WASH: Train your Ensemble with Communication-Efficient Weight Shuffling, then Average
Fuente:
arXiv
Saved in:
| Main Authors: | Fournier, Louis, Nabli, Adel, Aminbeidokhti, Masih, Pedersoli, Marco, Belilovsky, Eugene, Oyallon, Edouard |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
Cyclic Data Parallelism for Efficient Parallelism of Deep Neural Networks
by: Fournier, Louis, et al.
Published: (2024)
by: Fournier, Louis, et al.
Published: (2024)
On Non-Linear operators for Geometric Deep Learning
by: Sergeant-Perthuis, Grégoire, et al.
Published: (2022)
by: Sergeant-Perthuis, Grégoire, et al.
Published: (2022)
ACCO: Accumulate While You Communicate for Communication-Overlapped Sharded LLM Training
by: Nabli, Adel, et al.
Published: (2024)
by: Nabli, Adel, et al.
Published: (2024)
STOP: Spatiotemporal Orthogonal Propagation for Weight-Threshold-Leakage Synergistic Training of Deep Spiking Neural Networks
by: Gao, Haoran, et al.
Published: (2024)
by: Gao, Haoran, et al.
Published: (2024)
Twin Network Augmentation: A Novel Training Strategy for Improved Spiking Neural Networks and Efficient Weight Quantization
by: Deckers, Lucas, et al.
Published: (2024)
by: Deckers, Lucas, et al.
Published: (2024)
Reliable Brain Tumor Segmentation Based on Spiking Neural Networks with Efficient Training
by: Ghiardelli, Aurora Pia, et al.
Published: (2026)
by: Ghiardelli, Aurora Pia, et al.
Published: (2026)
A Self-Ensemble Inspired Approach for Effective Training of Binary-Weight Spiking Neural Networks
by: Meng, Qingyan, et al.
Published: (2025)
by: Meng, Qingyan, et al.
Published: (2025)
Theoretical Analysis of Explicit Averaging and Novel Sign Averaging in Comparison-Based Search
by: Morinaga, Daiki, et al.
Published: (2024)
by: Morinaga, Daiki, et al.
Published: (2024)
EVOS: Efficient Implicit Neural Training via EVOlutionary Selector
by: Zhang, Weixiang, et al.
Published: (2024)
by: Zhang, Weixiang, et al.
Published: (2024)
TT-SNN: Tensor Train Decomposition for Efficient Spiking Neural Network Training
by: Lee, Donghyun, et al.
Published: (2024)
by: Lee, Donghyun, et al.
Published: (2024)
Frozen Backpropagation: Relaxing Weight Symmetry in Deep Spiking Neural Networks
by: Goupy, Gaspard, et al.
Published: (2025)
by: Goupy, Gaspard, et al.
Published: (2025)
An Efficient Evolutionary Algorithm for Diversified Top-k (Weight) Clique Search Problems
by: Zheng, Jiongzhi, et al.
Published: (2024)
by: Zheng, Jiongzhi, et al.
Published: (2024)
Should Under-parameterized Student Networks Copy or Average Teacher Weights?
by: Şimşek, Berfin, et al.
Published: (2023)
by: Şimşek, Berfin, et al.
Published: (2023)
Dynamically Weighted Momentum with Adaptive Step Sizes for Efficient Deep Network Training
by: Wang, Zhifeng, et al.
Published: (2025)
by: Wang, Zhifeng, et al.
Published: (2025)
A Novel Structure-Agnostic Multi-Objective Approach for Weight-Sharing Compression in Deep Neural Networks
by: Khosrowshahli, Rasa, et al.
Published: (2025)
by: Khosrowshahli, Rasa, et al.
Published: (2025)
Parallel Spiking Unit for Efficient Training of Spiking Neural Networks
by: Li, Yang, et al.
Published: (2024)
by: Li, Yang, et al.
Published: (2024)
Training a Custom CNN on Five Heterogeneous Image Datasets
by: Tabassum, Anika, et al.
Published: (2026)
by: Tabassum, Anika, et al.
Published: (2026)
Dynamic Event-based Optical Identification and Communication
by: von Arnim, Axel, et al.
Published: (2023)
by: von Arnim, Axel, et al.
Published: (2023)
Gated Attention Coding for Training High-performance and Efficient Spiking Neural Networks
by: Qiu, Xuerui, et al.
Published: (2023)
by: Qiu, Xuerui, et al.
Published: (2023)
Efficiently Training Time-to-First-Spike Spiking Neural Networks from Scratch
by: Che, Kaiwei, et al.
Published: (2024)
by: Che, Kaiwei, et al.
Published: (2024)
Unsupervised Domain Adaptation Architecture Search with Self-Training for Land Cover Mapping
by: Broni-Bediako, Clifford, et al.
Published: (2024)
by: Broni-Bediako, Clifford, et al.
Published: (2024)
Adaptive Time-step Training for Enhancing Spike-Based Neural Radiance Fields
by: Lin, Ranxi, et al.
Published: (2025)
by: Lin, Ranxi, et al.
Published: (2025)
Towards Chip-in-the-loop Spiking Neural Network Training via Metropolis-Hastings Sampling
by: Safa, Ali, et al.
Published: (2024)
by: Safa, Ali, et al.
Published: (2024)
Stabilizing Direct Training of Spiking Neural Networks: Membrane Potential Initialization and Threshold-robust Surrogate Gradient
by: Kook, Hyunho, et al.
Published: (2025)
by: Kook, Hyunho, et al.
Published: (2025)
SU-YOLO: Spiking Neural Network for Efficient Underwater Object Detection
by: Li, Chenyang, et al.
Published: (2025)
by: Li, Chenyang, et al.
Published: (2025)
A Multiplication-Free Spike-Time Learning Algorithm and its Efficient FPGA Implementation for On-Chip SNN Training
by: Mirsadeghi, Maryam, et al.
Published: (2026)
by: Mirsadeghi, Maryam, et al.
Published: (2026)
Sparse Convolutional Recurrent Learning for Efficient Event-based Neuromorphic Object Detection
by: Wang, Shenqi, et al.
Published: (2025)
by: Wang, Shenqi, et al.
Published: (2025)
An Ensemble of Evolutionary Algorithms With Both Crisscross Search and Sparrow Search for Processing Inferior Individuals
by: Du, Mingxuan, et al.
Published: (2026)
by: Du, Mingxuan, et al.
Published: (2026)
Smart Buildings Energy Consumption Forecasting using Adaptive Evolutionary Ensemble Learning Models
by: Neshat, Mehdi, et al.
Published: (2025)
by: Neshat, Mehdi, et al.
Published: (2025)
Accurate and Efficient Event-based Semantic Segmentation Using Adaptive Spiking Encoder-Decoder Network
by: Zhang, Rui, et al.
Published: (2023)
by: Zhang, Rui, et al.
Published: (2023)
Attention-Driven LPLC2 Neural Ensemble Model for Multi-Target Looming Detection and Localization
by: Liu, Renyuan, et al.
Published: (2025)
by: Liu, Renyuan, et al.
Published: (2025)
A Multi-operator Ensemble LSHADE with Restart and Local Search Mechanisms for Single-objective Optimization
by: Chauhan, Dikshit, et al.
Published: (2024)
by: Chauhan, Dikshit, et al.
Published: (2024)
Weighted-Scenario Optimisation for the Chance Constrained Travelling Thief Problem
by: Don, Thilina Pathirage, et al.
Published: (2025)
by: Don, Thilina Pathirage, et al.
Published: (2025)
Apprenticeship-Inspired Elegance: Synergistic Knowledge Distillation Empowers Spiking Neural Networks for Efficient Single-Eye Emotion Recognition
by: Wang, Yang, et al.
Published: (2024)
by: Wang, Yang, et al.
Published: (2024)
Multi-objective Memetic Algorithm with Adaptive Weights for Inverse Antenna Design
by: Kadlec, Petr, et al.
Published: (2024)
by: Kadlec, Petr, et al.
Published: (2024)
Dynamic Activation with Knowledge Distillation for Energy-Efficient Spiking NN Ensembles
by: Konstantaropoulos, Orestis, et al.
Published: (2025)
by: Konstantaropoulos, Orestis, et al.
Published: (2025)
Hybrid Wave-wind System Power Optimisation Using Effective Ensemble Covariance Matrix Adaptation Evolutionary Algorithm
by: Neshat, Mehdi, et al.
Published: (2025)
by: Neshat, Mehdi, et al.
Published: (2025)
Snail Homing and Mating Search Algorithm for Weight Optimization of Stepped-Transmission Shaft
by: Saha, Kaustav, et al.
Published: (2025)
by: Saha, Kaustav, et al.
Published: (2025)
Evolutionary Automata and Deep Evolutionary Computation
by: Eberbach, Eugene
Published: (2024)
by: Eberbach, Eugene
Published: (2024)
A Weight Adaptation Trigger Mechanism in Decomposition-based Evolutionary Multi-Objective Optimisation
by: Han, Xiaofeng, et al.
Published: (2025)
by: Han, Xiaofeng, et al.
Published: (2025)
Similar Items
-
Cyclic Data Parallelism for Efficient Parallelism of Deep Neural Networks
by: Fournier, Louis, et al.
Published: (2024) -
On Non-Linear operators for Geometric Deep Learning
by: Sergeant-Perthuis, Grégoire, et al.
Published: (2022) -
ACCO: Accumulate While You Communicate for Communication-Overlapped Sharded LLM Training
by: Nabli, Adel, et al.
Published: (2024) -
STOP: Spatiotemporal Orthogonal Propagation for Weight-Threshold-Leakage Synergistic Training of Deep Spiking Neural Networks
by: Gao, Haoran, et al.
Published: (2024) -
Twin Network Augmentation: A Novel Training Strategy for Improved Spiking Neural Networks and Efficient Weight Quantization
by: Deckers, Lucas, et al.
Published: (2024)