Cover Image

DP-SGD-Global-Adapt-V2-S: Triad Improvements of Privacy, Accuracy and Fairness via Step Decay Noise Multiplier and Step Decay Upper Clipping Threshold

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chilukoti, Sai Venkatesh, Hossen, Md Imran, Shan, Liqun, Tida, Vijay Srinivas, Bappy, Mahathir Mohammad, Tian, Wenmeng, Hei, Xiai
Format:	Preprint
Published:	2023
Subjects:	Machine Learning Cryptography and Security 26, 40
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Facebook Report on Privacy of fNIRS data
by: Hossen, Md Imran, et al.
Published: (2024)

Differentially private fine-tuned NF-Net to predict GI cancer type
by: Chilukoti, Sai Venkatesh, et al.
Published: (2025)

Unified Kernel-Segregated Transpose Convolution Operation
by: Tida, Vijay Srinivas, et al.
Published: (2025)

Double Backdoored: Converting Code Large Language Model Backdoors to Traditional Malware via Adversarial Instruction Tuning Attacks
by: Hossen, Md Imran, et al.
Published: (2024)

A Unified Training Process for Fake News Detection based on Fine-Tuned BERT Model
by: Tida, Vijay Srinivas, et al.
Published: (2022)

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

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

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

On the Adversarial Robustness of Instruction-Tuned Large Language Models for Code
by: Hossen, Md Imran, et al.
Published: (2024)

MHDash: An Online Platform for Benchmarking Mental Health-Aware AI Assistants
by: Zhang, Yihe, et al.
Published: (2026)

Step-Size Decay and Structural Stagnation in Greedy Sparse Learning
by: Berná, Pablo M.
Published: (2026)

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

ThermoCAPTCHA: Privacy-Preserving Human Verification with Farm-Resistant Traceable Tokens
by: Paul, Shovon, et al.
Published: (2026)

The Power of Decaying Steps: Enhancing Attack Stability and Transferability for Sign-based Optimizers
by: Tao, Wei, et al.
Published: (2026)

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

SGD and Weight Decay Secretly Minimize the Rank of Your Neural Network
by: Galanti, Tomer, et al.
Published: (2022)

DP-SGD with weight clipping
by: Barczewski, Antoine, et al.
Published: (2023)

Revisiting the Geometrically Decaying Step Size: Linear Convergence for Smooth or Non-Smooth Functions
by: Kim, Jihun
Published: (2025)

Bayesian Optimistic Optimisation with Exponentially Decaying Regret
by: Tran-The, Hung, et al.
Published: (2021)

Steps Adaptive Decay DPSGD: Enhancing Performance on Imbalanced Datasets with Differential Privacy with HAM10000
by: Huang, Xiaobo, et al.
Published: (2025)

Balls-and-Bins Sampling for DP-SGD
by: Chua, Lynn, et al.
Published: (2024)

How Private are DP-SGD Implementations?
by: Chua, Lynn, et al.
Published: (2024)

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

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

Proactive DP: A Multple Target Optimization Framework for DP-SGD
by: van Dijk, Marten, et al.
Published: (2021)

In Reference to Step‐By‐Step Surgery for Diffuse Idiopathic Skeletal Hyperostosis ( DISH ) of the Cervical Spine
by: Ali Imran Ozmarasali, et al.
Published: (2025)

Chain-of-Probe: Examining the Necessity and Accuracy of CoT Step-by-Step
by: Wang, Zezhong, et al.
Published: (2024)

Trade-off Functions for DP-SGD with Subsampling based on Random Shuffling: Tight Upper and Lower Bounds
by: van Dijk, Marten, et al.
Published: (2026)

To Shuffle or not to Shuffle: Auditing DP-SGD with Shuffling
by: Annamalai, Meenatchi Sundaram Muthu Selva, et al.
Published: (2024)

Feature-Aware Anisotropic Local Differential Privacy for Utility-Preserving Graph Representation Learning in Metal Additive Manufacturing
by: Islam, MD Shafikul, et al.
Published: (2026)

Exploring Possibilities of AI-Powered Legal Assistance in Bangladesh through Large Language Modeling
by: Wasi, Azmine Toushik, et al.
Published: (2024)

FlashDP: Private Training Large Language Models with Efficient DP-SGD
by: Wang, Liangyu, et al.
Published: (2025)

QueryGym: Step-by-Step Interaction with Relational Databases
by: Ananthakrishnan, Haritha, et al.
Published: (2025)

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

When Scaling Fails: Mitigating Audio Perception Decay of LALMs via Multi-Step Perception-Aware Reasoning
by: Mao, Ruixiang, et al.
Published: (2026)

Remember Me: Bridging the Long-Range Gap in LVLMs with Three-Step Inference-Only Decay Resilience Strategies
by: Gao, Peng, et al.
Published: (2025)

Step-by-Step Data Cleaning Recommendations to Improve ML Prediction Accuracy
by: Mohammed, Sedir, et al.
Published: (2025)

DP-AdamW: Investigating Decoupled Weight Decay and Bias Correction in Private Deep Learning
by: Chooi, Jay, et al.
Published: (2025)

AdaptViG: Adaptive Vision GNN with Exponential Decay Gating
by: Munir, Mustafa, et al.
Published: (2025)

Last-Iterate Convergence of Randomized Kaczmarz and SGD with Greedy Step Size
by: Dereziński, Michał, et al.
Published: (2026)