arXiv AI
Jun 4
Model-Preserving Adaptive Rounding
arXiv:2505. 22988v3 Announce Type: replace-cross Abstract: The goal of quantization is to produce a compressed model whose output distribution is as close to the original model's as possible.
Layerwise Error Attribution for Fast and Robust Mixed-Precision Post-Training Quantization
Layerwise Error Attribution for Fast and Robust Mixed-Precision Post-Training Quantization proposes a new allocation method that assigns bits to layers under a global memory budget using a small calibration set. The method derives a layerwise probabilistic analysis separating propagated error from local perturbations, enabling a simple, solver‑free allocation algorithm that is robust to corrupted calibration data. Experiments on DRUNet denoising tasks and quantized diffusion models show significant speed‑ups (up to 2,570×) and improved performance, with PSNR gains of up to 7.5 dB under corrupted calibration.
Related stories
arXiv AI
5d ago
When Lower Reconstruction Loss Hurts: Distributionally Robust Refinement for Low-Bit LLM Quantization
The paper examines weight-only post‑training quantization (PTQ) and finds that minimizing reconstruction loss does not always improve model performance, sometimes even harming it on calibration data. It shows that weights with low reconstruction loss on one distribution can perform worse when activation distributions shift. To address this, the authors introduce Distributionally Robust Quantization (DRQ), a refinement step that minimizes worst‑case reconstruction loss over a constrained set of activation distributions while keeping the quantization grid unchanged. Experiments demonstrate that DRQ improves models quantized by several PTQ methods across dense and mixture‑of‑experts large language models, offering better downstream performance without extra inference cost.
arXiv AI
Jul 28
MixQuant: Adaptive Mixed-Precision Quantization for Large Language Models
arXiv:2607. 23047v1 Announce Type: cross Abstract: Mixed-precision quantization improves the accuracy of post-training quantization by allocating higher bitwidths to sensitive layers, but existing methods solve the allocation for a single fixed memory budget.
arXiv Machine Learning
Oct 7
Activation Denoising: A Robustness View on Parallel vs Sequential LLM Quantization
arXiv:2610.07522v1 Announce Type: new Abstract: Post-training quantization is a powerful tool for compressing large language models. The most scalable methods quantize every layer in parallel, but qu...
arXiv AI
Jun 9
Joint Structural Pruning and Mixed-Precision Quantization for LLM Compression
arXiv:2606. 07819v1 Announce Type: new Abstract: Recently, the efficiency of Large Language Models (LLMs) deployment has become a critical concern in practical applications.
arXiv Machine Learning
Jun 4
AlphaQ: Calibration-Free Bit Allocation for Mixture-of-Experts Quantization
arXiv:2606. 04980v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures scale model capacity through sparse expert activation, but their deployment remains memory-bound because all expert weights must reside in memory.
arXiv AI
Jun 4
Recover-LoRA for Aggressive Quantization: Reclaiming Accuracy in 2-Bit Language Models via Low-Rank Adaptation with Knowledge Distillation on Synthetic Data
arXiv:2606. 04238v1 Announce Type: cross Abstract: Aggressive weight quantization to 2-bit precision offers substantial throughput and memory gains for large language model (LLM) inference, but typically incurs severe accuracy degradation.
arXiv AI
Aug 20
Entropy-Constrained Adaptive Stochastic Quantization
arXiv:2608. 18147v1 Announce Type: cross Abstract: Adaptive stochastic quantization (ASQ) is a recently introduced quantization approach that optimizes the Mean Squared Error (MSE) for a given input while preserving unbiasedness.
arXiv AI
Jun 2
BitsMoE: Efficient Spectral Energy-Guided Bit Allocation for MoE LLM Quantization
arXiv:2606. 00079v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) large language models reduce per-token computation through sparse expert activation, but their deployment remains memory-intensive because all expert weights must be kept resident in memory.
arXiv Machine Learning
Aug 12
ReRound: Reconstructive Rounding to Resolve Midpoint Ambiguity in Calibration-Free LLM Quantization
arXiv:2608. 11045v1 Announce Type: new Abstract: ReRound (Reconstructive Rounding) is a post-training quantization method that addresses the midpoint ambiguity inherent in standard round-to-nearest (RTN) schemes when quantizing weights near the centers of quantization intervals.
arXiv AI
Sep 10
SQS: Bayesian DNN Compression through Sparse Quantized Sub-distributions
arXiv:2510.08999v2 Announce Type: replace-cross Abstract: Compressing large-scale neural networks is essential for deploying models on resource-constrained devices. Most existing methods adopt weight...
arXiv Machine Learning
Jun 2
Inner Product Aware Quantization: Provably Fast, Accurate, and Adaptive Algorithms
arXiv:2606. 00289v1 Announce Type: new Abstract: Quantization is a fundamental tool used to compress datasets, neural network weights, and memory usage in a range of computational tasks.