Copertina

Type-II Saddles and Probabilistic Stability of Stochastic Gradient Descent

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ziyin, Liu, Li, Botao, Galanti, Tomer, Ueda, Masahito
Natura:	Preprint
Pubblicazione:	2023
Soggetti:	Machine Learning Optimization and Control Data Analysis, Statistics and Probability
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

High dimensional analysis reveals conservative sharpening and a stochastic edge of stability
di: Agarwala, Atish, et al.
Pubblicazione: (2024)

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

Dichotomy of Feature Learning and Unlearning: Fast-Slow Analysis on Neural Networks with Stochastic Gradient Descent
di: Imai, Shota, et al.
Pubblicazione: (2026)

Controlling the Flow: Stability and Convergence for Stochastic Gradient Descent with Decaying Regularization
di: Kassing, Sebastian, et al.
Pubblicazione: (2025)

Algorithmic Stability of Stochastic Gradient Descent with Momentum under Heavy-Tailed Noise
di: Dang, Thanh, et al.
Pubblicazione: (2025)

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

Annealed Stein Variational Gradient Descent for Improved Uncertainty Estimation in Full-Waveform Inversion
di: Corrales, Miguel, et al.
Pubblicazione: (2024)

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

Parameter Symmetry and Noise Equilibrium of Stochastic Gradient Descent
di: Ziyin, Liu, et al.
Pubblicazione: (2024)

The Universe as a Learning System
di: Shushi, Tomer
Pubblicazione: (2024)

Exact Dynamics of Multi-class Stochastic Gradient Descent
di: Collins-Woodfin, Elizabeth, et al.
Pubblicazione: (2025)

Gaussian Approximation and Multiplier Bootstrap for Stochastic Gradient Descent
di: Sheshukova, Marina, et al.
Pubblicazione: (2025)

Probabilistic Emissivity Retrieval from Hyperspectral Data via Physics-Guided Variational Inference
di: Tempelman, Joshua R., et al.
Pubblicazione: (2025)

Stochastic Optimal Control Matching
di: Domingo-Enrich, Carles, et al.
Pubblicazione: (2023)

Probabilistic Guarantees of Stochastic Recursive Gradient in Non-Convex Finite Sum Problems
di: Zhong, Yanjie, et al.
Pubblicazione: (2024)

Stopping Rules for Stochastic Gradient Descent via Anytime-Valid Confidence Sequences
di: Aolaritei, Liviu, et al.
Pubblicazione: (2025)

Probabilistic Spatiotemporal Modeling of Day-Ahead Wind Power Generation with Input-Warped Gaussian Processes
di: Li, Qiqi, et al.
Pubblicazione: (2024)

Stochastic Clock Attention for Aligning Continuous and Ordered Sequences
di: Soh, Hyungjoon, et al.
Pubblicazione: (2025)

Analysing heavy-tail properties of Stochastic Gradient Descent by means of Stochastic Recurrence Equations
di: Damek, Ewa, et al.
Pubblicazione: (2024)

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

Rapid Overfitting of Multi-Pass Stochastic Gradient Descent in Stochastic Convex Optimization
di: Vansover-Hager, Shira, et al.
Pubblicazione: (2025)

Quantifying uncertainty in inverse scattering problems set in layered environments
di: Abugattas, Carolina, et al.
Pubblicazione: (2025)

Flatness-Aware Stochastic Gradient Langevin Dynamics
di: Bruno, Stefano, et al.
Pubblicazione: (2025)

High-probability Convergence Bounds for Nonlinear Stochastic Gradient Descent Under Heavy-tailed Noise
di: Armacki, Aleksandar, et al.
Pubblicazione: (2023)

Stochastic Inference of Plate Bending from Heterogeneous Data: Physics-informed Gaussian Processes via Kirchhoff-Love Theory
di: Kavrakov, Igor, et al.
Pubblicazione: (2024)

A Pipeline for Data-Driven Learning of Topological Features with Applications to Protein Stability Prediction
di: Mishra, Amish, et al.
Pubblicazione: (2024)

Probabilistic Flux Limiters
di: Nguyen-Fotiadis, Nga T. T., et al.
Pubblicazione: (2024)

Actuation manifold from snapshot data
di: Marra, Luigi, et al.
Pubblicazione: (2024)

Tunnelling Through Time Series: A Probabilistic Visibility Graph for Local and Global Pattern Discovery
di: Sotero, Roberto, et al.
Pubblicazione: (2025)

Cryo-EM as a Stochastic Inverse Problem
di: Espinosa, Diego Sanchez, et al.
Pubblicazione: (2025)

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

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

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

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

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

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

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

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

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

Early Stopping in Contextual Bandits and Inferences
di: Cui, Zihan
Pubblicazione: (2025)