Image de couverture de livre

Differentiable, Bit-shifting, and Scalable Quantization without training neural network from scratch

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Badar, Zia
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Same accuracy, twice as fast: continuous training surpasses retraining from scratch
par: Verwimp, Eli, et autres
Publié: (2025)

PCA-VAE: Differentiable Subspace Quantization without Codebook Collapse
par: Lu, Hao, et autres
Publié: (2026)

Low-Bit, High-Fidelity: Optimal Transport Quantization for Flow Matching
par: Varam, Dara, et autres
Publié: (2025)

Technical Report: Activation Residual Hessian Quantization (ARHQ) for Low-Bit LLM Quantization
par: Wang, YiFeng, et autres
Publié: (2026)

1-Bit FQT: Pushing the Limit of Fully Quantized Training to 1-bit
par: Gao, Chang, et autres
Publié: (2024)

GD doesn't make the cut: Three ways that non-differentiability affects neural network training
par: Kumar, Siddharth Krishna
Publié: (2024)

Wasserstein distributional adversarial training for deep neural networks
par: Bai, Xingjian, et autres
Publié: (2025)

When Bits Break Recourse: Counterfactual-Faithful Quantization
par: Yahyati, Chaymae, et autres
Publié: (2026)

PQD: Post-training Quantization for Efficient Diffusion Models
par: Ye, Jiaojiao, et autres
Publié: (2024)

Efficient Multi-bit Quantization Network Training via Weight Bias Correction and Bit-wise Coreset Sampling
par: Kim, Jinhee, et autres
Publié: (2025)

Aligned explanations in neural networks
par: Lobet, Corentin, et autres
Publié: (2026)

Equivariant neural networks and equivarification
par: Bao, Erkao, et autres
Publié: (2019)

On the explainability of max-plus neural networks
par: Enaieh, Ikhlas, et autres
Publié: (2026)

Data-Free Quantization via Mixed-Precision Compensation without Fine-Tuning
par: Chen, Jun, et autres
Publié: (2023)

Outlier-Aware Training for Low-Bit Quantization of Structural Re-Parameterized Networks
par: Niu, Muqun, et autres
Publié: (2024)

MaskBit: Embedding-free Image Generation via Bit Tokens
par: Weber, Mark, et autres
Publié: (2024)

MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization
par: Su, Le, et autres
Publié: (2026)

Quantization Variation: A New Perspective on Training Transformers with Low-Bit Precision
par: Huang, Xijie, et autres
Publié: (2023)

Does Vector Quantization Fail in Spatio-Temporal Forecasting? Exploring a Differentiable Sparse Soft-Vector Quantization Approach
par: Chen, Chao, et autres
Publié: (2023)

Exploring possible vector systems for faster training of neural networks with preconfigured latent spaces
par: Gabdullin, Nikita
Publié: (2025)

Post-training Quantization for Text-to-Image Diffusion Models with Progressive Calibration and Activation Relaxing
par: Tang, Siao, et autres
Publié: (2023)

Are classical deep neural networks weakly adversarially robust?
par: Sun, Nuolin, et autres
Publié: (2025)

On margin-based generalization prediction in deep neural networks
par: Mouton, Coenraad
Publié: (2024)

Characterization of topological structures in different neural network architectures
par: Świder, Paweł
Publié: (2024)

D4C: Data-Free Quantization for Contrastive Language-Image Pre-training Models
par: Zhang, Wenlun, et autres
Publié: (2025)

Sparse components distinguish visual pathways & their alignment to neural networks
par: Marvi, Ammar I, et autres
Publié: (2025)

Spectral structural distortion reveals redundant neurons in neural networks
par: Wang, Yongyu
Publié: (2026)

Multi-task convolutional neural network for image aesthetic assessment
par: Soydaner, Derya, et autres
Publié: (2023)

Unveiling Differences in Generative Models: A Scalable Differential Clustering Approach
par: Zhang, Jingwei, et autres
Publié: (2024)

Enhanced Privacy and Communication Efficiency in Non-IID Federated Learning with Adaptive Quantization and Differential Privacy
par: Ardıç, Emre, et autres
Publié: (2026)

BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook
par: Gu, Hao, et autres
Publié: (2025)

Neural network relief: a pruning algorithm based on neural activity
par: Dekhovich, Aleksandr, et autres
Publié: (2021)

Training morphological neural networks with gradient descent: some theoretical insights
par: Blusseau, Samy
Publié: (2024)

OCT Data is All You Need: How Vision Transformers with and without Pre-training Benefit Imaging
par: Han, Zihao, et autres
Publié: (2025)

Reduced storage direct tensor ring decomposition for convolutional neural networks compression
par: Gabor, Mateusz, et autres
Publié: (2024)

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis
par: Gabdullin, Nikita
Publié: (2024)

DPAdapter: Improving Differentially Private Deep Learning through Noise Tolerance Pre-training
par: Wang, Zihao, et autres
Publié: (2024)

MimiQ: Low-Bit Data-Free Quantization of Vision Transformers with Encouraging Inter-Head Attention Similarity
par: Choi, Kanghyun, et autres
Publié: (2024)

Shedding the Bits: Pushing the Boundaries of Quantization with Minifloats on FPGAs
par: Aggarwal, Shivam, et autres
Publié: (2023)

Pseudo-label Refinement for Improving Self-Supervised Learning Systems
par: Zia-ur-Rehman, et autres
Publié: (2024)