Buchumschlag

Drawing Early-Bird Tickets: Towards More Efficient Training of Deep Networks

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	You, Haoran, Li, Chaojian, Xu, Pengfei, Fu, Yonggan, Wang, Yue, Chen, Xiaohan, Baraniuk, Richard G., Wang, Zhangyang, Lin, Yingyan Celine
Format:	Preprint
Veröffentlicht:	2019
Schlagworte:	Machine Learning
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Early-Bird GCNs: Graph-Network Co-Optimization Towards More Efficient GCN Training and Inference via Drawing Early-Bird Lottery Tickets
von: You, Haoran, et al.
Veröffentlicht: (2021)

Early-Bird Diffusion: Investigating and Leveraging Timestep-Aware Early-Bird Tickets in Diffusion Models for Efficient Training
von: Whalen, Lexington, et al.
Veröffentlicht: (2025)

FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training
von: Fu, Yonggan, et al.
Veröffentlicht: (2020)

Robust Tickets Can Transfer Better: Drawing More Transferable Subnetworks in Transfer Learning
von: Fu, Yonggan, et al.
Veröffentlicht: (2023)

DANCE: DAta-Network Co-optimization for Efficient Segmentation Model Training and Inference
von: Li, Chaojian, et al.
Veröffentlicht: (2021)

ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural Networks
von: You, Haoran, et al.
Veröffentlicht: (2022)

ShiftAddNet: A Hardware-Inspired Deep Network
von: You, Haoran, et al.
Veröffentlicht: (2020)

SuperTickets: Drawing Task-Agnostic Lottery Tickets from Supernets via Jointly Architecture Searching and Parameter Pruning
von: You, Haoran, et al.
Veröffentlicht: (2022)

Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networks
von: Fu, Yonggan, et al.
Veröffentlicht: (2021)

A3C-S: Automated Agent Accelerator Co-Search towards Efficient Deep Reinforcement Learning
von: Fu, Yonggan, et al.
Veröffentlicht: (2021)

AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks
von: Fu, Yonggan, et al.
Veröffentlicht: (2020)

Auto-Agent-Distiller: Towards Efficient Deep Reinforcement Learning Agents via Neural Architecture Search
von: Fu, Yonggan, et al.
Veröffentlicht: (2020)

DNA: Differentiable Network-Accelerator Co-Search
von: Zhang, Yongan, et al.
Veröffentlicht: (2020)

When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models
von: You, Haoran, et al.
Veröffentlicht: (2024)

2-in-1 Accelerator: Enabling Random Precision Switch for Winning Both Adversarial Robustness and Efficiency
von: Fu, Yonggan, et al.
Veröffentlicht: (2021)

InstantNet: Automated Generation and Deployment of Instantaneously Switchable-Precision Networks
von: Fu, Yonggan, et al.
Veröffentlicht: (2021)

HW-NAS-Bench:Hardware-Aware Neural Architecture Search Benchmark
von: Li, Chaojian, et al.
Veröffentlicht: (2021)

CPT: Efficient Deep Neural Network Training via Cyclic Precision
von: Fu, Yonggan, et al.
Veröffentlicht: (2021)

Omni-Recon: Harnessing Image-based Rendering for General-Purpose Neural Radiance Fields
von: Fu, Yonggan, et al.
Veröffentlicht: (2024)

Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators
von: Fu, Yonggan, et al.
Veröffentlicht: (2021)

Gen-NeRF: Efficient and Generalizable Neural Radiance Fields via Algorithm-Hardware Co-Design
von: Fu, Yonggan, et al.
Veröffentlicht: (2023)

Max-Affine Spline Insights Into Deep Network Pruning
von: You, Haoran, et al.
Veröffentlicht: (2021)

GPT4AIGChip: Towards Next-Generation AI Accelerator Design Automation via Large Language Models
von: Fu, Yonggan, et al.
Veröffentlicht: (2023)

ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer
von: You, Haoran, et al.
Veröffentlicht: (2023)

MG-Verilog: Multi-grained Dataset Towards Enhanced LLM-assisted Verilog Generation
von: Zhang, Yongan, et al.
Veröffentlicht: (2024)

Towards Cognitive AI Systems: a Survey and Prospective on Neuro-Symbolic AI
von: Wan, Zishen, et al.
Veröffentlicht: (2024)

Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration
von: Yu, Zhongzhi, et al.
Veröffentlicht: (2024)

Neon: Negative Extrapolation From Self-Training Improves Image Generation
von: Alemohammad, Sina, et al.
Veröffentlicht: (2025)

Instant-3D: Instant Neural Radiance Field Training Towards On-Device AR/VR 3D Reconstruction
von: Li, Sixu, et al.
Veröffentlicht: (2023)

i-FlatCam: A 253 FPS, 91.49 $μ$J/Frame Ultra-Compact Intelligent Lensless Camera for Real-Time and Efficient Eye Tracking in VR/AR
von: Zhao, Yang, et al.
Veröffentlicht: (2022)

RT-NeRF: Real-Time On-Device Neural Radiance Fields Towards Immersive AR/VR Rendering
von: Li, Chaojian, et al.
Veröffentlicht: (2022)

ERSAM: Neural Architecture Search For Energy-Efficient and Real-Time Social Ambiance Measurement
von: Li, Chaojian, et al.
Veröffentlicht: (2023)

MixRT: Mixed Neural Representations For Real-Time NeRF Rendering
von: Li, Chaojian, et al.
Veröffentlicht: (2023)

Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations?
von: Fu, Yonggan, et al.
Veröffentlicht: (2022)

Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processing
von: Fu, Yonggan, et al.
Veröffentlicht: (2022)

Towards Efficient Neuro-Symbolic AI: From Workload Characterization to Hardware Architecture
von: Wan, Zishen, et al.
Veröffentlicht: (2024)

Early Transformers: A study on Efficient Training of Transformer Models through Early-Bird Lottery Tickets
von: Cheekati, Shravan
Veröffentlicht: (2024)

DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks
von: Fu, Yonggan, et al.
Veröffentlicht: (2022)

Auto-CARD: Efficient and Robust Codec Avatar Driving for Real-time Mobile Telepresence
von: Fu, Yonggan, et al.
Veröffentlicht: (2023)

Fewer Denoising Steps or Cheaper Per-Step Inference: Towards Compute-Optimal Diffusion Model Deployment
von: Du, Zhenbang, et al.
Veröffentlicht: (2025)