Analysts discuss Nash-Kuiper theorem and its relation to turbulence.
problem High-dimensional phenomena and their relation to PDEs.
method Analysts' perspective on Nash-Kuiper theorem.
result Close connection between Nash-Kuiper theorem and turbulence.
The paper analyzes the training dynamics of neural networks using kernel methods.
problem Understanding the training dynamics of neural networks in high-dimensional settings.
method High-dimensional asymptotics and gradient flow on kernel least-squares objectives.
result The training dynamics of neural networks undergo three stages, characterized by behaviors in the Oracle and Empirical worlds.
Unified analysis of DLNs using DMFT reveals dynamics of loss convergence and generalization trade-offs.
problem Understanding the overall dynamics of diagonal linear networks (DLNs) in neural network training.
method Dynamical Mean-Field Theory (DMFT) applied to DLNs.
result Derives low-dimensional effective process capturing high-dimensional gradient flow dynamics.
TCR simplifies complex models into interpretable causal factors.
problem Understanding complex phenomena in high-dimensional models.
method Information theoretic objective for learning TCR from interventional data.
result TCR generates interpretable high-level explanations from complex models.
A new method uses PDEs to predict spatiotemporal phenomena.
problem Predicting high-dimensional spatiotemporal data.
method Partial differential equations (PDEs) for spatiotemporal disentanglement.
result The method outperforms existing models in accuracy and applicability.
New method for efficient inference over complex parameter spaces.
problem Challenges in Bayesian inference for high-dimensional, intractable likelihoods.
method Arbitrary Marginal Neural Ratio Estimation (AMNRE) for simulation-based inference.
result Efficient inference over arbitrary subsets of parameters without numerical integration.
Study on model collapse in regression models, proposing a mitigation strategy.
problem Model collapse in recursive training of regression models.
method Analytic formulae and adaptive regularization strategy.
result Modified scaling laws and mitigation strategy for model collapse.
SPACY discovers causal graphs from spatiotemporal data using variational inference.
problem Inferring causal relationships from high-dimensional spatiotemporal data with complex correlations.
method SPACY uses variational inference to model latent time series and their causal relationships, incorporating spatial factors to aggregate correlated data.
result SPACY outperforms state-of-the-art methods on synthetic and real-world data, identifying key causal phenomena.
Develops MgCSL for discovering causal structures in high-dimensional data.
problem Discovering causal relationships from high-dimensional data with complex interplay of variables.
method MgCSL uses sparse auto-encoders for coarse-graining and multi-layer perceptrons for detailed analysis, introducing simplified acyclicity constraints.
result MgCSL outperforms existing methods and finds explainable causal connections in fMRI datasets.
Paper presents ACLIME-ADMM for efficient structure learning in high-dimensional physical processes.
problem Learning dependencies in high-dimensional physical processes modeled by PDEs.
method ACLIME-ADMM, a two-step algorithm using ADMM for adaptive structure learning.
result ACLIME-ADMM efficiently recovers structure in real atmospheric data, including wind direction switches.
Analysis of three subspace estimation algorithms under incomplete data.
problem Estimating subspace from incomplete observations in high dimensions.
method High-dimensional analysis of Oja's method, GROUSE, and PETRELS.
result The time-varying principal angles converge weakly to deterministic processes with proper time scaling.
This paper extends RMT for deep learning models beyond eigenvalues.
problem Challenges in high-dimensional, overparameterized ML models.
method Introduces High-dimensional Equivalent to analyze nonlinear models.
result Unified understanding of training and generalization in deep learning.
High-dimensional spectroscopy data makes ML models achieve near-perfect accuracy, even when chemical distinctions are absent.
problem Why machine learning models achieve near-perfect accuracy in spectroscopic classification tasks without chemically meaningful features.
method Theoretical analysis grounded in the Feldman-Hajek theorem and concentration of measure, combined with specific experiments on synthetic and real fluorescence spectra.
result Infinitesimal distributional differences in high-dimensional spaces can lead to perfect separability, making models achieve near-perfect accuracy in spectroscopy.
Kernel methods and MLPs perform similarly to linear models in high dimensions.
problem Understanding the performance of kernel methods and MLPs in high-dimensional settings.
method Analysis of kernel methods and MLPs in a high-dimensional regime with proportional asymptotics.
result Linear models are optimal in high-dimensional settings when data is generated by kernel models with nonlinear relationships.
Classification is an important topic in statistics and machine learning with great potential in many real applications. In this paper, we investigate two popular large margin classification methods, Support Vector Machine (SVM) and Distance Weighted Discrimination (DWD), under two contexts: the high-dimensional, low-sa…
New approach quantifies overfitting in high-dimensional regression.
problem Quantifying and avoiding overfitting in large neural networks.
method Information bottleneck theory to minimize residual information while maximizing relevant bits.
result Characterized the relative information efficiency of randomized regression compared to optimal algorithms.
The paper proposes a method to improve data analysis by considering multiple subsets of attributes (views) to enhance geometric information.
problem Distortion of distance metrics in high-dimensional data analysis.
method Partitioning attributes into multiple subsets (views) and using consensus between views to extract geometric information.
result Enhanced geometric information from multiple views improves data analysis.
Study on ridgeless interpolation in high-dimensional regression models.
problem Understanding interpolation in high-dimensional least squares regression.
method Analyzes ridgeless interpolation in two models: linear and neural network.
result Reveals double descent behavior and benefits of overparametrization.
New method solves high-dimensional PDEs and 2BSDEs efficiently.
problem High-dimensional fully nonlinear PDEs and 2BSDEs in financial models.
method Connection between PDEs and 2BSDEs, merged formulation, temporal discretization, spatial approximation via neural nets, stochastic gradient descent.
result Efficient and accurate solution for high-dimensional nonlinear expectations.
The paper analyzes phase transitions in transfer learning for perceptrons.
problem Understanding when transfer learning from a source task to a target task is beneficial.
method Theoretical analysis of a pair of related perceptron learning tasks.
result Reveals a phase transition from negative to positive transfer as task similarity changes.
Develops a new method for uncertainty quantification in high-dimensional learning.
problem Challenges in uncertainty quantification in high-dimensional regression or learning problems.
method Data-driven approach for UQ that corrects bias terms from training data.
result Non-asymptotic confidence intervals that avoid overestimating uncertainty.
Neural Galerkin schemes use active learning to solve high-dimensional equations.
problem Inaccurate function approximations in high dimensions with limited training data.
method Neural Galerkin schemes based on deep learning with active learning for high-dimensional PDEs.
result Active data collection improves the numerical solution of high-dimensional equations.
A new method uncovers discrete and continuous factors in gene expression data.
problem Jointly identifying discrete and continuous factors of variability without supervision.
method cpl-mixVAE framework using multiple interacting networks.
result The method successfully uncovers discrete and continuous factors in gene expression data.
Develops a machine learning framework for computing most probable paths in stochastic systems.
problem Computing the most probable paths in stochastic dynamical systems.
method Reformulates the boundary value problem of Hamiltonian systems and uses a neural network to solve the Euler-Lagrange equation for the Onsager-Machlup action functional.
result Demonstrates the efficacy and accuracy of the machine learning approach in computing most probable paths for stochastic systems with various types of noise.
Optimal transport calibrates machine learning models for particle physics simulations.
problem Discrepancies between simulation and experimental data limit machine learning effectiveness.
method A model calibration approach based on optimal transport applied to high-dimensional simulations.
result Calibrated high-dimensional representations enable proper calibration of various downstream quantities.
The paper argues against the inefficiency of explaining deep learning phenomena.
problem Explaining deep learning phenomena often leads to ad hoc hypotheses.
method Analyzing recent literature to assess the relevance of these phenomena.
result Many phenomena do not appear in real-world applications and may be inefficient.
The paper solves optimal bounds for separating data points in high dimensions.
problem Correcting AI errors and analyzing vulnerabilities in high-dimensional data.
method General stochastic separation theorems with optimal probability estimates.
result Explicit and optimal estimates of separation probabilities for important classes of distributions.
Letter analyzes training dynamics of a nonlinear contrastive learning model in high dimensions.
problem Understanding training dynamics of nonlinear contrastive learning models in high-dimensional settings.
method High-dimensional analysis using McKean-Vlasov PDEs and low-dimensional ODEs.
result The model's performance evolves according to specific ODEs, revealing features like feature learnability and noise effects.
The paper tackles the challenge of representing and analyzing dynamic phenomena on Riemannian manifolds.
problem Challenges in analyzing trajectories on Riemannian manifolds due to non-linearity and high-dimensionality.
method The paper introduces a framework based on transported square-root velocity fields (TSRVF) to learn an embedding for action representations.
result The key result is the development of a method to map Riemannian trajectories to a low-dimensional Euclidean space, preserving temporal rates.
New CLT for AIPW estimator in high-dimensional settings.
problem Estimating ATE in high-dimensional covariate scenarios.
method Cross-fitting AIPW estimator with well-specified models.
result Established a new CLT for the scaled cross-fit AIPW.
High-dimensional SGD limits show surprising dynamics and phase transitions.
problem Understanding SGD in high dimensions and its scaling limits.
method Proving limit theorems for SGD trajectories in high dimensions, choosing summary statistics, initialization, and step-size.
result Critical scaling regime for step-size, new correction term, and complex diffusive limits.
Path signatures reveal community structure in coupled oscillators' dynamics.
problem Detecting communities in multivariate dynamical processes from time series data.
method Path signatures, a mathematical framework encoding geometric and temporal properties of continuous paths.
result Achieved exact recovery of structural communities from observed time series in multiple KSBM instances.
The paper studies concentration of measure on manifolds with boundary, focusing on 1-Lipschitz functions.
problem Concentration of measure phenomena of non-negative 1-Lipschitz functions on manifolds with Dirichlet boundary condition. method Examined relation between boundary concentration phenomena and large spectral gap phenomena of Dirichlet eigenvalues of Laplacian. Introduced new invariant called the observable inscribed radius.
result Formulated comparison theorems for the observable inscribed radius under lower Ricci curvature and mean curvature bounds for the boundary.
The paper develops a statistical theory explaining overfitting in imbalanced classification.
problem Overfitting in high-dimensional imbalanced classification.
method Developed a statistical theory for support vector machines and logistic regression.
result Overfitting is more severe for the minority class due to truncation or skewing effects in high-dimensional data.
Sharp changes in time series representing market dynamics are studied by means of the self--similar analysis suggested earlier by the authors. These sharp changes are market booms and crashes. Such crises phenomena in markets are analogous to critical phenomena in physics. A simple classification of the market crisis p…
The paper introduces new concepts to understand natural phenomena through topology and dynamics.
problem Understanding natural phenomena like tornado formation using topology and dynamics.
method Developed new theoretical concepts and models for 2-dimensional and solid 2-dimensional 0-surgery.
result Enhanced understanding of natural phenomena through topology and dynamics.
Study on Lane-Emden equation on curved spaces, revealing new existence and non-existence phenomena.
problem Existence and non-existence of positive solutions for the Lane-Emden equation on Riemannian models.
method Analysis of the subcritical Lane-Emden equation on various Riemannian manifolds with polynomial volume growth.
result Subcritical regime divides into three ranges with distinct existence and non-existence phenomena.
The paper explores higher property T in lattices and its connections to geometric phenomena.
problem Understanding higher property T in lattices and related geometric phenomena.
method Operator-algebraic characterizations of higher property T and connections to lattice geometry.
result Unified framework for understanding higher property T and related geometric phenomena.
This research connects topological changes to cosmic phenomena like black hole formation.
problem Understanding topological changes in cosmic phenomena.
method Using topological surgery and Morse functions to describe changes in 3-manifolds and their fundamental groups.
result New insights into natural phenomena through a topological perspective.
Paper connects Stokes phenomena to quantum groups and Poisson-Lie groups.
problem Analyse Stokes phenomena in Poisson-Lie groups and quantum groups.
method Use Ug-valued Stokes phenomena to construct quantum group U_hg and relate it to Poisson-Lie group G*.
result Show that Ug-valued Stokes phenomena can be obtained as a semiclassical limit of the KZ associator.
Gradient descent protects large neural networks from overfitting in high-dimensional data.
problem Generalization error in large neural networks trained on high-dimensional data.
method Average case analysis using random matrix theory and linear model solutions.
result Gradient descent naturally protects against overtraining in large networks, reducing overfitting at intermediate network sizes.
New topological surgery concepts for natural phenomena.
problem Understanding topological changes in natural processes.
method Extending topological surgery to natural phenomena, introducing new concepts.
result Enhanced understanding of topological changes in natural phenomena.
The study reveals the spectral structure of attention layers and its implications for generalization.
problem Understanding the spectral structure and generalization of trained attention layers.
method Empirical risk minimization in a single-head tied-attention layer, using random matrix theory, spin-glass theory, and approximate message passing.
result Exact high-dimensional characterization of training and test error, interpolation and recovery thresholds, and spectrum of the key and query matrices.
Paper investigates rigidity phenomena for weighted Ricci curvature bounds with Laplacian comparison theorem.
problem Investigating rigidity phenomena for weighted Ricci curvature bounds.
method Derived comparison geometric estimates and generalized for non-symmetric Laplacian.
result Obtained rigidity results for Laplacian comparison theorem, diameter comparisons, and volume comparisons.
We give a survey of some known results and of the many open questions in the study of generic phenomena in geometrically interesting groups.
New topological surgery concepts for natural phenomena.
problem Capturing topological changes in natural processes.
method Introducing new topological surgery concepts.
result Theoretical setting for examining topological changes.
Analyzes magnetic Laplacian on hyperbolic surfaces, highlighting key quantum phenomena.
problem Understanding quantum phenomena on hyperbolic surfaces with magnetic fields.
method Semiclassical analysis and mathematical modeling of the magnetic Laplacian.
result Discovers new insights into quantum behavior on hyperbolic surfaces with magnetic fields.
Study exotic phenomena in small 4-manifolds using diffeomorphisms.
problem Understanding exotic smooth structures and embeddings in 4-manifolds.
method Using constraints from Seiberg-Witten theory on diffeomorphisms.
result New methods to detect and bound exotic phenomena.