Using maximally entangled training data exponentially flattens the loss landscape of highly expressive quantum models, limiting the loss improvement achievable in a fixed-size neighborhood.
On the differential topology of expressivity of parame- terized quantum circuits.AppliedMath, 5(3):121, 2025
1 Pith paper cite this work, alongside 2 external citations. Polarity classification is still indexing.
1
Pith paper citing it
2
external citations · OpenAlex
fields
quant-ph 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Loss Behavior in Supervised Learning with Entangled States
Using maximally entangled training data exponentially flattens the loss landscape of highly expressive quantum models, limiting the loss improvement achievable in a fixed-size neighborhood.