Image de couverture de livre

Enabling Differentially Private Federated Learning for Speech Recognition: Benchmarks, Adaptive Optimizers and Gradient Clipping

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Pelikan, Martin, Azam, Sheikh Shams, Feldman, Vitaly, Silovsky, Jan "Honza", Talwar, Kunal, Brinton, Christopher G., Likhomanenko, Tatiana
Format:	Preprint
Publié:	2023
Sujets:	Machine Learning Cryptography and Security
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Instance-Optimality for Private KL Distribution Estimation
par: Ye, Jiayuan, et autres
Publié: (2025)

Instance-Optimal Private Density Estimation in the Wasserstein Distance
par: Feldman, Vitaly, et autres
Publié: (2024)

Cram Less to Fit More: Training Data Pruning Improves Memorization of Facts
par: Ye, Jiayuan, et autres
Publié: (2026)

PREAMBLE: Private and Efficient Aggregation via Block Sparse Vectors
par: Asi, Hilal, et autres
Publié: (2025)

Local Pan-Privacy for Federated Analytics
par: Feldman, Vitaly, et autres
Publié: (2025)

Privacy-Computation trade-offs in Private Repetition and Metaselection
par: Talwar, Kunal
Publié: (2024)

Adaptive Batch Size for Privately Finding Second-Order Stationary Points
par: Liu, Daogao, et autres
Publié: (2024)

Private Vector Mean Estimation in the Shuffle Model: Optimal Rates Require Many Messages
par: Asi, Hilal, et autres
Publié: (2024)

Fingerprinting Codes Meet Geometry: Improved Lower Bounds for Private Query Release and Adaptive Data Analysis
par: Lyu, Xin, et autres
Publié: (2024)

Omni-Router: Sharing Routing Decisions in Sparse Mixture-of-Experts for Speech Recognition
par: Gu, Zijin, et autres
Publié: (2025)

PAC-DP: Personalized Adaptive Clipping for Differentially Private Federated Learning
par: Zhou, Hao, et autres
Publié: (2026)

Faster Rates for Private Adversarial Bandits
par: Asi, Hilal, et autres
Publié: (2025)

Differentially-Private Multi-Tier Federated Learning
par: Chen, Evan, et autres
Publié: (2024)

Beyond the Labels: Unveiling Text-Dependency in Paralinguistic Speech Recognition Datasets
par: Pešán, Jan, et autres
Publié: (2024)

Improved Sample Complexity for Private Nonsmooth Nonconvex Optimization
par: Kornowski, Guy, et autres
Publié: (2024)

On Privately Estimating a Single Parameter
par: Asi, Hilal, et autres
Publié: (2025)

Adaptive Gradient Clipping for Robust Federated Learning
par: Allouah, Youssef, et autres
Publié: (2024)

DP-LAC: Lightweight Adaptive Clipping for Differentially Private Federated Fine-tuning of Language Models
par: Mehmood, Haaris, et autres
Publié: (2026)

Private Online Learning via Lazy Algorithms
par: Asi, Hilal, et autres
Publié: (2024)

Differentially-Private Multi-Tier Federated Learning: A Formal Analysis and Evaluation
par: Chen, Evan, et autres
Publié: (2025)

Communication-Efficient and Differentially Private Vertical Federated Learning with Zeroth-Order Optimization
par: Zhang, Jianing, et autres
Publié: (2025)

Gradient Correction in Federated Learning with Adaptive Optimization
par: Chen, Evan, et autres
Publié: (2025)

GeoClip: Geometry-Aware Clipping for Differentially Private SGD
par: Gilani, Atefeh, et autres
Publié: (2025)

AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks
par: Zhang, Huiqi, et autres
Publié: (2025)

Mitigating Disparate Impact of Differentially Private Learning through Bounded Adaptive Clipping
par: Zhao, Linzh, et autres
Publié: (2025)

Differentially Private Clipped-SGD: High-Probability Convergence with Arbitrary Clipping Level
par: Khah, Saleh Vatan, et autres
Publié: (2025)

The idea of the university : a reexamination / Jaroslav Pelikan
par: Pelikan, Jaroslav Jan, 1923-
Publié: (1923)

DC-SGD: Differentially Private SGD with Dynamic Clipping through Gradient Norm Distribution Estimation
par: Wei, Chengkun, et autres
Publié: (2025)

SpeakStream: Streaming Text-to-Speech with Interleaved Data
par: Bai, Richard He, et autres
Publié: (2025)

Problem-Based Learning in the Library: Evolving a Realistic Approach
par: Pelikan, Michael
Publié: (2004)

Concentration of the Langevin Algorithm's Stationary Distribution
par: Altschuler, Jason M., et autres
Publié: (2022)

Taming Subnet-Drift in D2D-Enabled Fog Learning: A Hierarchical Gradient Tracking Approach
par: Chen, Evan, et autres
Publié: (2023)

Speech Enhancement with Local Adaptive Rank-Order Filtering
par: Vitaly Kober
Publié: (2014)

Adaptive Sampling and Clipping for Private Worst-Case Group Optimization
par: Cairney-Leeming, Max, et autres
Publié: (2026)

Towards Automatic Assessment of Self-Supervised Speech Models using Rank
par: Aldeneh, Zakaria, et autres
Publié: (2024)

Hierarchical Federated Learning with Multi-Timescale Gradient Correction
par: Fang, Wenzhi, et autres
Publié: (2024)

Johann Jakob Bodmers Arbeit an der Ästhetik
par: Hees-Pelikan, Johannes
Publié: (2025)

Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach
par: Zhang, Xinwei, et autres
Publié: (2023)

Sporadic Gradient Tracking over Directed Graphs: A Theoretical Perspective on Decentralized Federated Learning
par: Zehtabi, Shahryar, et autres
Publié: (2026)

Unsupervised ASR via Cross-Lingual Pseudo-Labeling
par: Likhomanenko, Tatiana, et autres
Publié: (2023)