Imagen de Portada

DPZero: Private Fine-Tuning of Language Models without Backpropagation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Liang, Li, Bingcong, Thekumparampil, Kiran Koshy, Oh, Sewoong, He, Niao
Formato:	Preprint
Publicado:	2023
Materias:	Machine Learning Cryptography and Security Optimization and Control
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Zeroth-Order Optimization Finds Flat Minima
por: Zhang, Liang, et al.
Publicado: (2025)

Characterizing the Training Dynamics of Private Fine-tuning with Langevin diffusion
por: Ke, Shuqi, et al.
Publicado: (2024)

ConMeZO: Adaptive Descent-Direction Sampling for Gradient-Free Finetuning of Large Language Models
por: Behric, Lejs Deen, et al.
Publicado: (2025)

On the Gradient Complexity of Private Optimization with Private Oracles
por: Menart, Michael, et al.
Publicado: (2025)

Optimal Differentially Private Model Training with Public Data
por: Lowy, Andrew, et al.
Publicado: (2023)

Zeroth-Order Optimization at the Edge of Stability
por: Song, Minhak, et al.
Publicado: (2026)

Private Zeroth-Order Nonsmooth Nonconvex Optimization
por: Zhang, Qinzi, et al.
Publicado: (2024)

Differentially Private Bilevel Optimization
por: Kornowski, Guy
Publicado: (2024)

How to Make the Gradients Small Privately: Improved Rates for Differentially Private Non-Convex Optimization
por: Lowy, Andrew, et al.
Publicado: (2024)

Differentially Private Random Block Coordinate Descent
por: Maranjyan, Artavazd, et al.
Publicado: (2024)

Improved Sample Complexity for Private Nonsmooth Nonconvex Optimization
por: Kornowski, Guy, et al.
Publicado: (2024)

Distributed Online Private Learning of Convex Nondecomposable Objectives
por: Cheng, Huqiang, et al.
Publicado: (2022)

The Relative Gaussian Mechanism and its Application to Private Gradient Descent
por: Hendrikx, Hadrien, et al.
Publicado: (2023)

The Power of Sampling: Dimension-free Risk Bounds in Private ERM
por: Lee, Yin Tat, et al.
Publicado: (2021)

Public-data Assisted Private Stochastic Optimization: Power and Limitations
por: Ullah, Enayat, et al.
Publicado: (2024)

Private Stochastic Optimization With Large Worst-Case Lipschitz Parameter
por: Lowy, Andrew, et al.
Publicado: (2022)

Faster Algorithms for User-Level Private Stochastic Convex Optimization
por: Lowy, Andrew, et al.
Publicado: (2024)

Byzantine-Robust and Differentially Private Federated Optimization under Weaker Assumptions
por: Islamov, Rustem, et al.
Publicado: (2026)

Differentially Private Bilevel Optimization: Efficient Algorithms with Near-Optimal Rates
por: Lowy, Andrew, et al.
Publicado: (2025)

Differentially Private Non-Convex Optimization under the KL Condition with Optimal Rates
por: Menart, Michael, et al.
Publicado: (2023)

Private Algorithms for Stochastic Saddle Points and Variational Inequalities: Beyond Euclidean Geometry
por: Bassily, Raef, et al.
Publicado: (2024)

Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Losses
por: Lowy, Andrew, et al.
Publicado: (2021)

Differentially Private High Dimensional Bandits
por: Shukla, Apurv
Publicado: (2024)

Mirror Descent Algorithms with Nearly Dimension-Independent Rates for Differentially-Private Stochastic Saddle-Point Problems
por: González, Tomás, et al.
Publicado: (2024)

Private Heterogeneous Federated Learning Without a Trusted Server Revisited: Error-Optimal and Communication-Efficient Algorithms for Convex Losses
por: Gao, Changyu, et al.
Publicado: (2024)

Securing Multi-Agent Systems Against Corruptions via Node Contribution Backpropagation
por: Wu, Chengcan, et al.
Publicado: (2025)

Secure LLM Fine-Tuning via Safety-Aware Probing
por: Wu, Chengcan, et al.
Publicado: (2025)

Correlated Noise Provably Beats Independent Noise for Differentially Private Learning
por: Choquette-Choo, Christopher A., et al.
Publicado: (2023)

Scalable Neural Network Verification with Branch-and-bound Inferred Cutting Planes
por: Zhou, Duo, et al.
Publicado: (2024)

Differential Privacy for Euclidean Jordan Algebra with Applications to Private Symmetric Cone Programming
por: Song, Zhao, et al.
Publicado: (2025)

Private Online Learning via Lazy Algorithms
por: Asi, Hilal, et al.
Publicado: (2024)

Differential Privacy via Distributionally Robust Optimization
por: Selvi, Aras, et al.
Publicado: (2023)

Attention-Enhanced Graph Filtering for False Data Injection Attack Detection and Localization
por: Abdulin, Ruslan, et al.
Publicado: (2026)

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

Kernel Learning with Adversarial Features: Numerical Efficiency and Adaptive Regularization
por: Ribeiro, Antônio H., et al.
Publicado: (2025)

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

The Utility and Complexity of in- and out-of-Distribution Machine Unlearning
por: Allouah, Youssef, et al.
Publicado: (2024)

Efficient Optimization Algorithms for Linear Adversarial Training
por: RIbeiro, Antônio H., et al.
Publicado: (2024)

On the Benefits of Weight Normalization for Overparameterized Matrix Sensing
por: Wei, Yudong, et al.
Publicado: (2025)

On the Crucial Role of Initialization for Matrix Factorization
por: Li, Bingcong, et al.
Publicado: (2024)