Copertina

Subsampled Ensemble Can Improve Generalization Tail Exponentially

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Qian, Huajie, Ying, Donghao, Lam, Henry, Yin, Wotao
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Optimization and Control Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Learning to optimize: A tutorial for continuous and mixed-integer optimization
di: Chen, Xiaohan, et al.
Pubblicazione: (2024)

Expressive Power of Graph Neural Networks for (Mixed-Integer) Quadratic Programs
di: Chen, Ziang, et al.
Pubblicazione: (2024)

Rethinking the Capacity of Graph Neural Networks for Branching Strategy
di: Chen, Ziang, et al.
Pubblicazione: (2024)

Unified Convergence Analysis for Adaptive Optimization with Moving Average Estimator
di: Guo, Zhishuai, et al.
Pubblicazione: (2021)

Can SGD Handle Heavy-Tailed Noise?
di: Fatkhullin, Ilyas, et al.
Pubblicazione: (2025)

A Sketch-and-Project Analysis of Subsampled Natural Gradient Algorithms
di: Goldshlager, Gil, et al.
Pubblicazione: (2025)

Optimizer's Information Criterion: Dissecting and Correcting Bias in Data-Driven Optimization
di: Iyengar, Garud, et al.
Pubblicazione: (2023)

Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed
di: Chezhegov, Savelii, et al.
Pubblicazione: (2024)

Can Adaptive Gradient Methods Converge under Heavy-Tailed Noise? A Case Study of AdaGrad
di: Liu, Zijian
Pubblicazione: (2026)

LLM Embeddings Improve Test-time Adaptation to Tabular $Y|X$-Shifts
di: Zeng, Yibo, et al.
Pubblicazione: (2024)

Efficient Tail-Aware Generative Optimization via Flow Model Fine-Tuning
di: Wang, Zifan, et al.
Pubblicazione: (2026)

Convergence Analysis of Stochastic Gradient Descent with MCMC Estimators
di: Li, Tianyou, et al.
Pubblicazione: (2023)

Lower Bounds and Accelerated Algorithms in Distributed Stochastic Optimization with Communication Compression
di: He, Yutong, et al.
Pubblicazione: (2023)

Policy-based Primal-Dual Methods for Concave CMDP with Variance Reduction
di: Ying, Donghao, et al.
Pubblicazione: (2022)

Solving General Natural-Language-Description Optimization Problems with Large Language Models
di: Zhang, Jihai, et al.
Pubblicazione: (2024)

Exponential Concentration in Stochastic Approximation
di: Law, Kody, et al.
Pubblicazione: (2022)

Heavy-Tail Phenomenon in Decentralized SGD
di: Gurbuzbalaban, Mert, et al.
Pubblicazione: (2022)

Optimal Transport with Tempered Exponential Measures
di: Amid, Ehsan, et al.
Pubblicazione: (2023)

Tail Distribution of Regret in Optimistic Reinforcement Learning
di: Khodadadian, Sajad, et al.
Pubblicazione: (2025)

Concentration of General Stochastic Approximation Under Heavy-Tailed Markovian Noise
di: Agrawal, Shubhada, et al.
Pubblicazione: (2026)

From Gradient Clipping to Normalization for Heavy Tailed SGD
di: Hübler, Florian, et al.
Pubblicazione: (2024)

Stochastic Weakly Convex Optimization Under Heavy-Tailed Noises
di: Zhu, Tianxi, et al.
Pubblicazione: (2025)

Exponential Convergence of (Stochastic) Gradient Descent for Separable Logistic Regression
di: Kale, Sacchit, et al.
Pubblicazione: (2026)

Near-Optimal Decentralized Stochastic Nonconvex Optimization with Heavy-Tailed Noise
di: Wang, Menglian, et al.
Pubblicazione: (2026)

Optimal Asynchronous Stochastic Nonconvex Optimization under Heavy-Tailed Noise
di: Wu, Yidong, et al.
Pubblicazione: (2026)

In-Expectation Convergence of Stochastic Gradient Methods under Heavy-Tailed Noise
di: Liu, Zijian
Pubblicazione: (2026)

Efficient Private SCO for Heavy-Tailed Data via Averaged Clipping
di: Jin, Chenhan, et al.
Pubblicazione: (2022)

Achieving Margin Maximization Exponentially Fast via Progressive Norm Rescaling
di: Wang, Mingze, et al.
Pubblicazione: (2023)

PACE: Prune-And-Compress Ensemble Models
di: Akkerman, Fabian, et al.
Pubblicazione: (2026)

Tight Long-Term Tail Decay of (Clipped) SGD in Non-Convex Optimization
di: Armacki, Aleksandar, et al.
Pubblicazione: (2026)

Online Convex Optimization with Heavy Tails: Old Algorithms, New Regrets, and Applications
di: Liu, Zijian
Pubblicazione: (2025)

Scale-Invariant Neural Network Optimization: Norm Geometry and Heavy-Tailed Noise
di: Zhang, Jiayu, et al.
Pubblicazione: (2026)

Muon with Nesterov Momentum: Heavy-Tailed Noise and (Randomized) Inexact Polar Decomposition
di: Choudhury, Sayantan, et al.
Pubblicazione: (2026)

Exponentially Weighted Algorithm for Online Network Resource Allocation with Long-Term Constraints
di: Sid-Ali, Ahmed, et al.
Pubblicazione: (2024)

Beyond the Bellman Recursion: A Pontryagin-Guided Framework for Non-Exponential Discounting
di: Ko, Hojin, et al.
Pubblicazione: (2026)

Understanding SGD with Exponential Moving Average: A Case Study in Linear Regression
di: Li, Xuheng, et al.
Pubblicazione: (2025)

Operator Splitting for Learning to Predict Equilibria in Convex Games
di: McKenzie, Daniel, et al.
Pubblicazione: (2021)

High Probability Complexity Bounds for Non-Smooth Stochastic Optimization with Heavy-Tailed Noise
di: Gorbunov, Eduard, et al.
Pubblicazione: (2021)

Improving Generalization and Convergence by Enhancing Implicit Regularization
di: Wang, Mingze, et al.
Pubblicazione: (2024)

Empirical Risk Minimization with Shuffled SGD: A Primal-Dual Perspective and Improved Bounds
di: Cai, Xufeng, et al.
Pubblicazione: (2023)