Schrodinger Neural Network and Uncertainty Quantification: Quantum Machine

TL;DR

The paper introduces the Schrodinger Neural Network (SNN), a quantum-inspired architecture for conditional density estimation and uncertainty quantification that offers advantages like positivity, normalization, and multimodality.

Contribution

It presents a novel quantum mechanics-inspired neural network architecture that improves probabilistic predictions and uncertainty quantification in machine learning.

Findings

Provides a new architecture for density estimation with guaranteed positivity and normalization.

Enables native multimodality through interference among basis modes.

Offers scalable and extensible methods for multivariate outputs and operator-based extensions.

Abstract

We introduce the Schrodinger Neural Network (SNN), a principled architecture for conditional density estimation and uncertainty quantification inspired by quantum mechanics. The SNN maps each input to a normalized wave function on the output domain and computes predictive probabilities via the Born rule. The SNN departs from standard parametric likelihood heads by learning complex coefficients of a spectral expansion (e . g ., Chebyshev polynomials) whose squared modulus yields the conditional density $p(y|x)=\left| \psi _x(y)\right| {}^2$ with analytic normalization. This representation confers three practical advantages: positivity and exact normalization by construction, native multimodality through interference among basis modes without explicit mixture bookkeeping, and yields closed-form (or efficiently computable) functionals$-$such as moments and several calibration diagnostics$-$as quadratic forms in coefficient space. We develop the statistical and computational foundations of the SNN, including (i) training by exact maximum-likelihood with unit-sphere coefficient parameterization, (ii) physics-inspired quadratic regularizers (kinetic and potential energies) motivated by uncertainty relations between localization and spectral complexity, (iii) scalable low-rank and separable extensions for multivariate outputs, (iv) operator-based extensions that represent observables, constraints, and weak labels as self-adjoint matrices acting on the amplitude space, and (v) a comprehensive framework for evaluating multimodal predictions. The SNN provides a coherent, tractable framework to elevate probabilistic prediction from point estimates to physically inspired amplitude-based distributions.