Abstract

Fault-tolerant topological quantum computing relies on identifying Majorana zero modes (MZMs), but reliable detection in realistic devices remains challenging. Conventional topological indicators become inherently biased in finite, disordered systems, blurring the distinction between true MZMs and trivial states, and attempts to map these indicators to real observables via machine learning require dense, expensive conductance measurements. MEDA, a Measurement-Efficient, Disorder-Aware framework, addresses both limitations at once by mapping sparse, practically obtainable observables directly to the robust periodic disorder invariant (PDI). Using a novel sparse parameter regime, MEDA reduces measurement volume by 10x while maintaining predictive quality, even in moderate to strong disorder regimes that limit conventional methods, and naturally prioritizes input features consistent with the topological gap protocol.

Accepted to the 2026 IEEE International Conference on Quantum Computing and Engineering (QCE).