Image de couverture de livre

NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhao, Boran, Huang, Haiduo, Dang, Qiwei, Zhao, Wenzhe, Xia, Tian, Ren, Pengju
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

AdapSNE: Adaptive Fireworks-Optimized and Entropy-Guided Dataset Sampling for Edge DNN Training
par: Zhao, Boran, et autres
Publié: (2025)

FastEagle: Cascaded Drafting for Accelerating Speculative Decoding
par: Huang, Haiduo, et autres
Publié: (2025)

SparseMap: A Sparse Tensor Accelerator Framework Based on Evolution Strategy
par: Zhao, Boran, et autres
Publié: (2025)

Nearly Lossless Adaptive Bit Switching
par: Huang, Haiduo, et autres
Publié: (2025)

GeGS-PCR: Effective and Robust 3D Point Cloud Registration with Two-Stage Color-Enhanced Geometric-3DGS Fusion
par: Tian, Jiayi, et autres
Publié: (2026)

Partial Channel Network: Compute Fewer, Perform Better
par: Huang, Haiduo, et autres
Publié: (2025)

KernelDNA: Dynamic Kernel Sharing via Decoupled Naive Adapters
par: Huang, Haiduo, et autres
Publié: (2025)

IMMSched: Interruptible Multi-DNN Scheduling via Parallel Multi-Particle Optimizing Subgraph Isomorphism
par: Zhao, Boran, et autres
Publié: (2026)

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer
par: Huang, Haiduo, et autres
Publié: (2025)

IsoSched: Preemptive Tile Cascaded Scheduling of Multi-DNN via Subgraph Isomorphism
par: Zhao, Boran, et autres
Publié: (2025)

Exploring Variance Reduction in Importance Sampling for Efficient DNN Training
par: Kutsuna, Takuro
Publié: (2025)

FAST: Topology-Aware Frequency-Domain Distribution Matching for Coreset Selection
par: Cui, Jin, et autres
Publié: (2025)

Rethinking the Potential of Layer Freezing for Efficient DNN Training
par: Yang, Chence, et autres
Publié: (2025)

AdaPI: Facilitating DNN Model Adaptivity for Efficient Private Inference in Edge Computing
par: Zhou, Tong, et autres
Publié: (2024)

Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE
par: Huang, Haiduo, et autres
Publié: (2025)

DNN Modularization via Activation-Driven Training
par: Ngo, Tuan, et autres
Publié: (2024)

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
par: Zhao, Jiawei, et autres
Publié: (2024)

SwapNet: Efficient Swapping for DNN Inference on Edge AI Devices Beyond the Memory Budget
par: Wang, Kun, et autres
Publié: (2024)

DNN Memory Footprint Reduction via Post-Training Intra-Layer Multi-Precision Quantization
par: Ghavami, Behnam, et autres
Publié: (2024)

DAF: An Efficient End-to-End Dynamic Activation Framework for on-Device DNN Training
par: Liu, Renyuan, et autres
Publié: (2025)

NeFT: Negative Feedback Training to Improve Robustness of Compute-In-Memory DNN Accelerators
par: Qin, Yifan, et autres
Publié: (2023)

FusedInf: Efficient Swapping of DNN Models for On-Demand Serverless Inference Services on the Edge
par: Taki, Sifat Ut, et autres
Publié: (2024)

Hedging Memory Horizons for Non-Stationary Prediction via Online Aggregation
par: Wang, Yutong, et autres
Publié: (2026)

Near-Optimal Regret for KL-Regularized Multi-Armed Bandits
par: Ji, Kaixuan, et autres
Publié: (2026)

A Survey on Collaborative DNN Inference for Edge Intelligence
par: Ren, Weiqing, et autres
Publié: (2022)

DNNShifter: An Efficient DNN Pruning System for Edge Computing
par: Eccles, Bailey J., et autres
Publié: (2023)

CHIME: Chiplet-based Heterogeneous Near-Memory Acceleration for Edge Multimodal LLM Inference
par: Chen, Yanru, et autres
Publié: (2025)

PaSE: Parallelization Strategies for Efficient DNN Training
par: Elango, Venmugil
Publié: (2024)

HOSL: Hybrid-Order Split Learning for Memory-Constrained Edge Training
par: Lnu, Aakriti, et autres
Publié: (2026)

Efficient Sampling on Riemannian Manifolds via Langevin MCMC
par: Cheng, Xiang, et autres
Publié: (2024)

Improving Memory Efficiency for Training KANs via Meta Learning
par: Zhao, Zhangchi, et autres
Publié: (2025)

TensorGRaD: Tensor Gradient Robust Decomposition for Memory-Efficient Neural Operator Training
par: Loeschcke, Sebastian, et autres
Publié: (2025)

Learning the Optimal Path and DNN Partition for Collaborative Edge Inference
par: Huang, Yin, et autres
Publié: (2024)

On the Optimal Sample Complexity of Offline Multi-Armed Bandits with KL Regularization
par: Ji, Kaixuan, et autres
Publié: (2026)

Omni-Masked Gradient Descent: Memory-Efficient Optimization via Mask Traversal with Improved Convergence
par: Yang, Hui, et autres
Publié: (2026)

Causal Negative Sampling via Diffusion Model for Out-of-Distribution Recommendation
par: Zhao, Chu, et autres
Publié: (2025)

Nearly Optimal Algorithms for Contextual Dueling Bandits from Adversarial Feedback
par: Di, Qiwei, et autres
Publié: (2024)

Hardware-Aware DNN Compression for Homogeneous Edge Devices
par: Zhang, Kunlong, et autres
Publié: (2025)

COSMOS: A Hybrid Adaptive Optimizer for Memory-Efficient Training of LLMs
par: Liu, Liming, et autres
Publié: (2025)

Pay Less Attention to Function Words for Free Robustness of Vision-Language Models
par: Tian, Qiwei, et autres
Publié: (2025)