Cover Image

High dimensional analysis reveals conservative sharpening and a stochastic edge of stability

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Agarwala, Atish, Pennington, Jeffrey
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Optimization and Control Statistics Theory Data Analysis, Statistics and Probability
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Contributions to Robust and Efficient Methods for Analysis of High Dimensional Data
by: Yang, Kai
Published: (2025)

4+3 Phases of Compute-Optimal Neural Scaling Laws
by: Paquette, Elliot, et al.
Published: (2024)

Type-II Saddles and Probabilistic Stability of Stochastic Gradient Descent
by: Ziyin, Liu, et al.
Published: (2023)

Statistical Inference for Linear Functionals of Online SGD in High-dimensional Linear Regression
by: Agrawalla, Bhavya, et al.
Published: (2023)

High-dimensional scaling limits and fluctuations of online least-squares SGD with smooth covariance
by: Balasubramanian, Krishnakumar, et al.
Published: (2023)

Optimal and instance-dependent guarantees for Markovian linear stochastic approximation
by: Mou, Wenlong, et al.
Published: (2021)

High dimensional theory of two-phase optimizers
by: Agarwala, Atish
Published: (2026)

Fast Spawn\&Prune (FS\&P): Global convergence of stochastic conic particle gradient descent via birth/death process
by: De Castro, Yohann, et al.
Published: (2026)

Propagation of Chaos in Contextual Flow Maps
by: Chen, Shi, et al.
Published: (2026)

A mathematical theory for understanding when abstract representations emerge in neural networks
by: Wang, Bin, et al.
Published: (2025)

Statistical limits of correlation detection in trees
by: Ganassali, Luca, et al.
Published: (2022)

Alternating minimization for generalized rank one matrix sensing: Sharp predictions from a random initialization
by: Chandrasekher, Kabir Aladin, et al.
Published: (2022)

Convergence of coordinate ascent variational inference for log-concave measures via optimal transport
by: Arnese, Manuel, et al.
Published: (2024)

A Piecewise Lyapunov Analysis of Sub-quadratic SGD: Applications to Robust and Quantile Regression
by: Zhang, Yixuan, et al.
Published: (2025)

Early Stopping in Contextual Bandits and Inferences
by: Cui, Zihan
Published: (2025)

Orlicz regrets to consistently bound statistics of random variables with an application to environmental indicators
by: Yoshioka, Hidekazu, et al.
Published: (2023)

Statistical guarantees for continuous-time policy evaluation: blessing of ellipticity and new tradeoffs
by: Mou, Wenlong
Published: (2025)

Is RL fine-tuning harder than regression? A PDE learning approach for diffusion models
by: Mou, Wenlong
Published: (2025)

Data efficiency, dimensionality reduction, and the generalized symmetric information bottleneck
by: Martini, K. Michael, et al.
Published: (2023)

Markov Kernels, Distances and Optimal Control: A Parable of Linear Quadratic Non-Gaussian Distribution Steering
by: Teter, Alexis M. H., et al.
Published: (2025)

Convergence rate of random scan Coordinate Ascent Variational Inference under log-concavity
by: Lavenant, Hugo, et al.
Published: (2024)

Efficient Online Learning in Interacting Particle Systems
by: Sharrock, Louis, et al.
Published: (2026)

Non-convex matrix sensing: Breaking the quadratic rank barrier in the sample complexity
by: Stöger, Dominik, et al.
Published: (2024)

Well-posedness and approximation of reflected McKean-Vlasov SDEs with applications
by: Hinds, P. D., et al.
Published: (2024)

Phase transitions reveal hierarchical structure in deep neural networks
by: Ersoy, Ibrahim Talha, et al.
Published: (2025)

Accurate Estimation of Mutual Information in High Dimensional Data
by: Abdelaleem, Eslam, et al.
Published: (2025)

Deep Variational Multivariate Information Bottleneck -- A Framework for Variational Losses
by: Abdelaleem, Eslam, et al.
Published: (2023)

Optimal estimators of cross-partial derivatives and surrogates of functions
by: Lamboni, Matieyendou
Published: (2024)

The Risk Quadrangle in Optimization: An Overview with Recent Results and Extensions
by: Grechuk, Bogdan, et al.
Published: (2026)

Mutual information and task-relevant latent dimensionality
by: Gulati, Paarth, et al.
Published: (2026)

High-dimensional Limit of SGD for Diagonal Linear Networks
by: Malaxechebarría, Begoña García, et al.
Published: (2026)

Non-asymptotic convergence bounds for modified tamed unadjusted Langevin algorithm in non-convex setting
by: Neufeld, Ariel, et al.
Published: (2022)

Surveying the space of descriptions of a composite system with machine learning
by: Murphy, Kieran A., et al.
Published: (2024)

Exploring the Statistical Properties of Outputs from a Process Inspired by Geometrical Interpretation of Newton's Method
by: Kirouani, Taki
Published: (2024)

Marine spatial planning techniques with a case study on wave-powered offshore aquaculture farms
by: Ewig, Gabriel, et al.
Published: (2024)

First-Extinction Law for Resampling Processes
by: Benati, Matteo, et al.
Published: (2025)

Moment-based parameter inference with error guarantees for stochastic reaction networks
by: Li, Zekai, et al.
Published: (2024)

Model orthogonalization and Bayesian forecast mixing via Principal Component Analysis
by: Giuliani, Pablo, et al.
Published: (2024)

Higher order definition of causality by optimally conditioned transfer entropy
by: Kořenek, Jakub, et al.
Published: (2024)

Exploring applications of topological data analysis in stock index movement prediction
by: Huang, Dazhi, et al.
Published: (2024)