REVIEW 7 cited by
When can classical neural networks represent quantum states?
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
A naive classical representation of an n-qubit state requires specifying exponentially many amplitudes in the computational basis. Past works have demonstrated that classical neural networks can succinctly express these amplitudes for many physically relevant states, leading to computationally powerful representations known as neural quantum states. What underpins the efficacy of such representations? We show that conditional correlations present in the measurement distribution of quantum states control the performance of their neural representations. Such conditional correlations are basis dependent, arise due to measurement-induced entanglement, and reveal features not accessible through conventional few-body correlations often examined in studies of phases of matter. By combining theoretical and numerical analysis, we demonstrate how the state's entanglement and sign structure, along with the choice of measurement basis, give rise to distinct patterns of short- or long-range conditional correlations. Our findings provide a rigorous framework for exploring the expressive power of neural quantum states.
Forward citations
Cited by 7 Pith papers
-
Mechanistic Interpretability and Causal Feature Steering of Neural Quantum States via Sparse Autoencoders
Sparse autoencoders applied to Neural Quantum States extract unsupervised features correlating with and causally steering physical observables such as order parameters while preserving variational energy.
-
WF-Bench: A Benchmark for Neural Network WaveFunction Expressivity and Scaling Laws
WF-Bench is a new benchmark for neural network wavefunctions that matches them to diverse quantum many-body targets and derives empirical scaling laws for representability based on system size and model parameters lik...
-
Geometry-Induced Long-Range Correlations in Recurrent Neural Network Quantum States
Dilated RNN wave functions induce power-law correlations for the critical 1D transverse-field Ising model and the Cluster state, unlike the exponential decay of conventional RNN ansatze.
-
Learning quantum ground states in the space of measurement outcomes
Variational optimization of quantum ground states represented as SIC-POVM outcome probabilities using GRU autoregressive networks, tested on 1D Ising and Heisenberg models up to L=128.
-
Exploring the Effect of Basis Rotation on NQS Performance
Basis rotation of the Ising ground state relocates the target in the NQS parameter space and can cause shallow networks to converge to low-energy but wrong wavefunctions.
-
Quantum Complexity and New Directions in Nuclear Physics and High-Energy Physics Phenomenology
A review of how quantum information science is expected to provide new tools and insights for nuclear and high-energy physics phenomenology and quantum simulations.
-
Artificial intelligence for representing and characterizing quantum systems
A review organizes AI-based quantum system characterization into ML, deep learning, and language model paradigms, covering property prediction and implicit state reconstruction.
Discussion (0). Sign in to comment.