Copertina

Rethinking Layer-wise Gaussian Noise Injection: Bridging Implicit Objectives and Privacy Budget Allocation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Tan, Qifeng, Yang, Shusen, Ren, Xuebin, Zhang, Yikai
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

FairGFL: Privacy-Preserving Fairness-Aware Federated Learning with Overlapping Subgraphs
di: Zhou, Zihao, et al.
Pubblicazione: (2025)

LAVa: Layer-wise KV Cache Eviction with Dynamic Budget Allocation
di: Shen, Yiqun, et al.
Pubblicazione: (2025)

Rethinking Layer-wise Model Merging through Chain of Merges
di: Buzzega, Pietro, et al.
Pubblicazione: (2025)

ALPINE: Closed-Loop Adaptive Privacy Budget Allocation for Mobile Edge Crowdsensing
di: Cheng, Guanjie, et al.
Pubblicazione: (2025)

Review of Mathematical Optimization in Federated Learning
di: Yang, Shusen, et al.
Pubblicazione: (2024)

Rethinking Refinement: Correcting Generative Bias without Noise Injection
di: Peng, Xin, et al.
Pubblicazione: (2026)

On the Privacy of Selection Mechanisms with Gaussian Noise
di: Lebensold, Jonathan, et al.
Pubblicazione: (2024)

Multi-Task Combinatorial Bandits for Budget Allocation
di: Ge, Lin, et al.
Pubblicazione: (2024)

FedLED: Label-Free Equipment Fault Diagnosis with Vertical Federated Transfer Learning
di: Shen, Jie, et al.
Pubblicazione: (2023)

Training More Robust Classification Model via Discriminative Loss and Gaussian Noise Injection
di: Nguyen, Hai-Vy, et al.
Pubblicazione: (2024)

C3RL: Rethinking the Combination of Channel-independence and Channel-mixing from Representation Learning
di: Ma, Shusen, et al.
Pubblicazione: (2025)

Bridging the Dimensional Chasm: Uncover Layer-wise Dimensional Reduction in Transformers through Token Correlation
di: Song, Zhuo-Yang, et al.
Pubblicazione: (2025)

SqueezeAttention: 2D Management of KV-Cache in LLM Inference via Layer-wise Optimal Budget
di: Wang, Zihao, et al.
Pubblicazione: (2024)

Adaptive Budget Allocation in LLM-Augmented Surveys
di: Ye, Zikun, et al.
Pubblicazione: (2026)

Rethinking Multi-domain Generalization with A General Learning Objective
di: Tan, Zhaorui, et al.
Pubblicazione: (2024)

BGTplanner: Maximizing Training Accuracy for Differentially Private Federated Recommenders via Strategic Privacy Budget Allocation
di: Zhang, Xianzhi, et al.
Pubblicazione: (2024)

Scalable Model Merging with Progressive Layer-wise Distillation
di: Xu, Jing, et al.
Pubblicazione: (2025)

Layer-wise Linear Mode Connectivity
di: Adilova, Linara, et al.
Pubblicazione: (2023)

Layer-wise Derivative Controlled Networks
di: Martnishn, Rowan, et al.
Pubblicazione: (2026)

Rethinking the Potential of Layer Freezing for Efficient DNN Training
di: Yang, Chence, et al.
Pubblicazione: (2025)

DPack: Efficiency-Oriented Privacy Budget Scheduling
di: Tholoniat, Pierre, et al.
Pubblicazione: (2022)

FedSC: Provable Federated Self-supervised Learning with Spectral Contrastive Objective over Non-i.i.d. Data
di: Jing, Shusen, et al.
Pubblicazione: (2024)

Budget Allocation for Unknown Value Functions in a Lipschitz Space
di: Bateni, MohammadHossein, et al.
Pubblicazione: (2025)

Learning in Budgeted Auctions with Spacing Objectives
di: Fikioris, Giannis, et al.
Pubblicazione: (2024)

ZEBRA: Zero-shot Budgeted Resource Allocation for LLM Orchestration
di: Hamri, May, et al.
Pubblicazione: (2026)

Layer-wise dynamic rank for compressing large language models
di: Mi, Zhendong, et al.
Pubblicazione: (2025)

Rethinking Training Dynamics in Scale-wise Autoregressive Generation
di: Zhou, Gengze, et al.
Pubblicazione: (2025)

Diffusion Bridge Implicit Models
di: Zheng, Kaiwen, et al.
Pubblicazione: (2024)

MaskPrune: Mask-based LLM Pruning for Layer-wise Uniform Structures
di: Qin, Jiayu, et al.
Pubblicazione: (2025)

Limits of Personalizing Differential Privacy Budgets
di: Cyffers, Edwige, et al.
Pubblicazione: (2026)

Beyond Token Eviction: Mixed-Dimension Budget Allocation for Efficient KV Cache Compression
di: Miao, Ruijie, et al.
Pubblicazione: (2026)

Geometric Layer-wise Approximation Rates for Deep Networks
di: Zhang, Shijun, et al.
Pubblicazione: (2026)

Noise-Resilient Point-wise Anomaly Detection in Time Series Using Weak Segment Labels
di: Wang, Yaxuan, et al.
Pubblicazione: (2025)

Optimal Perturbation Budget Allocation for Data Poisoning in Offline Reinforcement Learning
di: Qiu, Junnan, et al.
Pubblicazione: (2025)

CoBA-RL: Capability-Oriented Budget Allocation for Reinforcement Learning in LLMs
di: Yao, Zhiyuan, et al.
Pubblicazione: (2026)

LoaQ: Layer-wise Output Approximation Quantization
di: Lin, Li, et al.
Pubblicazione: (2025)

LOTOS: Layer-wise Orthogonalization for Training Robust Ensembles
di: Ebrahimpour-Boroojeny, Ali, et al.
Pubblicazione: (2024)

ILILT: Implicit Learning of Inverse Lithography Technologies
di: Yang, Haoyu, et al.
Pubblicazione: (2024)

Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation
di: Li, Ziniu, et al.
Pubblicazione: (2025)

Hidden Representation Clustering with Multi-Task Representation Learning towards Robust Online Budget Allocation
di: Wang, Xiaohan, et al.
Pubblicazione: (2025)