Conference Open access

FQTree: Fine-Grained Quantization and Hardware Generation of Boosted Decision Trees

Zhi-Qiang Que Chang Sun Haiyan Wang D. Pamunuwa R. Weerasekera Q. Tang B. Zadeh Wayne Luk M. Spiropulu

Aug 2026 · IEEE International Conference on Application-Specific Systems, Architectures, and Processors · pp. 57-64 · 0 citations · 25 references

Computer Science

TL;DR

This work presents the FQTree algorithm for fine-grained quantization-aware training of BDTs, together with the QXGB framework for automatic hardware generation, and applies this quantization during boosting so that later trees adapt to the errors of the already-quantized ensemble.

Abstract

Boosted decision trees (BDTs) are widely used in latency-critical applications, but efficient hardware deployment remains challenging. Existing designs often rely on uniform or manually tuned fixed-point formats, which can introduce unnecessary hardware cost or accuracy loss. This work presents the FQTree algorithm11https://github.com/ecs-bristol/FQTree for fine-grained quantization-aware training of BDTs, together with the QXGB framework for automatic hardware generation. FQTree introduces a hardware-oriented leaf-value quantization scheme that uses a global quantization step together with a tree-wise shift, enabling compact nonnegative integer leaf representations, controlled clipping/pruning, and bias folding to reduce datapath cost. This work further applies this quantization during boosting so that later trees adapt to the errors of the already-quantized ensemble, and then lowers the trained model into low-latency hardware implementations through a compiler-based flow. Results on JSC, MNIST, and NID show that our method reduces LUT usage by 26-57% compared with the state-of-the-art FPGA-based BDT designs while matching or improving accuracy.

DOI arXiv Semantic Scholar

Read PDF

Similar papers

Preprint Aug 2026

FluxBin: Flexible LUT-based Ultra-low-bit LLM Inference by Algorithm-Kernel Synergy

FluxBin is proposed, an algorithm-kernel co-design that synergizes post-training quantization with a highly optimized CUDA kernel and introduces Decoupled Row-Column Binary Decomposition to enhance representational capacity while maintaining hardware efficiency.

Qingyao Yang, Run-Ming Yang, He Xiao et al. · 0 citations

#machine learning Preprint Aug 2026

Fine-Tuning Low-Bit Models with Gradient in Quantized Code Space

This work proposes code surrogate gradient as the first order signal in deployable code space to acceleate optimization, and performs guided search to preserve deployment faithfulness in fine-tuning low-bit models across different quantization datatypes.

Shiguang Wu, Zhou-Chen Lin, Quan-Ming Yao · 1 citation

Jul 2026

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference

This work introduces MXSens, a training-free method that assigns mixed mantissa bitwidths (4/6/8) based on column- and layer-wise sensitivity, naturally leveraging the block-wise structure of MXINT, and establishes a new balance between accuracy and resource efficiency for LLM quantization.

Simla Burcu Harma, D. Mishin, Zheng-Yuan Su et al. · arXiv.org · 1 citation

Jul 2026

PolyQ: Codesigning End-to-End Quantization Framework for Scalable Edge CPU LLM Inference

PolyQ, a CPU-oriented compiler/quantization co-design for activation-aware channel-wise bit allocation under a user-specified average-bit budget, shows that fractional-bit CPU deployment is practical, predictable, and energy-efficient across diverse edge targets.

Hyunwoo Oh, Suyeon Jang, Hanning Chen et al. · arXiv.org · 0 citations

Jul 2026

Quantize with Confidence? An Empirical Study of Quantization for Code Generation

Six state-of-the-art quantization methods are evaluated on two representative large code model families using the multilingual McEval and CoderEval benchmarks for Python and Java to provide practical guidance for selecting quantization strategies for deploying large code models on resource-constrained hardware.

Saima Afrin, MD Zahidul Haque, A. Mastropaolo · arXiv.org · 0 citations

#machine learning Preprint Sep 2026

The Structure of Quantization Damage in LLMs: Why the Next Bit Should Be Spent Globally

Post-training quantization (PTQ) is widely used to reduce the cost of serving large language models (LLMs), but its accuracy cost is uneven and is often tuned per model. We study where quantization damage occurs and how to allocate a small additional precision budget. Using causal mixed-precision intervention as ground...

Jun-Hao Hu, S. Ramachandran · 1 citation