Copertina

Memory Faults in Activation-sparse Quantized Deep Neural Networks: Analysis and Mitigation using Sharpness-aware Training

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Malhotra, Akul, Gupta, Sumeet Kumar
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Weight Transformations in Bit-Sliced Crossbar Arrays for Fault Tolerant Computing-in-Memory: Design Techniques and Evaluation Framework
di: Malhotra, Akul, et al.
Pubblicazione: (2025)

ReTern: Exploiting Natural Redundancy and Sign Transformations for Enhanced Fault Tolerance in Compute-in-Memory based Ternary LLMs
di: Malhotra, Akul, et al.
Pubblicazione: (2025)

BinSparX: Sparsified Binary Neural Networks for Reduced Hardware Non-Idealities in Xbar Arrays
di: Malhotra, Akul, et al.
Pubblicazione: (2024)

SiTe CiM: Signed Ternary Computing-in-Memory for Ultra-Low Precision Deep Neural Networks
di: Thakuria, Niharika, et al.
Pubblicazione: (2024)

Inverted Activations: Reducing Memory Footprint in Neural Network Training
di: Novikov, Georgii, et al.
Pubblicazione: (2024)

DQA: An Efficient Method for Deep Quantization of Deep Neural Network Activations
di: Hu, Wenhao, et al.
Pubblicazione: (2024)

EPSILON: Adaptive Fault Mitigation in Approximate Deep Neural Network using Statistical Signatures
di: Khalil, Khurram, et al.
Pubblicazione: (2025)

Sharpness-Aware Minimization with Adaptive Regularization for Training Deep Neural Networks
di: Zou, Jinping, et al.
Pubblicazione: (2024)

Training Memory in Deep Neural Networks: Mechanisms, Evidence, and Measurement Gaps
di: Sevetlidis, Vasileios, et al.
Pubblicazione: (2026)

Accelerating Neural Network Training Along Sharp and Flat Directions
di: Zakarin, Daniyar, et al.
Pubblicazione: (2025)

Compression-aware Training of Neural Networks using Frank-Wolfe
di: Zimmer, Max, et al.
Pubblicazione: (2022)

On-Device Training of Fully Quantized Deep Neural Networks on Cortex-M Microcontrollers
di: Deutel, Mark, et al.
Pubblicazione: (2024)

Activation Compression of Graph Neural Networks using Block-wise Quantization with Improved Variance Minimization
di: Eliassen, Sebastian, et al.
Pubblicazione: (2023)

Regularization-based Framework for Quantization-, Fault- and Variability-Aware Training
di: Biswas, Anmol, et al.
Pubblicazione: (2025)

Comparative Evaluation of Memory Technologies for Synaptic Crossbar Arrays- Part 2: Design Knobs and DNN Accuracy Trends
di: Victor, Jeffry, et al.
Pubblicazione: (2024)

Sharpness Aware Surrogate Training for Spiking Neural Networks
di: Nicholson, Maximilian
Pubblicazione: (2026)

Gradient-Free Training of Quantized Neural Networks
di: Cohen, Noa, et al.
Pubblicazione: (2024)

Quantization-Aware Regularizers for Deep Neural Networks Compression
di: Malchiodi, Dario, et al.
Pubblicazione: (2026)

Perfecting Imperfect Physical Neural Networks with Transferable Robustness using Sharpness-Aware Training
di: Xu, Tengji, et al.
Pubblicazione: (2024)

Activation Outliers in Transformer Quantization: Reproduction, Statistical Analysis, and Deployment Tradeoffs
di: Kaliaperumal, Pranav Kumar
Pubblicazione: (2026)

S2D: Selective Spectral Decay for Quantization-Friendly Conditioning of Neural Activations
di: Chavan, Arnav, et al.
Pubblicazione: (2026)

Deep Neural Network Initialization with Sparsity Inducing Activations
di: Price, Ilan, et al.
Pubblicazione: (2024)

Improving Quantization-aware Training of Low-Precision Network via Block Replacement on Full-Precision Counterpart
di: Yu, Chengting, et al.
Pubblicazione: (2024)

Robust Black-box Testing of Deep Neural Networks using Co-Domain Coverage
di: Gupta, Aishwarya, et al.
Pubblicazione: (2024)

Exploration of Activation Fault Reliability in Quantized Systolic Array-Based DNN Accelerators
di: Taheri, Mahdi, et al.
Pubblicazione: (2024)

Generalization Bounds for Rank-sparse Neural Networks
di: Ledent, Antoine, et al.
Pubblicazione: (2025)

DeepVigor+: Scalable and Accurate Semi-Analytical Fault Resilience Analysis for Deep Neural Network
di: Ahmadilivani, Mohammad Hasan, et al.
Pubblicazione: (2024)

Mitigating Deep Reinforcement Learning Backdoors in the Neural Activation Space
di: Vyas, Sanyam, et al.
Pubblicazione: (2024)

STRIDe: Cross-Coupled STT-MRAM Enabling Robust In-Memory-Computing for Deep Neural Network Accelerators
di: Ahmed, Imtiaz, et al.
Pubblicazione: (2026)

SAMPa: Sharpness-aware Minimization Parallelized
di: Xie, Wanyun, et al.
Pubblicazione: (2024)

Sharpness-aware Federated Graph Learning
di: Li, Ruiyu, et al.
Pubblicazione: (2025)

VTrans: Accelerating Transformer Compression with Variational Information Bottleneck based Pruning
di: Dutta, Oshin, et al.
Pubblicazione: (2024)

On the Hardness of Training Deep Neural Networks Discretely
di: Doron-Arad, Ilan
Pubblicazione: (2024)

Memory Analysis on the Training Course of DeepSeek Models
di: Zhang, Ping, et al.
Pubblicazione: (2025)

Improving Deep Learning Model Calibration for Cardiac Applications using Deterministic Uncertainty Networks and Uncertainty-aware Training
di: Dawood, Tareen, et al.
Pubblicazione: (2024)

Mitigating Quantization Errors Due to Activation Spikes in GLU-Based LLMs
di: Yang, Jaewoo, et al.
Pubblicazione: (2024)

Mitigating the Impact of Outlier Channels for Language Model Quantization with Activation Regularization
di: Nrusimha, Aniruddha, et al.
Pubblicazione: (2024)

On-device AI: Quantization-aware Training of Transformers in Time-Series
di: Ling, Tianheng, et al.
Pubblicazione: (2024)

Efficient Fault Detection in WSN Based on PCA-Optimized Deep Neural Network Slicing Trained with GOA
di: Feghhi, Mahmood Mohassel, et al.
Pubblicazione: (2025)

Class-based Subset Selection for Transfer Learning under Extreme Label Shift
di: Goyal, Akul, et al.
Pubblicazione: (2024)