Research
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.

168,695 papers · 148 categories

Trend · papers per month

134267401534 · May 202619922001200920172026
48 results for intrinsic low-dimensional structures

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.

Diffusion models learn multi-modal distributions with optimal efficiency.

problem Learning high-dimensional distributions with low-dimensional multi-modal structures.
method Score-based diffusion models, focusing on subgaussian distributions within subspaces.
result Diffusion models require O~(εk2)\widetilde{O}(\varepsilon^{-k \vee 2}) samples for 1-Wasserstein ε\varepsilon error, improving over prior guarantees.

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.

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.

Paper examines global Covid-19 data complexity and finds low intrinsic dimensions.

problem Understanding the complexity of Covid-19 data across countries.
method Used a Bayesian mixture model (Hidalgo) to estimate intrinsic dimensionality.
result Covid-19 data projects onto two low-dimensional manifolds without significant loss of information.

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.

The input data features set for many data driven tasks is high-dimensional while the intrinsic dimension of the data is low. Data analysis methods aim to uncover the underlying low dimensional structure imposed by the low dimensional hidden parameters by utilizing distance metrics that consider the set of attributes as…

2016-06-28abs ↗pdf ↗

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.

Wasserstein Autoencoders improve model efficiency and interpretability for low-dimensional data.

problem Limited statistical guarantees for WAEs in low-dimensional data.
method Proper network architecture selection and analysis of expected excess risk convergence rates.
result WAEs can learn data distributions efficiently when intrinsic dimension is considered.

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.

New research shows DDPM can adapt to data's intrinsic low dimensionality efficiently.

problem Theoretical inefficiency of DDPM in high-dimensional data.
method Investigates how DDPM can exploit intrinsic low dimensionality of data.
result Proves DDPM's iteration complexity scales nearly linearly with intrinsic dimension kk.

The paper shows diffusion models can converge faster to a target distribution with low-dimensional structure.

problem Improving the convergence rate of diffusion models to target distributions.
method Analyzing DDIM and DDPM samplers under low-dimensional structure assumptions.
result The iteration complexities of DDIM and DDPM are no greater than k/εk/\varepsilon in total variation distance.

Recent theory work has found that a special type of spatial partition tree - called a random projection tree - is adaptive to the intrinsic dimension of the data from which it is built. Here we examine this same question, with a combination of theory and experiments, for a broader class of trees that includes k-d trees…

2012-05-09abs ↗pdf ↗

Novelty search in low-dimensional space improves sample efficiency in exploration tasks.

problem Efficient exploration in complex environments with sparse rewards.
method Combines model-based and model-free objectives to learn a low-dimensional representation. Uses intrinsic novelty rewards based on nearest neighbor distances in this space.
result Our approach achieves more sample-efficient exploration compared to strong baselines on various tasks.

Paper analyzes dataset distillation for efficient encoding of task-relevant information.

problem Efficiently encoding task-relevant information from gradient-based learning of non-linear tasks.
method Theoretical analysis of dataset distillation applied to two-layer neural networks with gradient-based training.
result Low-dimensional structure of the problem is efficiently encoded into distilled data, reproducing a model with high generalization ability.

The paper improves the probability flow ODE sampler for faster sampling of natural images.

problem Improving the convergence rate of the probability flow ODE sampler.
method Adapting the probability flow ODE sampler to exploit intrinsic low-dimensional structures in natural image data.
result Achieves a dimension-free convergence rate of O(k/T)O(k/T) in total variation distance, improving upon existing results.

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 study explains transformer scaling laws using statistical and approximation theories.

problem Understanding why transformer scaling laws exist for large models trained on low-dimensional data.
method Established statistical estimation and mathematical approximation theories for transformers on low-dimensional manifolds.
result Predicted a power law between generalization error and model and data sizes, with power depending on intrinsic data dimension.

Contrastive learning adapts to data intrinsic dimensions, learning low-dimensional representations.

problem Learning high-dimensional representations from multi-modal data.
method Multi-modal contrastive learning with temperature optimization.
result Contrastive learning adapts to intrinsic dimensions of data, not specified dimensions.

Chart autoencoders learn latent features preserving manifold topology and geometry, with robust denoising capabilities.

problem Learning low-dimensional latent features of high-dimensional data sampled near a manifold.
method Chart autoencoders encode data into latent features on charts, preserving manifold topology and geometry.
result Chart autoencoders achieve a squared generalization error of n2d+2log4nn^{-\frac{2}{d+2}}\log^4 n under proper network architectures.

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.

Data living on manifolds commonly appear in many applications. Often this results from an inherently latent low-dimensional system being observed through higher dimensional measurements. We show that under certain conditions, it is possible to construct an intrinsic and isometric data representation, which respects an …

2018-06-01abs ↗pdf ↗

This paper describes a method for learning low-dimensional approximations of nonlinear dynamical systems, based on neural-network approximations of the underlying Koopman operator. Extended Dynamic Mode Decomposition (EDMD) provides a useful data-driven approximation of the Koopman operator for analyzing dynamical syst…

2017-12-04abs ↗pdf ↗

The paper tackles transfer learning for growing matrix representations, improving estimation accuracy.

problem Structured matrix estimation under growing ambient dimensions and latent representations.
method Proposes a general transfer framework decomposing target parameters into embedded source components, low-rank innovations, and sparse edits. Develops an anchored alternating projection estimator.
result Establishes deterministic error bounds that separate target noise, representation growth, and source estimation error, yielding improved rates.

New theory shows deep networks adapt to data's intrinsic dimensionality even when data isn't on a low-dimensional manifold.

problem Existing theories on deep nonparametric regression assume data lie on a low-dimensional manifold, which is often not the case in real-world applications.
method Introduces effective Minkowski dimension to characterize the intrinsic dimension of data subsets and proves sample complexity depends on this new complexity notation.
result Deep neural networks can adapt to the effective Minkowski dimension of data, circumventing the curse of dimensionality for moderate sample sizes.

Deep multi-task learning benefits from low intrinsic dimensionality, leading to better generalization.

problem Improving generalization in deep multi-task learning with high-dimensional models.
method Parametrizing multi-task networks in a low-dimensional space using random expansions and weight compression.
result First non-vacuous generalization bounds for deep multi-task networks are derived.

Paper improves deep learning convergence rates for low-dimensional data.

problem Sub-optimal rates in deep learning due to unrealistic assumptions on intrinsic dimension.
method Introduced an entropic notion of intrinsic dimension for exponential families and demonstrated improved convergence rates.
result Test error scales as O~(n2β2β+dˉ2β(λ))\tilde{\mathcal{O}}\left(n^{-\frac{2β}{2β+ \bar{d}_{2β}(λ)}}\right), improving on best-known rates.

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.

A new method for SVGD reduces variance in high dimensions.

problem High-dimensional variance in SVGD.
method Grassmann Stein Variational Gradient Descent (GSVGD) projects onto arbitrary subspaces and uses coupled Grassmann-valued diffusion.
result GSVGD explores high-dimensional problems with intrinsic low-dimensional structure efficiently.

The Random Projection Tree structures proposed in [Freund-Dasgupta STOC08] are space partitioning data structures that automatically adapt to various notions of intrinsic dimensionality of data. We prove new results for both the RPTreeMax and the RPTreeMean data structures. Our result for RPTreeMax gives a near-optimal…

2010-10-19abs ↗pdf ↗

Integrating wind power into the grid is challenging because of its random nature. Integration is facilitated with accurate short-term forecasts of wind power. The paper presents a spatio-temporal wind speed forecasting algorithm that incorporates the time series data of a target station and data of surrounding stations…

2015-03-04abs ↗pdf ↗

Improved score matching methods for estimating score functions and Hessians without high dimensionality.

problem Estimating score functions and Hessians efficiently in high-dimensional data.
method Implicit score matching and denoising score matching, leveraging Gagliardo-Nirenberg inequalities.
result Achieves convergence rates similar to denoising score matching and estimates Hessians without dimensionality issues.

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)O(k/\varepsilon) complexity.

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.

We consider dynamic pricing with many products under an evolving but low-dimensional demand model. Assuming the temporal variation in cross-elasticities exhibits low-rank structure based on fixed (latent) features of the products, we show that the revenue maximization problem reduces to an online bandit convex optimiza…

2018-01-30abs ↗pdf ↗

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-pp distance.
result Error bounds scale as n1/dp,q(μ)n^{-1 / d^\ast_{p,q}(μ)} for diffusion models.

Deep networks can approximate high-dimensional distributions from low-dimensional ones.

problem Approximating high-dimensional distributions from low-dimensional ones.
method Proved neural networks can transform low-dimensional distributions to high-dimensional ones with arbitrary closeness measured by Wasserstein distances and maximum mean discrepancy.
result Upper bounds of the approximation error are obtained in terms of the width and depth of neural network.

W2S FT often outperforms weak teachers due to low intrinsic dimensionality.

problem Understanding why weak-to-strong finetuning outperforms weak models.
method Analyzing W2S in ridgeless regression setting, focusing on variance reduction.
result Weak teacher's variance is inherited by strong student in shared feature subspace, reduced in discrepancy subspace.