AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Statistical Analysis of Quantum State Learning Process in Quantum Neural Networks

Hao-Kai Zhang, Chenghong Zhu, Mingrui Jing, Xin Wang

NeurIPS 2023 · Learning theory and algorithms › Prediction and decision losses · approach: Theory of neural network sensitivity · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
increase qubit count N of the ALT circuitALT QNN learning a random target state (p=0.2) · Loss curves, N in {2,6,10}, D in {1,3,5}convergent fidelity lossHurt
increase circuit depth D of the ALT circuitALT QNN learning a random target state (p=0.2) · Loss curves, N in {2,6,10}, D in {1,3,5}convergent fidelity lossImproved
increase qubit count from N=1 to 11ALT QNN with D=5 · Probability evaluation, 200 sampled targetsprobability of being a local minimumHurt
increase the number of trainable parameters being differentiatedALT QNN with D=5 · Probability evaluation, 200 sampled targetsprobability of being a local minimumImproved
increase qubit count from N=4 to N=10ALT QNN landscape profiles · Landscape profile sampling, p=0.2 and p=0.8landscape convexity around theta*Hurt
raise initial overlap p from 0.2 to 0.8ALT QNN landscape profiles · Landscape profile sampling, N=10local minimum curvatureMixed
start from a high-fidelity initial state with simplistic adaptive layer appendingQNN state learning · theory discussionlearnabilityNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy