Copertina

High-dimensional Asymptotics of Langevin Dynamics in Spiked Matrix Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Liang, Tengyuan, Sen, Subhabrata, Sur, Pragya
Natura:	Preprint
Pubblicazione:	2022
Soggetti:	Statistics Theory Machine Learning Probability
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Self-Distillation is Optimal Among Spectral Shrinkage Estimators in Spiked Covariance Models
di: Lecoiu, Radu, et al.
Pubblicazione: (2026)

Non-Asymptotic Analysis of Data Augmentation for Precision Matrix Estimation
di: Morisset, Lucas, et al.
Pubblicazione: (2025)

Time-Inhomogeneous Preconditioned Langevin Dynamics
di: Falk, Alexander, et al.
Pubblicazione: (2026)

Optimality of Approximate Message Passing Algorithms for Spiked Matrix Models with Rotationally Invariant Noise
di: Dudeja, Rishabh, et al.
Pubblicazione: (2024)

Fundamental limits of community detection from multi-view data: multi-layer, dynamic and partially labeled block models
di: Yang, Xiaodong, et al.
Pubblicazione: (2024)

Concentration of the Langevin Algorithm's Stationary Distribution
di: Altschuler, Jason M., et al.
Pubblicazione: (2022)

Optimal and Provable Calibration in High-Dimensional Binary Classification: Angular Calibration and Platt Scaling
di: Li, Yufan, et al.
Pubblicazione: (2025)

Blessings and Curses of Covariate Shifts: Adversarial Learning Dynamics, Directional Convergence, and Equilibria
di: Liang, Tengyuan
Pubblicazione: (2022)

High-Dimensional Asymptotics of Differentially Private PCA
di: Yun, Youngjoo, et al.
Pubblicazione: (2025)

Approximating Langevin Monte Carlo with ResNet-like Neural Network architectures
di: Miranda, Charles, et al.
Pubblicazione: (2023)

Parallelized Midpoint Randomization for Langevin Monte Carlo
di: Yu, Lu, et al.
Pubblicazione: (2024)

Bayes optimal learning in high-dimensional linear regression with network side information
di: Nandy, Sagnik, et al.
Pubblicazione: (2023)

Distributional Shrinkage II: Higher-Order Scores Encode Brenier Map
di: Liang, Tengyuan
Pubblicazione: (2025)

Efficient Sampling on Riemannian Manifolds via Langevin MCMC
di: Cheng, Xiang, et al.
Pubblicazione: (2024)

kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients
di: Lytras, Iosif, et al.
Pubblicazione: (2025)

User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient
di: Dalalyan, Arnak S., et al.
Pubblicazione: (2017)

Spectrum-Aware Debiasing: A Modern Inference Framework with Applications to Principal Components Regression
di: Li, Yufan, et al.
Pubblicazione: (2023)

Eigen-Spike Emergence and Quadratic Equivalents for Conjugate Kernels on Nonlinearly Separable Data
di: Cranston, Collin, et al.
Pubblicazione: (2026)

Asymptotically optimal sequential change detection for bounded means
di: Ram, Ashwin, et al.
Pubblicazione: (2026)

Non-asymptotic estimates for accelerated high order Langevin Monte Carlo algorithms
di: Neufeld, Ariel, et al.
Pubblicazione: (2024)

A Dynamical System View of Langevin-Based Non-Convex Sampling
di: Karimi, Mohammad Reza, et al.
Pubblicazione: (2022)

Asymptotic spectrum of weighted sample covariance: another proof of spectrum convergence
di: Oriol, Benoit
Pubblicazione: (2024)

Statistical Limits in Random Tensors with Multiple Correlated Spikes
di: Qi, Yang, et al.
Pubblicazione: (2025)

Spectral Estimators for Multi-Index Models: Precise Asymptotics and Optimal Weak Recovery
di: Kovačević, Filip, et al.
Pubblicazione: (2025)

Convergence of Kinetic Langevin Monte Carlo on Lie groups
di: Kong, Lingkai, et al.
Pubblicazione: (2024)

Preventing Model Collapse Under Overparametrization: Optimal Mixing Ratios for Interpolation Learning and Ridge Regression
di: Garg, Anvit, et al.
Pubblicazione: (2025)

Dynamic Structural Causal Models
di: Boeken, Philip, et al.
Pubblicazione: (2024)

ROTI-GCV: Generalized Cross-Validation for right-ROTationally Invariant Data
di: Luo, Kevin, et al.
Pubblicazione: (2024)

Sampling and estimation on manifolds using the Langevin diffusion
di: Bharath, Karthik, et al.
Pubblicazione: (2023)

Universality of high-dimensional scaling limits of stochastic gradient descent
di: Gheissari, Reza, et al.
Pubblicazione: (2025)

High-dimensional analysis of ridge regression for non-identically distributed data with a variance profile
di: Bigot, Jérémie, et al.
Pubblicazione: (2024)

Asymptotic non-linear shrinkage and eigenvector overlap for weighted sample covariance
di: Oriol, Benoit
Pubblicazione: (2024)

Generalization error of min-norm interpolators in transfer learning
di: Song, Yanke, et al.
Pubblicazione: (2024)

High-dimensional ridge regression with random features for non-identically distributed data with a variance profile
di: Dabo, Issa-Mbenard, et al.
Pubblicazione: (2025)

Local geometry of high-dimensional mixture models: Effective spectral theory and dynamical transitions
di: Arous, Gerard Ben, et al.
Pubblicazione: (2025)

Non-asymptotic analysis of Langevin-type Monte Carlo algorithms
di: Nakakita, Shogo
Pubblicazione: (2023)

Matrix Denoising with Doubly Heteroscedastic Noise: Fundamental Limits and Optimal Spectral Methods
di: Zhang, Yihan, et al.
Pubblicazione: (2024)

A Fourier representation of kernel Stein discrepancy with application to Goodness-of-Fit tests for measures on infinite dimensional Hilbert spaces
di: Wynne, George, et al.
Pubblicazione: (2022)

Multi-Environment GLAMP: Approximate Message Passing for Transfer Learning with Applications to Lasso-based Estimators
di: Wang, Longlin, et al.
Pubblicazione: (2025)

Sharp detection of low-dimensional structure in probability measures via dimensional logarithmic Sobolev inequalities
di: Li, Matthew T. C., et al.
Pubblicazione: (2024)