorithm for identifying the low-dimensional geometry of the effective dynamics of high-dimensional multiscale stochastic systems. Recently, the authors developed a mathematical framework for the computation of optimal reaction coordinates of such systems that is based …
Improved neural networks for relational reasoning by projecting high-dimensional data to low-dimensional manifolds.
problem Out-of-distribution generalization in complex relational reasoning tasks.
method Neuroscience-inspired inductive-biased module projecting high-dimensional object representations to low-dimensional manifolds.
result Significantly better out-of-distribution generalization performance on relational reasoning tasks.
Paper adapts DDPM to low-dimensional structures in image distributions.
problem Understanding and adapting to low-dimensional structures in image distributions.
method Developed a novel set of analysis tools to characterize algorithmic dynamics.
result First theoretical demonstration that DDPM can adapt to unknown low-dimensional structures.
Paper explores tradeoff between standard and robust accuracy for latent models.
problem Tradeoff between standard accuracy and robust accuracy in adversarial training.
method Revisits adversarial training for latent models, considering Gaussian mixture and generalized linear models.
result Low-dimensional manifold structure mitigates the tradeoff between standard and robust accuracy.
New framework tackles high-dimensional reliability analysis using surrogate models and active subspaces.
problem High computational cost and curse of dimensionality in reliability analysis of high-dimensional systems.
method Sparse Active Subspace (SAS) algorithm for identifying low-dimensional manifolds and constructing efficient surrogate models.
result Proposed framework significantly improves accuracy and efficiency of reliability analysis compared to existing methods.
One of the common tasks in unsupervised learning is dimensionality reduction, where the goal is to find meaningful low-dimensional structures hidden in high-dimensional data. Sometimes referred to as manifold learning, this problem is closely related to the problem of localization, which aims at embedding a weighted gr…
Deep neural networks reveal a low-dimensional manifold structure in data.
problem Understanding the structure of data for better model performance.
method Model-centric analysis of the data manifold using the local data matrix and Fisher information matrix.
result The dataset lies on a data leaf with a dimension bounded by the number of labels.
Classifies minimal immersions from S2 into specific flag manifolds.
problem Classifying minimal immersions from S2 into specific flag manifolds. method Classification based on constant curvature and low-dimensional flag manifolds.
result Primitive minimal immersions of constant curvature from S2 into F2,1,1 and F2,2,1 are classified.