Imagen de Portada

Enhancing DP-SGD through Non-monotonous Adaptive Scaling Gradient Weight

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Huang, Tao, Huang, Qingyu, Shi, Xin, Meng, Jiayang, Zheng, Guolong, Yang, Xu, Yi, Xun
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Gradient-Guided Conditional Diffusion Models for Private Image Reconstruction: Analyzing Adversarial Impacts of Differential Privacy and Denoising
por: Huang, Tao, et al.
Publicado: (2024)

Machine Unlearning with Minimal Gradient Dependence for High Unlearning Ratios
por: Huang, Tao, et al.
Publicado: (2024)

Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD
por: Thudi, Anvith, et al.
Publicado: (2023)

Enhanced Privacy Leakage from Noise-Perturbed Gradients via Gradient-Guided Conditional Diffusion Models
por: Meng, Jiayang, et al.
Publicado: (2025)

DP-CSGP: Differentially Private Stochastic Gradient Push with Compressed Communication
por: Zhu, Zehan, et al.
Publicado: (2025)

Have it your way: Individualized Privacy Assignment for DP-SGD
por: Boenisch, Franziska, et al.
Publicado: (2023)

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

XGrad: Boosting Gradient-Based Optimizers With Weight Prediction
por: Guan, Lei, et al.
Publicado: (2023)

Accumulative SGD Influence Estimation for Data Attribution
por: Shi, Yunxiao, et al.
Publicado: (2025)

Real-Time Privacy Risk Measurement with Privacy Tokens for Gradient Leakage
por: Meng, Jiayang, et al.
Publicado: (2025)

Fast and Stable Diffusion Planning through Variational Adaptive Weighting
por: Qiu, Zhiying, et al.
Publicado: (2025)

Technical Report: Full Version of Analyzing and Optimizing Perturbation of DP-SGD Geometrically
por: Duan, Jiawei, et al.
Publicado: (2025)

DP-aware AdaLN-Zero: Taming Conditioning-Induced Heavy-Tailed Gradients in Differentially Private Diffusion
por: Huang, Tao, et al.
Publicado: (2026)

Adaptive Batch Sizes Using Non-Euclidean Gradient Noise Scales for Stochastic Sign and Spectral Descent
por: Naganuma, Hiroki, et al.
Publicado: (2026)

Anon: Extrapolating Adaptivity Beyond SGD and Adam
por: Zhang, Yiheng, et al.
Publicado: (2026)

Scaling Laws of SignSGD in Linear Regression: When Does It Outperform SGD?
por: Kim, Jihwan, et al.
Publicado: (2026)

TS-DP: Reinforcement Speculative Decoding For Temporal Adaptive Diffusion Policy Acceleration
por: Li, Ye, et al.
Publicado: (2025)

From SGD to Muon: Adaptive Optimization via Schatten-p Norms
por: Massena, Thomas, et al.
Publicado: (2026)

Intermediate Outputs Are More Sensitive Than You Think
por: Huang, Tao, et al.
Publicado: (2024)

DP$^2$-NILM: A Distributed and Privacy-preserving Framework for Non-intrusive Load Monitoring
por: Dai, Shuang, et al.
Publicado: (2022)

Overcoming Non-monotonicity in Transducer-based Streaming Generation
por: Ma, Zhengrui, et al.
Publicado: (2024)

Diagonalisation SGD: Fast & Convergent SGD for Non-Differentiable Models via Reparameterisation and Smoothing
por: Wagner, Dominik, et al.
Publicado: (2024)

UniScale: Adaptive Unified Inference Scaling via Online Joint Optimization of Model Routing and Test-Time Scaling
por: Huang, Kaiyu, et al.
Publicado: (2026)

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

TimeDP: Learning to Generate Multi-Domain Time Series with Domain Prompts
por: Huang, Yu-Hao, et al.
Publicado: (2025)

EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba
por: Pei, Xiaohuan, et al.
Publicado: (2024)

Be More Real: Travel Diary Generation Using LLM Agents and Individual Profiles
por: Li, Xuchuan, et al.
Publicado: (2024)

LLM-AutoDP: Automatic Data Processing via LLM Agents for Model Fine-tuning
por: Huang, Wei, et al.
Publicado: (2026)

Adaptive Optimization for Enhanced Efficiency in Large-Scale Language Model Training
por: Chen, Jiajing, et al.
Publicado: (2024)

IntentionReasoner: Facilitating Adaptive LLM Safeguards through Intent Reasoning and Selective Query Refinement
por: Shen, Yuanzhe, et al.
Publicado: (2025)

Stochastic Collapse: How Gradient Noise Attracts SGD Dynamics Towards Simpler Subnetworks
por: Chen, Feng, et al.
Publicado: (2023)

Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement
por: Huang, Zhehao, et al.
Publicado: (2024)

LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration
por: Zhao, Jun, et al.
Publicado: (2024)

Gradient Weight-normalized Low-rank Projection for Efficient LLM Training
por: Huang, Jia-Hong, et al.
Publicado: (2024)

Emotional RAG: Enhancing Role-Playing Agents through Emotional Retrieval
por: Huang, Le, et al.
Publicado: (2024)

Minibatch and Local SGD: Algorithmic Stability and Linear Speedup in Generalization
por: Lei, Yunwen, et al.
Publicado: (2023)

GADT: Enhancing Transferable Adversarial Attacks through Gradient-guided Adversarial Data Transformation
por: Ma, Yating, et al.
Publicado: (2024)

Rethinking RoPE Scaling in Quantized LLM: Theory, Outlier, and Channel-Band Analysis with Weight Rescaling
por: Qiao, Ye, et al.
Publicado: (2025)

Grams: Gradient Descent with Adaptive Momentum Scaling
por: Cao, Yang, et al.
Publicado: (2024)

TrajGEOS: Trajectory Graph Enhanced Orientation-based Sequential Network for Mobility Prediction
por: Hu, Zhaoping, et al.
Publicado: (2024)