AI-enhanced tuning of quantum dot Hamiltonians toward Majorana modes

2026-01-05

AI Summary

This work proposes an unsupervised deep Vision Transformer architecture embedded with physical priors to efficiently tune the Hamiltonian of quantum dots for robust realization of Majorana zero modes. Leveraging transport conductance maps, the method establishes an end-to-end mapping from experimental measurements to Hamiltonian parameters, enabling both single-step and iterative tuning strategies. By innovatively integrating physical constraints into an unsupervised learning framework, the approach can generate nontrivial Majorana zero modes from widely detuned initial states with only a single update. Iterative refinement further substantially expands the accessible topological parameter space, enhancing the feasibility and stability of topological phase engineering in semiconductor-superconductor hybrid systems.

Technology Category

• Machine Learning: Quantum Machine Learning
• Computer Vision: Multi-modal Vision
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Security and Privacy: Large-scale security measurements

Abstract

We propose a neural network-based model capable of learning the broad landscape of working regimes in quantum dot simulators, and using this knowledge to autotune these devices - based on transport measurements - toward obtaining Majorana modes in the structure. The model is trained in an unsupervised manner on synthetic data in the form of conductance maps, using a physics-informed loss that incorporates key properties of Majorana zero modes. We show that, with appropriate training, a deep vision-transformer network can efficiently memorize relation between Hamiltonian parameters and structures on conductance maps and use it to propose parameters update for a quantum dot chain that drive the system toward topological phase. Starting from a broad range of initial detunings in parameter space, a single update step is sufficient to generate nontrivial zero modes. Moreover, by enabling an iterative tuning procedure - where the system acquires updated conductance maps at each step - we demonstrate that the method can address a much larger region of the parameter space.

Problem

• Majorana modes
• quantum dot
• topological phase
• Hamiltonian tuning
• conductance maps

Innovation

• neural network
• Majorana zero modes
• quantum dot
• physics-informed learning
• autotuning