When Can Depth Replace Precision? A Resource Theory of Quantized Neural Computation
深度何时能取代精度?量化神经计算的资源理论
机构 * University of Illinois Chicago(伊利诺伊大学芝加哥分校)
AI总结 研究固定输入输出映射下低比特残差计算能否取代数值精度,通过建模量化残差系统刻画无限深度极限,得出纯调度接近松弛类的速率等结论,还探讨了多种相关情况,指出深度取代精度有条件限制。
Comments 141 pages, 26 figures, 15 tables. Includes complete proofs and documents the QReplace decision-support and Lean 4 verification companions. To be submitted to the Journal of Machine Learning Research