Copertina

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

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Badar, Zia
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Same accuracy, twice as fast: continuous training surpasses retraining from scratch
di: Verwimp, Eli, et al.
Pubblicazione: (2025)

PCA-VAE: Differentiable Subspace Quantization without Codebook Collapse
di: Lu, Hao, et al.
Pubblicazione: (2026)

Low-Bit, High-Fidelity: Optimal Transport Quantization for Flow Matching
di: Varam, Dara, et al.
Pubblicazione: (2025)

Technical Report: Activation Residual Hessian Quantization (ARHQ) for Low-Bit LLM Quantization
di: Wang, YiFeng, et al.
Pubblicazione: (2026)

1-Bit FQT: Pushing the Limit of Fully Quantized Training to 1-bit
di: Gao, Chang, et al.
Pubblicazione: (2024)

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

Wasserstein distributional adversarial training for deep neural networks
di: Bai, Xingjian, et al.
Pubblicazione: (2025)

When Bits Break Recourse: Counterfactual-Faithful Quantization
di: Yahyati, Chaymae, et al.
Pubblicazione: (2026)

PQD: Post-training Quantization for Efficient Diffusion Models
di: Ye, Jiaojiao, et al.
Pubblicazione: (2024)

Efficient Multi-bit Quantization Network Training via Weight Bias Correction and Bit-wise Coreset Sampling
di: Kim, Jinhee, et al.
Pubblicazione: (2025)

Aligned explanations in neural networks
di: Lobet, Corentin, et al.
Pubblicazione: (2026)

Equivariant neural networks and equivarification
di: Bao, Erkao, et al.
Pubblicazione: (2019)

On the explainability of max-plus neural networks
di: Enaieh, Ikhlas, et al.
Pubblicazione: (2026)

Data-Free Quantization via Mixed-Precision Compensation without Fine-Tuning
di: Chen, Jun, et al.
Pubblicazione: (2023)

Outlier-Aware Training for Low-Bit Quantization of Structural Re-Parameterized Networks
di: Niu, Muqun, et al.
Pubblicazione: (2024)

MaskBit: Embedding-free Image Generation via Bit Tokens
di: Weber, Mark, et al.
Pubblicazione: (2024)

MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization
di: Su, Le, et al.
Pubblicazione: (2026)

Quantization Variation: A New Perspective on Training Transformers with Low-Bit Precision
di: Huang, Xijie, et al.
Pubblicazione: (2023)

Does Vector Quantization Fail in Spatio-Temporal Forecasting? Exploring a Differentiable Sparse Soft-Vector Quantization Approach
di: Chen, Chao, et al.
Pubblicazione: (2023)

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

Post-training Quantization for Text-to-Image Diffusion Models with Progressive Calibration and Activation Relaxing
di: Tang, Siao, et al.
Pubblicazione: (2023)

Are classical deep neural networks weakly adversarially robust?
di: Sun, Nuolin, et al.
Pubblicazione: (2025)

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

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

D4C: Data-Free Quantization for Contrastive Language-Image Pre-training Models
di: Zhang, Wenlun, et al.
Pubblicazione: (2025)

Sparse components distinguish visual pathways & their alignment to neural networks
di: Marvi, Ammar I, et al.
Pubblicazione: (2025)

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

Multi-task convolutional neural network for image aesthetic assessment
di: Soydaner, Derya, et al.
Pubblicazione: (2023)

Unveiling Differences in Generative Models: A Scalable Differential Clustering Approach
di: Zhang, Jingwei, et al.
Pubblicazione: (2024)

Enhanced Privacy and Communication Efficiency in Non-IID Federated Learning with Adaptive Quantization and Differential Privacy
di: Ardıç, Emre, et al.
Pubblicazione: (2026)

BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook
di: Gu, Hao, et al.
Pubblicazione: (2025)

Neural network relief: a pruning algorithm based on neural activity
di: Dekhovich, Aleksandr, et al.
Pubblicazione: (2021)

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

OCT Data is All You Need: How Vision Transformers with and without Pre-training Benefit Imaging
di: Han, Zihao, et al.
Pubblicazione: (2025)

Reduced storage direct tensor ring decomposition for convolutional neural networks compression
di: Gabor, Mateusz, et al.
Pubblicazione: (2024)

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

DPAdapter: Improving Differentially Private Deep Learning through Noise Tolerance Pre-training
di: Wang, Zihao, et al.
Pubblicazione: (2024)

MimiQ: Low-Bit Data-Free Quantization of Vision Transformers with Encouraging Inter-Head Attention Similarity
di: Choi, Kanghyun, et al.
Pubblicazione: (2024)

Shedding the Bits: Pushing the Boundaries of Quantization with Minifloats on FPGAs
di: Aggarwal, Shivam, et al.
Pubblicazione: (2023)

Pseudo-label Refinement for Improving Self-Supervised Learning Systems
di: Zia-ur-Rehman, et al.
Pubblicazione: (2024)