REVIEW 5 cited by
Beyond Barren Plateaus: Quantum Variational Algorithms Are Swamped With Traps
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
Signed reviews
read the original abstract
One of the most important properties of classical neural networks is how surprisingly trainable they are, though their training algorithms typically rely on optimizing complicated, nonconvex loss functions. Previous results have shown that unlike the case in classical neural networks, variational quantum models are often not trainable. The most studied phenomenon is the onset of barren plateaus in the training landscape of these quantum models, typically when the models are very deep. This focus on barren plateaus has made the phenomenon almost synonymous with the trainability of quantum models. Here, we show that barren plateaus are only a part of the story. We prove that a wide class of variational quantum models -- which are shallow, and exhibit no barren plateaus -- have only a superpolynomially small fraction of local minima within any constant energy from the global minimum, rendering these models untrainable if no good initial guess of the optimal parameters is known. We also study the trainability of variational quantum algorithms from a statistical query framework, and show that noisy optimization of a wide variety of quantum models is impossible with a sub-exponential number of queries. Finally, we numerically confirm our results on a variety of problem instances. Though we exclude a wide variety of quantum algorithms here, we give reason for optimism for certain classes of variational algorithms and discuss potential ways forward in showing the practical utility of such algorithms.
Forward citations
Cited by 5 Pith papers
-
Euclidean-Monte-Carlo-informed ground-state preparation for quantum simulation of scalar field theory
A classical pipeline turns Euclidean Monte Carlo correlation data into a variational ansatz and an efficient quantum circuit for the (1+1)D phi^4 ground state.
-
Regularizing quantum loss landscapes by noise injection
Noise injection into each parameterized Pauli gate exponentially suppresses high-frequency Fourier components of a quantum loss function, smoothing the landscape and improving optimization quality in numerical tests.
-
Statistical models of barren plateaus and anti-concentration of Pauli observables
In statistical models of barren plateaus, any two Pauli observables have non-zero regions whose overlap is exponentially smaller than each region, a phenomenon the paper calls anti-concentration.
-
Initialization and training of matrix product state probabilistic models
Gradient descent on randomly initialized matrix product states gets stuck in a causal trap that ignores boundary correlations, but natural gradient descent or a TTNS-Sketch warm start avoids the trap.
-
Supervised Quantum Machine Learning: A Future Outlook from Qubits to Enterprise Applications
A review of supervised quantum machine learning techniques and a speculative roadmap for 2025-2035, concluding that practical quantum advantage will be confined to niche domains until fault-tolerant hardware arrives.
Discussion (0). Continue with ORCID to comment.