Imagen de Portada

Near-Optimal Streaming Heavy-Tailed Statistical Estimation with Clipped SGD

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Das, Aniket, Nagaraj, Dheeraj, Pal, Soumyabrata, Suggala, Arun, Varshney, Prateek
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Regret minimization in Linear Bandits with offline data via extended D-optimal exploration
por: Vijayan, Sushant, et al.
Publicado: (2025)

Stochastic Re-weighted Gradient Descent via Distributionally Robust Optimization
por: Kumar, Ramnath, et al.
Publicado: (2023)

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

Online Matrix Completion: A Collaborative Approach with Hott Items
por: Baby, Dheeraj, et al.
Publicado: (2024)

Privacy of SGD under Gaussian or Heavy-Tailed Noise: Guarantees without Gradient Clipping
por: Şimşekli, Umut, et al.
Publicado: (2024)

Revisiting Gradient Normalization and Clipping for Nonconvex SGD under Heavy-Tailed Noise: Necessity, Sufficiency, and Acceleration
por: Sun, Tao, et al.
Publicado: (2024)

Convergence of Clipped-SGD for Convex $(L_0,L_1)$-Smooth Optimization with Heavy-Tailed Noise
por: Chezhegov, Savelii, et al.
Publicado: (2025)

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

To Clip or not to Clip: the Dynamics of SGD with Gradient Clipping in High-Dimensions
por: Marshall, Noah, et al.
Publicado: (2024)

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

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

Clip Body and Tail Separately: High Probability Guarantees for DPSGD with Heavy Tails
por: Sha, Haichao, et al.
Publicado: (2024)

Nonconvex Stochastic Optimization under Heavy-Tailed Noises: Optimal Convergence without Gradient Clipping
por: Liu, Zijian, et al.
Publicado: (2024)

Offline-to-online hyperparameter transfer for stochastic bandits
por: Sharma, Dravyansh, et al.
Publicado: (2025)

Robust Federated Learning Over the Air: Combating Heavy-Tailed Noise with Median Anchored Clipping
por: Li, Jiaxing, et al.
Publicado: (2024)

The Poisson Midpoint Method for Langevin Dynamics: Provably Efficient Discretization for Diffusion Models
por: Kandasamy, Saravanan, et al.
Publicado: (2024)

Implicit Compressibility of Overparametrized Neural Networks Trained with Heavy-Tailed SGD
por: Wan, Yijun, et al.
Publicado: (2023)

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

Finite time analysis of temporal difference learning with linear function approximation: Tail averaging and regularisation
por: Patil, Gandharv, et al.
Publicado: (2022)

DC-SGD: Differentially Private SGD with Dynamic Clipping through Gradient Norm Distribution Estimation
por: Wei, Chengkun, et al.
Publicado: (2025)

Poisson Midpoint Method for Log Concave Sampling: Beyond the Strong Error Lower Bounds
por: Srinivasan, Rishikesh, et al.
Publicado: (2025)

Tractable Gaussian Phase Retrieval with Heavy Tails and Adversarial Corruption with Near-Linear Sample Complexity
por: Das, Santanu, et al.
Publicado: (2026)

Interleaved Gibbs Diffusion: Generating Discrete-Continuous Data with Implicit Constraints
por: Anil, Gautham Govind, et al.
Publicado: (2025)

GeoClip: Geometry-Aware Clipping for Differentially Private SGD
por: Gilani, Atefeh, et al.
Publicado: (2025)

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

On the Convergence of DP-SGD with Adaptive Clipping
por: Shulgin, Egor, et al.
Publicado: (2024)

Differentially Private Clipped-SGD: High-Probability Convergence with Arbitrary Clipping Level
por: Khah, Saleh Vatan, et al.
Publicado: (2025)

Data-Driven Upper Confidence Bounds with Near-Optimal Regret for Heavy-Tailed Bandits
por: Tamás, Ambrus, et al.
Publicado: (2024)

Glauber Generative Model: Discrete Diffusion Models via Binary Classification
por: Varma, Harshit, et al.
Publicado: (2024)

Convex Distillation: Efficient Compression of Deep Networks via Convex Optimization
por: Varshney, Prateek, et al.
Publicado: (2024)

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

Clipped SGD Algorithms for Performative Prediction: Tight Bounds for Clipping Bias and Remedies
por: Li, Qiang, et al.
Publicado: (2024)

CDQuant: Greedy Coordinate Descent for Accurate LLM Quantization
por: Nair, Pranav Ajit, et al.
Publicado: (2024)

Improving Generalization via Meta-Learning on Hard Samples
por: Jain, Nishant, et al.
Publicado: (2024)

Second-order Optimization under Heavy-Tailed Noise: Hessian Clipping and Sample Complexity Limits
por: Sadiev, Abdurakhmon, et al.
Publicado: (2025)

Dimension-free Score Matching and Time Bootstrapping for Diffusion Models
por: Kumar, Syamantak, et al.
Publicado: (2025)

Sharp High-Probability Rates for Nonlinear SGD under Heavy-Tailed Noise via Symmetrization
por: Armacki, Aleksandar, et al.
Publicado: (2025)

DP-SGD Without Clipping: The Lipschitz Neural Network Way
por: Bethune, Louis, et al.
Publicado: (2023)

Clipped Gradient Methods for Nonsmooth Convex Optimization under Heavy-Tailed Noise: A Refined Analysis
por: Liu, Zijian
Publicado: (2025)

Second Order Methods for Bandit Optimization and Control
por: Suggala, Arun, et al.
Publicado: (2024)