• Corpus ID: 248721798

Beyond Barren Plateaus: Quantum Variational Algorithms Are Swamped With Traps

  title={Beyond Barren Plateaus: Quantum Variational Algorithms Are Swamped With Traps},
  author={Eric R. Anschuetz and Bobak Toussi Kiani},
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… 
Laziness, Barren Plateau, and Noise in Machine Learning
This work precisely reformulates the quantum barren plateau statement towards a precision statement and injects new hope toward near-term variational quantum algorithms, and provides theoretical connections toward classical machine learning.
Avoiding barren plateaus via transferability of smooth solutions in Hamiltonian Variational Ansatz
A large ongoing research effort focuses on Variational Quantum Algorithms (VQAs), representing leading candidates to achieve computational speed-ups on current quantum devices. The scalability of VQAs
Degeneracy Engineering for Classical and Quantum Annealing: A Case Study of Sparse Linear Regression in Collider Physics
This paper introduces the technique of degeneracy engineering, through which the relative degeneracy of the ground state is increased by modifying a subset of terms in the objective Hamiltonian, and shows how to cast (cid:96) 0 -norm regularization as a quadratic unconstrained binary optimization (QUBO) problem, suitable for implementation on annealing platforms.
Bayesian Learning of Parameterised Quantum Circuits
A probabilistic point of view is taken and the classical optimisation of a quantum circuit is reformulated as an approximation of a Bayesian posterior, induced by combining the cost function to be minimised with a prior distribution over the parameters of the quantum circuit.
An Empirical Study of Quantum Dynamics as a Ground State Problem with Neural Quantum States
Neural quantum states are variational wave functions parameterised by artificial neural networks, a mathematical model studied for decades in the machine learning community. In the context of
To Learn a Mocking-Black Hole
It is shown that for t−doped Clifford black holes that is, black holes modeled by random Clifford circuits doped with an amount t of non-Clifford resources an information retrieval decoder can be learned with fidelity scaling as exp(−αt) using quantum machine learning while having access only to out-of-time-order correlation functions.


Exponentially Many Local Minima in Quantum Neural Networks
A quantitative investigation on the landscape of loss functions of QNNs is conducted and a class of simple yet extremely hard QNN instances for training is identified and the optimality of the construction is shown by providing an almost matching upper bound on such dependence.
Barren plateaus in quantum neural network training landscapes
It is shown that for a wide class of reasonable parameterized quantum circuits, the probability that the gradient along any reasonable direction is non-zero to some fixed precision is exponentially small as a function of the number of qubits.
Absence of Barren Plateaus in Quantum Convolutional Neural Networks
This work rigorously analyze the gradient scaling for the parameters in the QCNN architecture and finds that the variance of the gradient vanishes no faster than polynomially, implying that QCNNs do not exhibit barren plateaus.
Entanglement Induced Barren Plateaus
It is shown that for any bounded objective function on the visible layers, the Lipshitz constants of the expectation value of that objective function will scale inversely with the dimension of the hidden-subsystem with high probability, and how this can cause both gradient descent and gradient-free methods to fail.
Exploring entanglement and optimization within the Hamiltonian Variational Ansatz
This paper focuses on a special family of quantum circuits called the Hamiltonian Variational Ansatz (HVA), which takes inspiration from the quantum approximation optimization algorithm and adiabatic quantum computation and exhibits favorable structural properties and numerically observes that the optimization landscape of HVA becomes almost trap free when the ansatz is over-parameterized.
Cost function dependent barren plateaus in shallow parametrized quantum circuits
This work rigorously proves two results, assuming V(θ) is an alternating layered ansatz composed of blocks forming local 2-designs, that establish a connection between locality and trainability.
Efficient Measure for the Expressivity of Variational Quantum Algorithms.
The superiority of variational quantum algorithms (VQAs) such as quantum neural networks (QNNs) and variational quantum eigensolvers (VQEs) heavily depends on the expressivity of the employed
Power of data in quantum machine learning
This work shows that some problems that are classically hard to compute can be easily predicted by classical machines learning from data and proposes a projected quantum model that provides a simple and rigorous quantum speed-up for a learning problem in the fault-tolerant regime.
Abrupt transitions in variational quantum circuit training
A critical layer depth will abruptly train arbitrarily close to the target, thereby minimizing the objective function, and shed new light on the divide-and-conquer trainability of variational quantum circuits.
Variational Quantum Algorithms
An overview of the field of Variational Quantum Algorithms is presented and strategies to overcome their challenges as well as the exciting prospects for using them as a means to obtain quantum advantage are discussed.