Estimates intrinsic dimension of data manifolds using local angle statistics.
problem Estimating intrinsic dimension of data on manifolds.
method Local angle statistics to estimate variance of angles between vectors near a point on the manifold.
result Consistency and asymptotic distribution of the local dimension estimator established.
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 ~ ( ε − k ∨ 2 ) \widetilde{O}(\varepsilon^{-k \vee 2}) O ( ε − k ∨ 2 ) samples for 1-Wasserstein ε \varepsilon ε error, improving over prior guarantees. Inference-Time Scaling can be extended to domains prone to systematic failure using intrinsic statistics.
problem Scaling inference time in domains prone to systematic failure
method Intrinsic Selection (iS), Intrinsic Particle Filtering (iPF), and Particle Distillation (dPF)
result Intrinsic Selection improves engineering design selection by 20% and pass@1 by 6.1 points on average.
Unified framework for singular statistical models using observable charts.
problem Non-identifiability and breakdown of classical asymptotic theory in singular models.
method Invariant framework based on observable charts to define local coordinate systems in model space.
result Observable order provides a lower bound on KL divergence vanishing rate in singular models.
Study provides bounds for estimating intrinsic dimension using Gaussian kernels.
problem Estimating intrinsic dimension from data.
method Finite-sample concentration and anti-concentration bounds for Gaussian kernel sums.
result Explicit dependence on sample size, bandwidth, and geometric parameters.
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.
New covariance function improves climate model accuracy.
problem Non-stationary and non-uniform spatial data in climate modeling.
method Intrinsic non-stationary covariance function for Gaussian process regression.
result Improved regression estimates for relative sea level changes.
New Wintgen inequality for statistical surfaces discovered.
problem Extending Wintgen inequality to statistical surfaces.
method Applied Wintgen inequality framework to statistical surfaces.
result Established Wintgen inequality for statistical surfaces.
Paper proposes a new method for efficient exploration in reinforcement learning.
problem Sparse reward reinforcement learning challenges in exploration.
method Learn separate intrinsic and extrinsic task policies, schedule between them, and use successor feature control (SFC).
result Substantially improved exploration efficiency with SFC and hierarchical usage of intrinsic drives.
The paper improves ranking by integrating covariates and sparse intrinsic scores.
problem Ranking items with incomplete preference scores explained by covariates.
method Extends BTL model with covariate information and sparse intrinsic scores, using penalized MLE.
result Developed debiased estimator for penalized MLE with distributional properties.
MSA compares neural representations' intrinsic geometry for better understanding.
problem Existing similarity measures fail to capture subtle distinctions between neural network solutions.
method Metric similarity analysis (MSA) using Riemannian geometry.
result MSA can disentangle features of neural computations and compare nonlinear dynamics.
New estimators for intrinsic dimension and Wasserstein distance improve OT accuracy.
problem Intrinsic dimension estimation and Wasserstein distance estimation in large-scale OT.
method Introduces novel estimators for intrinsic dimension and Wasserstein distance.
result Simple, tuning-free estimator of OT and fast intrinsic dimension estimator.
Research aims to bridge statistical learning to causal models in AI.
problem Challenges in machine learning and AI related to causality.
method Transition from statistical learning to causal models.
result Progress in AI may require advances in causal modeling.
The paper improves GANs' theoretical guarantees for low-dimensional data.
problem Theoretical guarantees for GANs' statistical accuracy remain pessimistic.
method Analytical derivation of statistical guarantees on estimated densities.
result Theoretical rates of convergence for GANs and BiGANs are derived.
New method estimates deep neural network's intrinsic dimension for better generalization.
problem Estimating intrinsic dimension of deep neural networks for generalization.
method Topological data analysis (TDA) and persistent homology (PHD).
result Efficient algorithm to estimate PHD in deep neural networks.
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…
New method learns intrinsic manifold from observed data for accurate localization.
problem Learning latent intrinsic geometry from observed high-dimensional data.
method Intrinsic Isometric Manifold Learning (IIML) using neural networks for metric estimation.
result IIML achieves accurate localization in ad-hoc sensor networks from imaging data.
Study finds intrinsic multifractality in maize and barley spot markets, but not in wheat and rice.
problem Understanding the complex price behavior of global grain spot markets.
method Utilized multifractal fluctuation analysis (MF-DFA) to investigate intrinsic multifractality.
result Intrinsic multifractality found in maize and barley sub-indices, but not in wheat and rice.
Estimates intrinsic dimension without distances, outperforming other methods.
problem Estimating intrinsic dimension for efficient data processing.
method Uses binary adjacency matrices based on a random connection model.
result Asymptotic distribution and rate of convergence specified.
The thesis explores prediction games with different opponents and moves, revealing intrinsic barriers and efficient algorithms.
problem Understanding and designing efficient algorithms for prediction games with various opponents and move orders.
method Geometric insights into three types of prediction games: general learning task, prediction with expert advice, and online convex optimization.
result Revealed intrinsic barriers and developed computationally efficient learning algorithms with strong theoretical guarantees.
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.
Sharp computational-statistical phase transitions for hypothesis testing problems.
problem Understanding the limits of statistical accuracy with computational constraints.
method Oracle computational model to connect risk with problem structures.
result Sharp characterization of phase transitions for normal mean and sparse principal component detection.
This paper explores intrinsic rewards to improve learning from multiple value functions.
problem How to adapt reinforcement learning systems to optimize learning from multiple value functions.
method Investigated and compared 14 different intrinsic reward mechanisms in a new bandit-like parallel-learning testbed.
result Intrinsic rewards based on the amount of learning can generate useful behavior, if each individual learner is introspective.
A new statistical model uses Orlicz-Sobolev spaces with Gaussian weight.
problem Statistical modeling of infinite-dimensional probability measures.
method Affine statistical bundle on Gaussian Orlicz-Sobolev space.
result Provides tools for solving infinite-dimensional evolution problems.
Unified geometric interpretation of statistical estimation inequalities.
problem Curvature corrections in parametric statistical estimation.
method Cartan-geometric jet bundle formulation and jet prolongations.
result Unified geometric interpretation of higher-order information inequalities.
Diffusion means converge to extrinsic means for long times on spheres.
problem Understanding the long-time behavior of diffusion means on manifolds.
method Introduced diffusion means as a parameterized family of location statistics on manifolds, and analyzed their convergence to extrinsic means for long times.
result For real projective spaces and connected compact symmetric spaces, the long-time limit of diffusion means is conjectured to be the extrinsic mean in the isometric embedding.
The paper classifies statistical Einstein manifolds in exponential families.
problem Classifying statistical Einstein manifolds in exponential families.
method Deriving partial differential equations for potential functions, obtaining special and group-invariant solutions.
result Special and group-invariant solutions of the equations for potential functions of exponential families.
Polynomial chaos surrogates handle intrinsic noise in stochastic models.
problem Handling intrinsic noise in stochastic models with parametric uncertainty.
method Developed a PCE surrogate on a joint space of intrinsic and parametric uncertainty using Rosenblatt transformations and Karhunen-Loeve expansion.
result Quantified intrinsic noise contribution to model output variance using PCE Sobol indices.
The paper analyzes Karcher means on restricted PSD matrices with statistical guarantees.
problem Statistical analysis of non-linear manifolds in machine learning.
method Intrinsic mean model on restricted PSD matrices, Karcher mean analysis, extrinsic signal-plus-noise model.
result Non-asymptotic statistical analysis of Karcher means with deterministic error bounds.
Flow matching adapts to manifold structures without diffusion.
problem Theoretical understanding of flow matching in manifold-supported settings.
method Flow matching with linear interpolation on smooth manifolds, analyzing velocity field and density estimator.
result Non-asymptotic convergence guarantee and statistical consistency of flow matching on manifolds.
AI uses statistical PQRS workflow for human-machine collaboration.
problem Integrating AI with statistical principles for better results.
method PQRS workflow integrating statistical concepts with AI.
result Reproducibility and interpretability of AI algorithms and results.
Study shows one-dimensional location-scale-shape models are flat in Wasserstein geometry.
problem Investigating curvature in location-scale-shape models under Wasserstein metric.
method Introduced location-scale-shape model and investigated its geometry.
result Location-scale-shape model is intrinsically flat but extrinsically curved in Wasserstein geometry.
The paper analyzes how much data points can be altered to change their rank in nearest neighbor searches.
problem Vulnerability of nearest neighbor search in high-dimensional data.
method Statistical analysis of perturbation needed to change neighbor rank.
result Derived statistical distribution of perturbation needed to modify neighbor rank.
New budget quantifies drift in closed-loop learning, improving reproducibility.
problem Characterizing statistical learning under distributional drift in closed-loop settings.
method Introduces an intrinsic drift budget C T C_T C T quantifying cumulative information-geometric motion of the data distribution. result Proves a drift-feedback bound of order T − 1 / 2 + C T / T T^{-1/2}+C_T/T T − 1/2 + C T / T for prequential reproducibility, up to controlled second-order remainder terms. Geometric surgery theory applied to quantum statistics in spacetime.
problem Constraints of quantum statistics data in spacetime dimensions.
method Geometric-topology surgery theory applied to spacetime manifolds.
result New quantum surgery constraints derived, analogous to Verlinde formula.
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.
Paper proposes KIIM to infer causal relationships from data.
problem Inferring causal relationships from data is challenging.
method KIIM captures higher order statistics of conditional distributions.
result KIIM outperforms existing methods in causal inference.
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 p p distance. result Error bounds scale as n − 1 / d p , q ∗ ( μ ) n^{-1 / d^\ast_{p,q}(μ)} n − 1/ d p , q ∗ ( μ ) for diffusion models. We develop methods to efficiently approximate data in metric spaces without additional assumptions.
problem Efficiently approximating data in metric spaces without imposing structural assumptions.
method Identify discrete modulus of continuity, investigate consistency, propose algorithm, and develop approximation theory.
result Consistent approximation of data in metric spaces without structural assumptions.
Proofs Fisher-Rao distance on Gaussian covariance manifold.
problem Proving Fisher-Rao distance on Gaussian covariance manifold.
method Basic Riemannian geometry.
result Proof of Fisher-Rao distance on covariance cone.
QPass evaluates soccer players' passes based on intrinsic value.
problem Lack of quantitative evaluation of players' contributions to team strategy.
method Developed QPass methodology to quantify player pass value.
result Players losing ball possession can lead to better chances of winning.
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 ~ ( n − 2 β 2 β + d ˉ 2 β ( λ ) ) \tilde{\mathcal{O}}\left(n^{-\frac{2β}{2β+ \bar{d}_{2β}(λ)}}\right) O ~ ( n − 2 β + d ˉ 2 β ( λ ) 2 β ) , improving on best-known rates. Introduces intrinsic Riemannian cross-covariance for manifold-valued random objects.
problem Covariance estimation for random objects on Riemannian manifolds.
method Defines covariance and correlation via parallel transport.
result Proposed covariance is independent of coordinate choices.
Introduces intrinsic Hopf-Lax semigroup linking to intrinsic slope.
problem Understanding intrinsic Hopf-Lax semigroup and its relation to intrinsic slope.
method Introduces and proves the link between intrinsic Hopf-Lax semigroup and intrinsic slope.
result Intrinsic Hopf-Lax semigroup is a subsolution of Hamilton-Jacobi type equality.
This paper analyzes deep federated learning for low-dimensional data, revealing intrinsic dimensionality's role in convergence rates.
problem Insufficient investigation of generalization error in heterogeneous federated learning, especially for low-dimensional data.
method Statistical analysis of deep federated regression in a two-stage sampling model.
result Intrinsic dimensionality, characterized by entropic dimension, determines convergence rates for deep learners.
The paper analyzes reflected diffusion models on hypercube data.
problem Challenges in modeling bounded domains with low-dimensional data.
method Employed an infinite series expansion of transition densities to bound the score function and its approximation.
result Established convergence rates for generative algorithm adapting to intrinsic dimensionality.
A neural network-based two-sample test improves classification accuracy.
problem Differentiating between two sub-exponential densities.
method Difference of logit function from trained classification neural network.
result Network complexity scales with intrinsic dimensionality for low-dimensional manifolds.
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.