# A Non-Uniform Quantization Framework for Time-Encoding Machines

arXiv: https://arxiv.org/abs/2511.02728 · HTML: https://mlsanity.com/paper/2511.02728/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 28 references that are in the map.
- First posted on arXiv 4 Nov 2025.

## Builds on (most cited first, 3 of 3)

- [FRI-TEM: Time Encoding Sampling of Finite-Rate-of-Innovation Signals](https://mlsanity.com/paper/2106.05564/) (2021)
- [Adaptive Integrate-and-Fire Time Encoding Machine with Quantization](https://mlsanity.com/paper/2403.02992/) (2024)
- [Smart structural health monitoring (SHM) system for on-board localization of defects in pipes using torsional ultrasonic guided waves](https://mlsanity.com/paper/2403.11110/) (2024)

## Built on by (most cited first, 1 of 1)

- [Compute Only Once: UG-Separation for Efficient Large Recommendation Models](https://mlsanity.com/paper/2602.10455/) (2026)

## Abstract (arXiv)

Time encoding machines (TEMs) provide an event-driven alternative to classical uniform sampling, enabling power-efficient representations without a global clock. While prior work analyzed uniform quantization (UQ) of firing intervals, we show that these intervals are inherently non-uniformly distributed, motivating the use of non-uniform quantization (NUQ). We derive the probability distribution of firing intervals for a class of bandlimited signals and design a power-law-based NUQ scheme tailored to this distribution. Simulations demonstrate that NUQ significantly outperforms UQ under the same bit budget. We also compare TEMs with non-uniform sampling (NUS), where both amplitudes and timings require quantization, and show that TEM--NUQ achieves lower error at half the transmission cost. These results highlight the advantages of distribution-aware quantization and establish TEM--NUQ as an efficient alternative to conventional UQ and NUS schemes.