REVIEW 18 cited by
BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
We study the challenging task of neural network quantization without end-to-end retraining, called Post-training Quantization (PTQ). PTQ usually requires a small subset of training data but produces less powerful quantized models than Quantization-Aware Training (QAT). In this work, we propose a novel PTQ framework, dubbed BRECQ, which pushes the limits of bitwidth in PTQ down to INT2 for the first time. BRECQ leverages the basic building blocks in neural networks and reconstructs them one-by-one. In a comprehensive theoretical study of the second-order error, we show that BRECQ achieves a good balance between cross-layer dependency and generalization error. To further employ the power of quantization, the mixed precision technique is incorporated in our framework by approximating the inter-layer and intra-layer sensitivity. Extensive experiments on various handcrafted and searched neural architectures are conducted for both image classification and object detection tasks. And for the first time we prove that, without bells and whistles, PTQ can attain 4-bit ResNet and MobileNetV2 comparable with QAT and enjoy 240 times faster production of quantized models. Codes are available at https://github.com/yhhhli/BRECQ.
Forward citations
Cited by 18 Pith papers
-
FPTQuant: Function-Preserving Transforms for LLM Quantization
FPTQuant introduces function-preserving transforms that make transformer activations amenable to static 4-bit quantization with minimal inference overhead.
-
Task-Specific Zero-shot Quantization-Aware Training for Object Detection
A zero-shot quantization-aware training method for object detectors that synthesizes task-specific images with bounding-box labels via adaptive label sampling, then distills task-specific knowledge into the quantized network.
-
DMQ: Dissecting Outliers of Diffusion Models for Post-Training Quantization
A post-training quantization method that combines learned channel scaling and power-of-two scaling keeps diffusion image quality high at 4-bit weight, 6-bit activation precision.
-
TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision
TruncQuant uses a floor-based quantizer with 2^n scaling instead of rounding with 2^n-1, so truncating high-precision weights via bit-shift exactly matches direct low-precision quantization, recovering accuracy lost b...
-
BASE-Q: Bias and Asymmetric Scaling Enhanced Rotational Quantization for Large Language Models
BASE-Q combines bias correction and asymmetric scaling under fixed rotations to improve 4-bit weight-activation quantization, narrowing the accuracy gap to full precision by up to 50.5% over prior rotation-based methods.
-
Saliency-Aware Quantized Imitation Learning for Efficient Robotic Control
A saliency-weighted quantization-aware training method lets 4-bit quantized imitation-learning policies match full-precision success rates across robot manipulation, driving, and control benchmarks.
-
Loss Landscape Analysis for Reliable Quantized ML Models for Scientific Sensing
Loss landscape flatness and connectivity visually correlate with robustness to noise and bit flips in two quantized scientific sensing models, but the correlation is not quantified and the a priori claim remains unvalidated.
-
Efficient Reasoning on the Edge
LoRA adapters, budget-forced GRPO, dynamic switching, parallel verification and FPTQuant enable practical chain-of-thought reasoning on quantized Qwen2.5-7B for edge devices.
-
Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models
Using CMA-ES to jointly optimize activation quantization scales keeps speech-model accuracy near full precision under full INT8 and INT4 quantization.
-
Harnessing Input-Adaptive Inference for Efficient VLN
A three-part input-adaptive inference method (view masking, adaptive early exit, view caching) cuts VLN computation roughly in half on seven benchmarks with moderate success-rate loss.
-
Compress Any Segment Anything Model (SAM)
Birkhoff compresses 18 SAM variants to about one-fifth their size with less than 1% accuracy loss, data-free, using a trajectory-based codebook and a fused GPU operator.
-
PQCAD-DM: Progressive Quantization and Calibration-Assisted Distillation for Extremely Efficient Diffusion Model
PQCAD-DM combines progressive two-stage quantization with calibration-assisted distillation to halve the sampling steps of a quantized diffusion model while keeping FID scores close to baseline.
-
Post-Training Quantization for Video Matting
PTQ4VM applies block-wise, globally affine-calibrated, optical-flow-guided post-training quantization to video matting, reaching near full-precision accuracy at 4-bit weights and activations.
-
MixFrag: Fragility-Guided Mixed-Precision Post-Training Quantization for Vision Transformers
KL-isolation fragility plus MCKP bit allocation yields mixed-precision ViT PTQ that lags recent ImageNet PTQ but reports large COCO AP gains at MP3/MP3.
-
Cross-Layer Error Compensation and Finite-Sample Feature-Statistics Matching for Extreme Low-Bit Quantization of Large Language Models
A whole-network final-feature and statistics matching objective improves 1.125-bit and 4.125-bit LLM quantization over layer-local and distillation baselines, but its cross-layer mechanism reduces exactly to final-fea...
-
Progressive Element-wise Gradient Estimation for Neural Network Quantization
PEGE replaces the straight-through estimator with a curriculum-driven blend of quantized and full-precision weights plus an additive discretization-error correction, reporting small accuracy gains on low-bit CNNs.
-
Rethinking the Outlier Distribution in Large Language Models: An In-depth Study
The paper claims that most massive activations in LLMs are residual-propagated 'fake' outliers that can be removed without accuracy loss.
-
Can Post-Training Quantization Benefit from an Additional QLoRA Integration?
Adding QLoRA on top of a 4-bit post-training quantized LLM improves task accuracy over quantization alone, and can match or beat full 16-bit fine-tuning on some tasks.
Discussion (0). Continue with ORCID to comment.