Barren plateaus are swamped with traps

Abstract

Two main challenges preventing efficient training of variational quantum algorithms and quantum machine learning models are local minima and barren plateaus. Typically, barren plateaus are associated with deep circuits, while shallow circuits have been shown to suffer from suboptimal local minima. We point out a simple mechanism that creates exponentially many poor local minima specifically in the barren plateau regime. These local minima are trivial solutions, optimizing only a few terms in the loss function, leaving the rest on their barren plateaus. More precisely, we show the existence of approximate local minima, optimizing a single loss term, and conjecture the existence of exact local minima, optimizing only a logarithmic fraction of all loss function terms. One implication of our findings is that simply yielding large gradients is not sufficient to render an initialization strategy a meaningful solution to the barren plateau problem.

arXiv comment9+5 pages

References in corpus (44)

• Quantum Computing in the NISQ era and beyond
• Quantum Machine Learning
• Variational Quantum Algorithms
• Hardware-efficient Variational Quantum Eigensolver for Small Molecules and Quantum Magnets
• Barren plateaus in quantum neural network training landscapes
• Noisy intermediate-scale quantum (NISQ) algorithms
• Quantum Circuit Learning
• An introduction to quantum machine learning
• Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits
• Evaluating analytic gradients on quantum hardware
• An adaptive variational algorithm for exact molecular simulations on a quantum computer
• The effect of data encoding on the expressive power of variational quantum machine learning models
• Exact and Approximate Unitary 2-Designs: Constructions and Applications
• Connecting ansatz expressibility to gradient magnitudes and barren plateaus
• Quantum autoencoders for efficient compression of quantum data
• Training variational quantum algorithms is NP-hard
• qubit-ADAPT-VQE: An adaptive algorithm for constructing hardware-efficient ansatze on a quantum processor
• An initialization strategy for addressing barren plateaus in parametrized quantum circuits
• Quantum-assisted quantum compiling
• Layerwise learning for quantum neural networks
• Beyond Barren Plateaus: Quantum Variational Algorithms Are Swamped With Traps
• Diagnosing Barren Plateaus with Tools from Quantum Optimal Control
• Exploiting symmetry in variational quantum machine learning
• Trainability of Dissipative Perceptron-Based Quantum Neural Networks
• Theory of overparametrization in quantum neural networks
• Group-Invariant Quantum Machine Learning
• Equivalence of quantum barren plateaus to cost concentration and narrow gorges
• A Lie Algebraic Theory of Barren Plateaus for Deep Parameterized Quantum Circuits
• Approximate unitary $t$-designs by short random quantum circuits using nearest-neighbor and long-range gates
• Adaptive Variational Quantum Dynamics Simulations
• On barren plateaus and cost function locality in variational quantum algorithms
• The Adjoint Is All You Need: Characterizing Barren Plateaus in Quantum Ansätze
• Synergy Between Quantum Circuits and Tensor Networks: Short-cutting the Race to Practical Quantum Advantage
• Robust quantum compilation and circuit optimisation via energy minimisation
• Adaptive variational quantum eigensolvers for highly excited states
• Classical surrogates for quantum learning models
• Training Saturation in Layerwise Quantum Approximate Optimisation
• Abrupt Transitions in Variational Quantum Circuit Training
• Trainability Enhancement of Parameterized Quantum Circuits via Reduced-Domain Parameter Initialization
• Variational quantum eigensolver techniques for simulating carbon monoxide oxidation
• Multidimensional Fourier series with quantum circuits
• Fourier expansion in variational quantum algorithms
• Efficient variational synthesis of quantum circuits with coherent multi-start optimization
• Equivalence of cost concentration and gradient vanishing for quantum circuits: An elementary proof in the Riemannian formulation

Cited by in corpus (4)

• Barren Plateaus in Variational Quantum Computing
• Deep-Circuit QAOA
• Evidence for effectively constant shot complexity in the quantum approximate optimization algorithm without per-instance optimization
• Learning complexity gradually in quantum machine learning models