Gradient-Based Post-Training Quantization: Challenging the Status Quo

• URL: http://arxiv.org/abs/2308.07662v1
• Date: Tue, 15 Aug 2023 09:25:11 GMT
• Title: Gradient-Based Post-Training Quantization: Challenging the Status Quo
• Authors: Edouard Yvinec, Arnaud Dapogny and Kevin Bailly
• Abstract summary: Quantization has become a crucial step for the efficient deployment of deep neural networks. In this work, we show that the process is, to a certain extent, robust to a number of variables. We derive a number of best practices for designing more efficient and scalable GPTQ methods.
• Score: 23.1120983784623
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Quantization has become a crucial step for the efficient deployment of deep neural networks, where floating point operations are converted to simpler fixed point operations. In its most naive form, it simply consists in a combination of scaling and rounding transformations, leading to either a limited compression rate or a significant accuracy drop. Recently, Gradient-based post-training quantization (GPTQ) methods appears to be constitute a suitable trade-off between such simple methods and more powerful, yet expensive Quantization-Aware Training (QAT) approaches, particularly when attempting to quantize LLMs, where scalability of the quantization process is of paramount importance. GPTQ essentially consists in learning the rounding operation using a small calibration set. In this work, we challenge common choices in GPTQ methods. In particular, we show that the process is, to a certain extent, robust to a number of variables (weight selection, feature augmentation, choice of calibration set). More importantly, we derive a number of best practices for designing more efficient and scalable GPTQ methods, regarding the problem formulation (loss, degrees of freedom, use of non-uniform quantization schemes) or optimization process (choice of variable and optimizer). Lastly, we propose a novel importance-based mixed-precision technique. Those guidelines lead to significant performance improvements on all the tested state-of-the-art GPTQ methods and networks (e.g. +6.819 points on ViT for 4-bit quantization), paving the way for the design of scalable, yet effective quantization methods.

Related papers

• PTQ1.61: Push the Real Limit of Extremely Low-Bit Post-Training Quantization Methods for Large Language Models [64.84734437930362]
  Large Language Models (LLMs) suffer severe performance degradation when facing extremely low-bit (sub 2-bit) quantization. We propose an extremely low-bit PTQ method called PTQ1.61, which enables weight quantization to 1.61-bit for the first time. Experiments indicate our PTQ1.61 achieves state-of-the-art performance in extremely low-bit quantization.
  arXiv  Detail & Related papers  (2025-02-18T08:04:58Z)
• RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models [95.32315448601241]
  We propose an algorithm named Rotated Straight-Through-Estimator (RoSTE) RoSTE combines quantization-aware supervised fine-tuning (QA-SFT) with an adaptive rotation strategy to reduce activation outliers. Our findings reveal that the prediction error is directly proportional to the quantization error of the converged weights, which can be effectively managed through an optimized rotation configuration.
  arXiv  Detail & Related papers  (2025-02-13T06:44:33Z)
• Rethinking Post-Training Quantization: Introducing a Statistical Pre-Calibration Approach [22.25748046511075]
  Post-training Quantization (PTQ) techniques rely on calibration processes to maintain their accuracy. We propose a weight-adaptive PTQ method that can be considered a precursor to calibration-based PTQ methods. We show that our proposed approach can perform on par with most common calibration-based PTQ methods.
  arXiv  Detail & Related papers  (2025-01-15T19:44:15Z)
• Gradient-based Automatic Mixed Precision Quantization for Neural Networks On-Chip [0.9187138676564589]
  We present High Granularity Quantization (HGQ), an innovative quantization-aware training method. HGQ fine-tune the per-weight and per-activation precision by making them optimizable through gradient descent. This approach enables ultra-low latency and low power neural networks on hardware capable of performing arithmetic operations.
  arXiv  Detail & Related papers  (2024-05-01T17:18:46Z)
• EPTQ: Enhanced Post-Training Quantization via Hessian-guided Network-wise Optimization [3.3998740964877463]
  Quantization is a key method for deploying deep neural networks on edge devices with limited memory and computation resources. We propose a new method for enhanced Post-Training Quantization (EPTQ) that employs a network-wise quantization optimization process.
  arXiv  Detail & Related papers  (2023-09-20T10:50:28Z)
• Norm Tweaking: High-performance Low-bit Quantization of Large Language Models [21.855106896725598]
  We introduce a technique called norm tweaking, which can be used as a plugin in current PTQ methods to achieve high precision. Our method demonstrates significant improvements in both weight-only quantization and joint quantization of weights and activations. Our simple and effective approach makes it more practical for real-world applications.
  arXiv  Detail & Related papers  (2023-09-06T06:51:15Z)
• PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models [52.09865918265002]
  We propose a novel quantize before fine-tuning'' framework, PreQuant. PreQuant is compatible with various quantization strategies, with outlier-aware fine-tuning incorporated to correct the induced quantization error. We demonstrate the effectiveness of PreQuant on the GLUE benchmark using BERT, RoBERTa, and T5.
  arXiv  Detail & Related papers  (2023-05-30T08:41:33Z)
• Gradient-descent quantum process tomography by learning Kraus operators [63.69764116066747]
  We perform quantum process tomography (QPT) for both discrete- and continuous-variable quantum systems. We use a constrained gradient-descent (GD) approach on the so-called Stiefel manifold during optimization to obtain the Kraus operators. The GD-QPT matches the performance of both compressed-sensing (CS) and projected least-squares (PLS) QPT in benchmarks with two-qubit random processes.
  arXiv  Detail & Related papers  (2022-08-01T12:48:48Z)
• Cluster-Promoting Quantization with Bit-Drop for Minimizing Network Quantization Loss [61.26793005355441]
  Cluster-Promoting Quantization (CPQ) finds the optimal quantization grids for neural networks. DropBits is a new bit-drop technique that revises the standard dropout regularization to randomly drop bits instead of neurons. We experimentally validate our method on various benchmark datasets and network architectures.
  arXiv  Detail & Related papers  (2021-09-05T15:15:07Z)
• FLIP: A flexible initializer for arbitrarily-sized parametrized quantum circuits [105.54048699217668]
  We propose a FLexible Initializer for arbitrarily-sized Parametrized quantum circuits. FLIP can be applied to any family of PQCs, and instead of relying on a generic set of initial parameters, it is tailored to learn the structure of successful parameters. We illustrate the advantage of using FLIP in three scenarios: a family of problems with proven barren plateaus, PQC training to solve max-cut problem instances, and PQC training for finding the ground state energies of 1D Fermi-Hubbard models.
  arXiv  Detail & Related papers  (2021-03-15T17:38:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.