On Speedups for Convex Optimization via Quantum Dynamics

• URL: http://arxiv.org/abs/2503.24332v1
• Date: Mon, 31 Mar 2025 17:21:12 GMT
• Title: On Speedups for Convex Optimization via Quantum Dynamics
• Authors: Shouvanik Chakrabarti, Dylan Herman, Jacob Watkins, Enrico Fontana, Brandon Augustino, Junhyung Lyle Kim, Marco Pistoia,
• Abstract summary: We explore the potential for quantum speed in convex optimization using discrete simulations of the Quantum Hamiltonian Descent framework.<n>In continuous time, we demonstrate that QHD, with suitable parameters, can achieve arbitrarily fast convergence rates.<n>We show that QHD offers a super-quadratic query advantage over all known classical algorithms tolerating this level of evaluation noise.
• Score: 2.5094874597551913
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We explore the potential for quantum speedups in convex optimization using discrete simulations of the Quantum Hamiltonian Descent (QHD) framework, as proposed by Leng et al., and establish the first rigorous query complexity bounds. We develop enhanced analyses for quantum simulation of Schr\"odinger operators with black-box potential via the pseudo-spectral method, providing explicit resource estimates independent of wavefunction assumptions. These bounds are applied to assess the complexity of optimization through QHD. Our findings pertain to unconstrained convex optimization in $d$ dimensions. In continuous time, we demonstrate that QHD, with suitable parameters, can achieve arbitrarily fast convergence rates. The optimization speed limit arises solely from the discretization of the dynamics, mirroring a property of the classical dynamics underlying QHD. Considering this cost, we show that a $G$-Lipschitz convex function can be optimized to an error of $\epsilon$ with $\widetilde{\mathcal{O}}(d^{1.5}G^2 R^2/\epsilon^2)$ queries. Moreover, under reasonable assumptions on the complexity of Hamiltonian simulation, $\widetilde{\Omega}(d/\epsilon^2)$ queries are necessary. Thus, QHD does not offer a speedup over classical zeroth order methods with exact oracles. However, we demonstrate that the QHD algorithm tolerates $\widetilde{\mathcal{O}}(\epsilon^3/d^{1.5}G^2 R^2)$ noise in function evaluation. We show that QHD offers a super-quadratic query advantage over all known classical algorithms tolerating this level of evaluation noise in the high-dimension regime. Additionally, we design a quantum algorithm for stochastic convex optimization that provides a super-quadratic speedup over all known classical algorithms in the high-dimension regime. To our knowledge, these results represent the first rigorous quantum speedups for convex optimization achieved through a dynamical algorithm.

Related papers

• Quantum Hamiltonian Descent for Non-smooth Optimization [7.773836776652785]
  We investigate how quantum mechanics can be leveraged to overcome limitations of classical algorithms.<n>We propose a global convergence rate for non-smoothtime global convergence problems through a novel design.<n>In addition, we propose discrete-time QHD fully digitized via a novel Lynov function.
  arXiv  Detail & Related papers  (2025-03-20T06:02:33Z)
• Exponentially Better Bounds for Quantum Optimization via Dynamical Simulation [0.5097809301149342]
  We provide several quantum algorithms for continuous optimization that do not require any gradient estimation.<n>We encode the optimization problem into the dynamics of a physical system and coherently simulate the time evolution.
  arXiv  Detail & Related papers  (2025-02-06T18:32:26Z)
• Optimizing Unitary Coupled Cluster Wave Functions on Quantum Hardware: Error Bound and Resource-Efficient Optimizer [0.0]
  We study the projective quantum eigensolver (PQE) approach to optimizing unitary coupled cluster wave functions on quantum hardware. The algorithm uses projections of the Schr"odinger equation to efficiently bring the trial state closer to an eigenstate of the Hamiltonian. We present numerical evidence of superiority over both the optimization introduced in arXiv:2102.00345 and VQE optimized using the Broyden Fletcher Goldfarb Shanno (BFGS) method.
  arXiv  Detail & Related papers  (2024-10-19T15:03:59Z)
• Application of Langevin Dynamics to Advance the Quantum Natural Gradient Optimization Algorithm [47.47843839099175]
  A Quantum Natural Gradient (QNG) algorithm for optimization of variational quantum circuits has been proposed recently.<n>Momentum-QNG is more effective to escape local minima and plateaus in the variational parameter space.
  arXiv  Detail & Related papers  (2024-09-03T15:21:16Z)
• Sum-of-Squares inspired Quantum Metaheuristic for Polynomial Optimization with the Hadamard Test and Approximate Amplitude Constraints [76.53316706600717]
  Recently proposed quantum algorithm arXiv:2206.14999 is based on semidefinite programming (SDP) We generalize the SDP-inspired quantum algorithm to sum-of-squares. Our results show that our algorithm is suitable for large problems and approximate the best known classicals.
  arXiv  Detail & Related papers  (2024-08-14T19:04:13Z)
• A quantum-classical performance separation in nonconvex optimization [7.427989325451079]
  We prove that the recently proposed Quantum Hamiltonian (QHD) algorithm is able to solve any $d$dimensional queries from this family. On the other side, a comprehensive empirical study suggests that representative state-of-the-art classical algorithms/solvers would require a superpolynomial time to solve such queries.
  arXiv  Detail & Related papers  (2023-11-01T19:51:00Z)
• Accelerated First-Order Optimization under Nonlinear Constraints [73.2273449996098]
  We exploit between first-order algorithms for constrained optimization and non-smooth systems to design a new class of accelerated first-order algorithms. An important property of these algorithms is that constraints are expressed in terms of velocities instead of sparse variables.
  arXiv  Detail & Related papers  (2023-02-01T08:50:48Z)
• Improved Convergence Rate of Stochastic Gradient Langevin Dynamics with Variance Reduction and its Application to Optimization [50.83356836818667]
  gradient Langevin Dynamics is one of the most fundamental algorithms to solve non-eps optimization problems. In this paper, we show two variants of this kind, namely the Variance Reduced Langevin Dynamics and the Recursive Gradient Langevin Dynamics.
  arXiv  Detail & Related papers  (2022-03-30T11:39:00Z)
• Twisted hybrid algorithms for combinatorial optimization [68.8204255655161]
  Proposed hybrid algorithms encode a cost function into a problem Hamiltonian and optimize its energy by varying over a set of states with low circuit complexity. We show that for levels $p=2,ldots, 6$, the level $p$ can be reduced by one while roughly maintaining the expected approximation ratio.
  arXiv  Detail & Related papers  (2022-03-01T19:47:16Z)
• Quantum algorithms for approximate function loading [0.0]
  We introduce two approximate quantum-state preparation methods for the NISQ era inspired by the Grover-Rudolph algorithm. A variational algorithm capable of loading functions beyond the aforementioned smoothness conditions is proposed.
  arXiv  Detail & Related papers  (2021-11-15T17:36:13Z)
• Hybrid quantum-classical algorithms for approximate graph coloring [65.62256987706128]
  We show how to apply the quantum approximate optimization algorithm (RQAOA) to MAX-$k$-CUT, the problem of finding an approximate $k$-vertex coloring of a graph. We construct an efficient classical simulation algorithm which simulates level-$1$ QAOA and level-$1$ RQAOA for arbitrary graphs.
  arXiv  Detail & Related papers  (2020-11-26T18:22:21Z)
• Convergence of adaptive algorithms for weakly convex constrained optimization [59.36386973876765]
  We prove the $mathcaltilde O(t-1/4)$ rate of convergence for the norm of the gradient of Moreau envelope. Our analysis works with mini-batch size of $1$, constant first and second order moment parameters, and possibly smooth optimization domains.
  arXiv  Detail & Related papers  (2020-06-11T17:43:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.