On The Robustness-Resolution Tradeoff In Temporal Quantization Of Event Streams

2026-09-14

AI Summary

研究解决了事件流时间量化中的鲁棒性-分辨率权衡问题，通过定义一类连续编码器并证明其全局L1敏感度下限，实验表明线性插值能有效降低表示漂移。

Abstract

Event pipelines often discretize asynchronous timestamps before learning. This step looks harmless, but its stability depends directly on temporal resolution. We study this dependence at the representation level. We first show that hard temporal binning is discontinuous: an arbitrarily small timestamp shift near a boundary can move unit event mass between bins. We then define a class of nonnegative, mass-preserving, resolution-faithful continuous encoders and prove that every encoder in this class has global L1 sensitivity at least 2/Delta, where Delta denotes bin width. Linear two-bin interpolation attains this limit. Local support and first-moment preservation also make it unique. Experiments on SHD, N-MNIST, and DVS128 Gesture support the analysis. Across uniform timestamp budgets, linear interpolation lowers mean representation drift by 47-72% while keeping clean accuracy nearly unchanged. On DVS Gesture, it produces zero prediction flips across all tested budgets and three seeds. On SHD, measured drift follows 1/Delta with R^2 = 0.992.

Problem

• Temporal Quantization
• Event Streams
• Robustness-Resolution Tradeoff
• Temporal Resolution
• Discretization

Innovation

• Temporal Quantization
• Continuous Encoders
• Global L1 Sensitivity
• Linear Interpolation
• Representation Drift