评估动态训练后量化中灾难性失效的可能性
Assessing the Potential for Catastrophic Failure in Dynamic Post-Training Quantization
AI总结：
该研究针对动态训练后量化可能引发的灾难性失效问题，通过知识蒸馏与强化学习任务学习网络-位宽策略对，证实存在准确率下降10%-65%的有害组合，强调了PTQ实际部署需谨慎并应重视鲁棒性与安全研究。
摘要：
训练后量化（Post-training quantization, PTQ）是近期兴起的一种有效技术，它通过用更低精度表示神经网络的权重与激活值，来降低网络的计算复杂度与内存占用。尽管这一范式在降低计算与存储成本方面已取得显著成效，但根据推理过程中遇到的输入分布不同，模型性能可能会出现大幅下降。在考虑将其部署于安全关键环境时，研究潜在性能下降的程度，以及输入分布的哪些特征可能导致这种下降至关重要。在本研究中，我们探究了动态PTQ引发极端失效的问题，并构建了一个知识蒸馏与强化学习任务，用于学习网络与位宽策略的组合对，从而从最坏情况潜力的角度分析量化下的灾难性失效。我们的结果证实了这类“有害”网络-策略对的存在：多个实例显示，与性能下降不足2%的“鲁棒”对应组相比，有害组的准确率下降幅度在10%-65%之间。通过系统的实验与分析，我们还对最高脆弱性节点进行了初步探索。尽管我们的结果是理解PTQ引入的失效案例的初步一步，但我们的发现最终强调了在实际部署场景中保持谨慎的必要性。我们希望这项工作能推动更严格的鲁棒性检验，并让深度学习更广泛领域的未来研究更重视安全考量。
英文摘要：
Post-training quantization (PTQ) has recently emerged as an effective tool for reducing the computational complexity and memory usage of a neural network by representing its weights and activations with lower precision. While this paradigm has shown great success in lowering compute and storage costs, there is the potential for drastic performance reduction depending upon the distribution of inputs experienced in inference. When considering possible deployment in safety-critical environments, it is important to investigate the extent of potential performance reduction, and what characteristics of input distributions may give rise to this reduction. In this work, we explore the idea of extreme failure stemming from dynamic PTQ and formulate a knowledge distillation and reinforcement learning task to learn a network and bit-width policy pair such that catastrophic failure under quantization is analyzed in terms of worst case potential. Our results confirm the existence of this "detrimental" network-policy pair, with several instances demonstrating performance reductions in the range of 10-65% in accuracy, compared to their "robust" counterparts encountering a <2% decrease. From systematic experimentation and analyses, we also provide an initial exploration into points at highest vulnerability. While our results represent an initial step toward understanding failure cases introduced by PTQ, our findings ultimately emphasize the need for caution in real-world deployment scenarios. We hope this work encourages more rigorous examinations of robustness and a greater emphasis on safety considerations for future works within the broader field of deep learning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
