Imagen de Portada

Noise is All You Need: Private Second-Order Convergence of Noisy SGD

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Avdiukhin, Dmitrii, Dinitz, Michael, Fan, Chenglin, Yaroslavtsev, Grigory
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

Finding Differentially Private Second Order Stationary Points in Stochastic Minimax Optimization
por: Xu, Difei, et al.
Publicado: (2026)

Implicit Bias in Noisy-SGD: With Applications to Differentially Private Training
por: Sander, Tom, et al.
Publicado: (2024)

PCDP-SGD: Improving the Convergence of Differentially Private SGD via Projection in Advance
por: Sha, Haichao, et al.
Publicado: (2023)

RQP-SGD: Differential Private Machine Learning through Noisy SGD and Randomized Quantization
por: Feng, Ce, et al.
Publicado: (2024)

Convergent Privacy Loss of Noisy-SGD without Convexity and Smoothness
por: Chien, Eli, et al.
Publicado: (2024)

Second-Order Convergence in Private Stochastic Non-Convex Optimization
por: Tao, Youming, et al.
Publicado: (2025)

DP-Muon: Differentially Private Optimization via Matrix-Orthogonalized Momentum
por: Kim, Jihwan, et al.
Publicado: (2026)

Federated Learning Clients Clustering with Adaptation to Data Drifts
por: Li, Minghao, et al.
Publicado: (2024)

Accuracy is Not All You Need
por: Dutta, Abhinav, et al.
Publicado: (2024)

Diffusion Models under Alternative Noise: Simplified Analysis and Sensitivity
por: Choi, Juhyeok, et al.
Publicado: (2025)

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

Attention is All You Need Until You Need Retention
por: Yaslioglu, M. Murat
Publicado: (2025)

Data Deletion for Linear Regression with Noisy SGD
por: Xia, Zhangjie, et al.
Publicado: (2024)

VAMO: Efficient Zeroth-Order Variance Reduction for SGD with Faster Convergence
por: Chen, Jiahe, et al.
Publicado: (2025)

Context is All You Need
por: Delanois, Jean Erik, et al.
Publicado: (2026)

A Generalized Binary Tree Mechanism for Differentially Private Approximation of All-Pair Distances
por: Dinitz, Michael, et al.
Publicado: (2025)

Attention Is All You Need But You Don't Need All Of It For Inference of Large Language Models
por: Tyukin, Georgy, et al.
Publicado: (2024)

Ski Rental with Distributional Predictions of Unknown Quality
por: Cui, Qiming, et al.
Publicado: (2026)

One Good Source is All You Need: Near-Optimal Regret for Bandits under Heterogeneous Noise
por: Bhat, Amith, et al.
Publicado: (2026)

CAMformer: Associative Memory is All You Need
por: Molom-Ochir, Tergel, et al.
Publicado: (2025)

Top-$nσ$: Not All Logits Are You Need
por: Tang, Chenxia, et al.
Publicado: (2024)

Some Attention is All You Need for Retrieval
por: Michalak, Felix, et al.
Publicado: (2025)

Half Search Space is All You Need
por: Rumiantsev, Pavel, et al.
Publicado: (2025)

Multistep Inverse Is Not All You Need
por: Levine, Alexander, et al.
Publicado: (2024)

Exploitation Is All You Need... for Exploration
por: Rentschler, Micah, et al.
Publicado: (2025)

Simple Feedfoward Neural Networks are Almost All You Need for Time Series Forecasting
por: Sun, Fan-Keng, et al.
Publicado: (2025)

Cross-Validation Is All You Need: A Statistical Approach To Label Noise Estimation
por: Chen, Jianan, et al.
Publicado: (2023)

On the Second-Order Convergence of Biased Policy Gradient Algorithms
por: Mu, Siqiao, et al.
Publicado: (2023)

Support is All You Need for Certified VAE Training
por: Xu, Changming, et al.
Publicado: (2025)

MoE Lens -- An Expert Is All You Need
por: Chaudhari, Marmik, et al.
Publicado: (2026)

Fusion or Confusion? Multimodal Complexity Is Not All You Need
por: Rheude, Tillmann, et al.
Publicado: (2025)

Realizable Learning is All You Need
por: Hopkins, Max, et al.
Publicado: (2021)

Cooperation Is All You Need
por: Adeel, Ahsan, et al.
Publicado: (2023)

Private and Fair Machine Learning: Revisiting the Disparate Impact of Differentially Private SGD
por: Demelius, Lea, et al.
Publicado: (2025)

Convergence Analysis of SGD under Expected Smoothness
por: Kawamoto, Yuta, et al.
Publicado: (2025)

All You Need Is Synthetic Task Augmentation
por: Godin, Guillaume
Publicado: (2025)

Element-wise Attention Is All You Need
por: Feng, Guoxin
Publicado: (2025)

Differentially Private Algorithms for Graph Cuts: A Shifting Mechanism Approach and More
por: Chandra, Rishi, et al.
Publicado: (2024)

More Agents Is All You Need
por: Li, Junyou, et al.
Publicado: (2024)

Alignment with Preference Optimization Is All You Need for LLM Safety
por: Alami, Reda, et al.
Publicado: (2024)