Research Papers 论文研究 4h ago Updated 21m ago 更新于 21分钟前 48

Calibration-Preserving Pruning: Compression as a Reliability Contract 保校准剪枝:压缩作为可靠性契约

Calibration-Preserving Pruning (CPP) combines base pruning scores with nonconformity-gradient saliency to compress models while preserving prediction-set efficiency under conformal prediction Split conformal prediction guarantees finite-sample marginal coverage independently of the pruning rule; CPP addresses the separate efficiency problem of producing smaller valid prediction sets On Qwen2.5-1.5B at 50% sparsity, CPP-SparseGPT reduced mean set size from 10.1 to 8.6 on DBpedia-14 with improved 提出校准保持剪枝(CPP)方法,通过非共形梯度显著性增强基础剪枝分数,在模型压缩同时保持预测可靠性 分割共形预测而非剪枝规则本身提供有限样本边际覆盖率,CPP解决的是效率问题:能否保留足够好的分数几何结构以获得更小的有效预测集 在Qwen2.5-1.5B模型50%稀疏度实验中,CPP-SparseGPT在DBpedia-14上将平均预测集大小从10.1降至8.6,准确率从0.347提升至0.366 匹配控制实验表明通用监督梯度解释了大部分性能增益,阈值感知候选标签CPP在显式准确率约束下达到7.8的平均集合大小 方法在RoBERTa-base和Llama-3-8B上验证了迁移性,但结论仅限于可

62
Hot 热度
76
Quality 质量
68
Impact 影响力

Analysis 深度分析

TL;DR

  • Calibration-Preserving Pruning (CPP) combines base pruning scores with nonconformity-gradient saliency to compress models while preserving prediction-set efficiency under conformal prediction
  • Split conformal prediction guarantees finite-sample marginal coverage independently of the pruning rule; CPP addresses the separate efficiency problem of producing smaller valid prediction sets
  • On Qwen2.5-1.5B at 50% sparsity, CPP-SparseGPT reduced mean set size from 10.1 to 8.6 on DBpedia-14 with improved accuracy (0.347→0.366), outperforming baseline Wanda
  • Matched controls reveal that generic supervised gradients account for much of CPP's gain; true-label CPP is statistically indistinguishable from Wanda+SNIP, while threshold-aware candidate-label CPP achieves 7.8 mean set size at explicit accuracy and offline-compute costs
  • Results generalize across RoBERTa-base and Llama-3-8B diagnostics but claims are limited to reliability-sensitive classification tasks

Why It Matters

This work bridges model compression and statistical reliability, showing that pruning can be designed not just for accuracy retention but for conformal prediction efficiency—a critical concern for deployed AI systems where prediction-set calibration directly impacts trust and safety. For practitioners deploying pruned models in high-stakes classification settings, CPP offers a principled path to smaller, valid prediction sets without sacrificing coverage guarantees.

Technical Details

  • CPP augments a base pruning score (SparseGPT or Wanda) with nonconformity-gradient saliency, using four disjoint data splits: pruning, validation-selection, conformal-calibration, and test
  • Theoretical analysis shows bounded score perturbations imply bounded conformal-quantile shifts and controlled prediction-set inflation, though the generic coverage theorem is not CPP-specific
  • Empirical evaluation on Qwen2.5-1.5B at 50% sparsity across 15 dataset-sparsity cells: CPP-SparseGPT produced smaller sets in 13/15 and higher accuracy in 11/15 compared to baselines
  • Threshold-aware candidate-label CPP reaches a mean set size of 7.8 on DBpedia-14 with explicit accuracy and offline-compute costs, outperforming true-label variants
  • Transfer diagnostics on RoBERTa-base and Llama-3-8B support generalization, though the framework is currently limited to classification tasks requiring reliability guarantees

Industry Insight

  • As AI systems face increasing regulatory scrutiny around uncertainty quantification, pruning methods that preserve conformal coverage guarantees will become essential for deploying compressed models in regulated domains like healthcare and finance
  • The finding that generic supervised gradients explain much of CPP's gain suggests practitioners can achieve similar efficiency improvements through simpler gradient-based pruning without the overhead of conformal-aware scoring, depending on their compute constraints
  • The trade-off between offline-compute costs and prediction-set efficiency in threshold-aware CPP highlights a practical design decision: organizations should invest in candidate-label CPP only when downstream prediction-set size directly impacts latency or cost constraints

TL;DR

  • 提出校准保持剪枝(CPP)方法,通过非共形梯度显著性增强基础剪枝分数,在模型压缩同时保持预测可靠性
  • 分割共形预测而非剪枝规则本身提供有限样本边际覆盖率,CPP解决的是效率问题:能否保留足够好的分数几何结构以获得更小的有效预测集
  • 在Qwen2.5-1.5B模型50%稀疏度实验中,CPP-SparseGPT在DBpedia-14上将平均预测集大小从10.1降至8.6,准确率从0.347提升至0.366
  • 匹配控制实验表明通用监督梯度解释了大部分性能增益,阈值感知候选标签CPP在显式准确率约束下达到7.8的平均集合大小
  • 方法在RoBERTa-base和Llama-3-8B上验证了迁移性,但结论仅限于可靠性敏感的分类任务

为什么值得看

本文在模型压缩与可靠性保障的交叉领域提供了新的理论视角和实践方法,证明压缩与校准并非零和博弈。对于部署高可靠性AI系统的从业者,CPP提供了一种在保持统计保证的同时提升压缩效率的可行路径。

技术解析

  • CPP采用四分割策略:分离的剪枝、验证选择、共形校准和测试分割,确保评估的无偏性;理论证明有界分数扰动可推导有界的共形分位数偏移和可控的集合膨胀
  • 实验基于Qwen2.5-1.5B,在15个数据集-稀疏度组合中,CPP-SparseGPT在13个组合中产生更小的预测集,在11个组合中提高准确率
  • 与Wanda和SNIP的匹配对照显示,真实标签CPP与Wanda+SNIP在统计上无法区分,但阈值感知的候选标签CPP在离线计算成本下实现了更优的集合效率
  • 理论贡献在于澄清了共形预测的通用覆盖定理与CPP具体方法的关系:有界扰动保证通用覆盖,但不使覆盖定理成为CPP特有

行业启示

  • 模型压缩不应仅关注准确率或稀疏度指标,可靠性校准是工业部署的关键维度,CPP框架为压缩模型的可靠性评估提供了标准化方法
  • 梯度显著性作为剪枝指导信号的有效性得到验证,未来可探索更精细的梯度融合策略以进一步平衡压缩率与预测集效率
  • 共形预测与模型压缩的结合代表了AI可靠性工程的重要趋势,建议在高风险应用场景(医疗、金融、自动驾驶)中优先采用此类校准保持的压缩方案

Disclaimer: The above content is generated by AI and is for reference only. 免责声明:以上内容由 AI 生成,仅供参考。

Research 科学研究 Quantization 量化 Inference 推理