Pith. sign in

REVIEW 15 cited by

Does provable absence of barren plateaus imply classical simulability?

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

arxiv 2312.09121 v3 pith:SYBQ2EQ7 submitted 2023-12-14 quant-ph cs.LGstat.ML

classification quant-phcs.LGstat.ML
keywords barrenmanyplateausquantumclassicaldataargumentsavoid
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

A large amount of effort has recently been put into understanding the barren plateau phenomenon. In this perspective article, we face the increasingly loud elephant in the room and ask a question that has been hinted at by many but not explicitly addressed: Can the structure that allows one to avoid barren plateaus also be leveraged to efficiently simulate the loss classically? We collect evidence-on a case-by-case basis-that many commonly used models whose loss landscapes avoid barren plateaus can also admit classical simulation, provided that one can collect some classical data from quantum devices during an initial data acquisition phase. This follows from the observation that barren plateaus result from a curse of dimensionality, and that current approaches for solving them end up encoding the problem into some small, classically simulable, subspaces. Thus, while stressing that quantum computers can be essential for collecting data, our analysis sheds doubt on the information processing capabilities of many parametrized quantum circuits with provably barren plateau-free landscapes. We end by discussing the (many) caveats in our arguments including the limitations of average case arguments, the role of smart initializations, models that fall outside our assumptions, the potential for provably superpolynomial advantages and the possibility that, once larger devices become available, parametrized quantum circuits could heuristically outperform our analytic expectations.

Discussion (0). Sign in to comment.

Forward citations

Cited by 15 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 37 citations worldwide. Full citation record

  1. A hardware-efficient variational ansatz with an exact diagonal metric for real- and imaginary-time evolution and Haar sampling

    quant-ph 2026-07 conditional novelty 7.0 of 10

    A hardware-efficient binary-tree ansatz has a closed-form diagonal Fubini–Study metric, enabling metric-aware VQE and time evolution without auxiliary circuits, with linear-in-k pruning for sparse sectors.

  2. Loss Behavior in Supervised Learning with Entangled States

    quant-ph 2025-09 conditional novelty 7.0 of 10

    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.

  3. Trainability of Parametrised Linear Combinations of Unitaries

    quant-ph 2025-06 conditional novelty 7.0 of 10

    Sums of trainable parametrised circuits remain trainable, with explicit variance formulas for LCU states under Haar-random assumptions.

  4. Stacking the Deck: Tunable Trainability in Stacked LCUs

    quant-ph 2026-07 conditional novelty 6.0 of 10

    Stacked LCUs of fermionic Gaussian unitaries give variance Ω(1/(n k^{3l})) against classical simulation O(k^{2l} n^3) and quantum gate count O(l k n^2), with layers l as the single dial.

  5. Concentration-Free Quantum Kernel Learning in the Rydberg Blockade

    cond-mat.str-el 2025-08 unverdicted novelty 6.0 of 10

    A Rydberg blockade based quantum kernel is claimed to avoid exponential concentration while remaining classically hard to simulate.

  6. Pitfalls when tackling the exponential concentration of parameterized quantum models

    quant-ph 2025-07 conditional novelty 6.0 of 10

    Exponentially concentrated measurement outcomes are statistically indistinguishable from fixed noise after polynomial shots, so classical post-processing cannot fix them, and common proposed remedies do not escape this.

  7. LCQNN: Linear Combination of Quantum Neural Networks

    quant-ph 2025-07 conditional novelty 6.0 of 10

    LCQNN combines several trainable unitaries through a learned superposition on control qubits, yielding gradient variance bounds that scale polynomially with local system size rather than exponentially with total qubit count.

  8. Quantum Recurrent Embedding Neural Network

    quant-ph 2025-06 conditional novelty 6.0 of 10

    A quantum recurrent embedding neural network is proven to avoid barren plateaus via a dynamical Lie algebra decomposition, with applications to Hamiltonian and topological phase classification.

  9. Demonstration of Efficient Predictive Surrogates for Large-scale Quantum Processors

    quant-ph 2025-07 conditional novelty 5.0 of 10

    Classical surrogates using truncated trigonometric expansions emulate noisy quantum processors and cut measurement overhead in VQE pre-training and Floquet phase identification.

  10. Out of Tune: Demystifying Noise-Effects on Quantum Fourier Models

    quant-ph 2025-06 conditional novelty 5.0 of 10

    Noise, especially decoherent gate errors, systematically reduces Fourier coefficient magnitudes, expressibility, and entangling capability of quantum Fourier models, with circuit architecture and encoding modulating t...

  11. Protein folding with an all-to-all trapped-ion quantum computer

    quant-ph 2025-06 conditional novelty 5.0 of 10

    BF-DCQO on IonQ's trapped-ion processors solves dense HUBO instances (protein folding up to 33 qubits, MAX 4-SAT and spin-glasses at 36 qubits) when followed by classical post-processing.

  12. Quantum reinforcement learning in dynamic environments

    quant-ph 2025-07 conditional novelty 4.0 of 10

    A quantum hybrid RL agent with a dissipation mechanism outlearns a classical agent in a Gridworld with a suddenly changing reward path, for suitable dissipation values.

  13. Perspectives on Utilization of Measurements in Quantum Algorithms

    quant-ph 2025-07 conditional novelty 3.0 of 10

    A survey that categorizes quantum measurement uses into static circuits, dynamic circuits, and challenge-solving techniques, and argues measurements deserve more attention in algorithm design.

  14. Artificial intelligence for representing and characterizing quantum systems

    quant-ph 2025-09 unverdicted novelty 1.0 of 10

    A review organizes AI-based quantum system characterization into ML, deep learning, and language model paradigms, covering property prediction and implicit state reconstruction.

  15. Thermalization from quantum entanglement: jet simulations in the massive Schwinger model

    hep-ph 2025-06

Pith tools