Copertina

A Piecewise Lyapunov Analysis of Sub-quadratic SGD: Applications to Robust and Quantile Regression

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhang, Yixuan, Huo, Dongyan, Chen, Yudong, Xie, Qiaomin
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Optimization and Control Probability Statistics Theory
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

The Collusion of Memory and Nonlinearity in Stochastic Approximation With Constant Stepsize
di: Huo, Dongyan, et al.
Pubblicazione: (2024)

Prelimit Coupling and Steady-State Convergence of Constant-stepsize Nonsmooth Contractive SA
di: Zhang, Yixuan, et al.
Pubblicazione: (2024)

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

Bias and Extrapolation in Markovian Linear Stochastic Approximation with Constant Stepsizes
di: Huo, Dongyan, et al.
Pubblicazione: (2022)

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

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

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)

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)

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

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

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

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

Wasserstein Distributionally Robust Quantile Regression
di: Zhang, Chunxu, et al.
Pubblicazione: (2026)

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

Piecewise Polynomial Regression of Tame Functions via Integer Programming
di: Bareilles, Gilles, et al.
Pubblicazione: (2023)

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

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

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

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

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

Constant Stepsize Q-learning: Distributional Convergence, Bias and Extrapolation
di: Zhang, Yixuan, et al.
Pubblicazione: (2024)

Achieving Exponential Asymptotic Optimality in Average-Reward Restless Bandits without Global Attractor Assumption
di: Hong, Yige, et al.
Pubblicazione: (2024)

Restless Bandits with Average Reward: Breaking the Uniform Global Attractor Assumption
di: Hong, Yige, et al.
Pubblicazione: (2023)

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

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

Wasserstein Distributionally Robust Optimization with Heterogeneous Data Sources
di: Rychener, Yves, et al.
Pubblicazione: (2024)

New algorithms for sampling and diffusion models
di: Zhang, Xicheng
Pubblicazione: (2024)

Efficient Group Lasso Regularized Rank Regression with Data-Driven Parameter Determination
di: Lin, Meixia, et al.
Pubblicazione: (2025)

Piecewise Linearity of Min-Norm Solution Map of a Nonconvexly Regularized Convex Sparse Model
di: Zhang, Yi, et al.
Pubblicazione: (2023)

Convergence of SGD for Training Neural Networks with Sliced Wasserstein Losses
di: Tanguy, Eloi
Pubblicazione: (2023)

On Regularization via Early Stopping for Least Squares Regression
di: Sonthalia, Rishi, et al.
Pubblicazione: (2024)

Central limit theorems for vector-valued composite functionals with smoothing and applications
di: Chen, Huihui, et al.
Pubblicazione: (2024)

Two-Timescale Linear Stochastic Approximation: Constant Stepsizes Go a Long Way
di: Kwon, Jeongyeol, et al.
Pubblicazione: (2024)

Decentralized Sparse Linear Regression via Gradient-Tracking: Linear Convergence and Statistical Guarantees
di: Maros, Marie, et al.
Pubblicazione: (2022)

Sharp Rates of MMD Empirical Estimation with Power Kernels
di: Colasanto, Francesco, et al.
Pubblicazione: (2026)

Optimal transport and Wasserstein distances for causal models
di: Cheridito, Patrick, et al.
Pubblicazione: (2023)