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

arXiv: https://arxiv.org/abs/2609.22295 · HTML: https://mlsanity.com/paper/2609.22295/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 21 references that are in the map.
- First posted on arXiv 14 Sep 2026.

## Builds on (most cited first, 14 of 14)

- [Event-based Vision: A Survey](https://mlsanity.com/paper/1904.08405/) (2019)
- [Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccades](https://mlsanity.com/paper/1507.07629/) (2015)
- [Unsupervised Event-based Learning of Optical Flow, Depth, and Egomotion](https://mlsanity.com/paper/1812.08156/) (2018)
- [HATS: Histograms of Averaged Time Surfaces for Robust Event-based Object Classification](https://mlsanity.com/paper/1803.07913/) (2018)
- [End-to-End Learning of Representations for Asynchronous Event-Based Data](https://mlsanity.com/paper/1904.08245/) (2019)
- [The Heidelberg spiking datasets for the systematic evaluation of spiking neural networks](https://mlsanity.com/paper/1910.07407/) (2019)
- [Towards Anytime Optical Flow Estimation with Event Cameras](https://mlsanity.com/paper/2307.05033/) (2023)
- [EventFly: Event Camera Perception from Ground to the Sky](https://mlsanity.com/paper/2503.19916/) (2025)
- [Adversarial Attack for Asynchronous Event-based Data](https://mlsanity.com/paper/2112.13534/) (2021)
- [Adversarial Attacks on Event-Based Pedestrian Detectors: A Physical Approach](https://mlsanity.com/paper/2503.00377/) (2025)
- [Time Is All It Takes: Spike-Retiming Attacks on Event-Driven Spiking Neural Networks](https://mlsanity.com/paper/2602.03284/) (2026)
- [Making Every Event Count: Balancing Data Efficiency and Accuracy in Event Camera Subsampling](https://mlsanity.com/paper/2505.21187/) (2025)
- [A Systematic Survey on Event Camera Representation Learning](https://mlsanity.com/paper/2606.23078/) (2026)
- [Efficient Multi-Timescale Event Representations for Feed-Forward Object Detection](https://mlsanity.com/paper/2609.05049/) (2026)

## Abstract (arXiv)

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.