Technology Category
Search and Optimization: Non-convex OptimizationMachine Learning: Quantum Machine LearningReasoning under Uncertainty: Stochastic Optimization
Classical and Quantum Speedups for Non-Convex Optimization via Energy Conserving Descent
🤖 AI Summary
This work addresses the challenge of non-convex optimization, where algorithms often become trapped in local minima and struggle to converge efficiently to the global optimum. To overcome this, the authors propose the Energy-Conserving Descent (ECD) method and provide the first theoretical analysis of its properties. They further introduce a stochastic variant, sECD, by incorporating energy-preserving noise, and develop a quantum version, qECD, leveraging quantum Hamiltonian simulation. Through modeling via stochastic differential equations and first-hitting-time analysis on a one-dimensional double-well objective function, both sECD and qECD achieve exponential acceleration over classical gradient descent. Notably, in high-barrier regimes, qECD substantially outperforms sECD, demonstrating a clear quantum advantage.
Technology Category
Application Category
📝 Abstract
The Energy Conserving Descent (ECD) algorithm was recently proposed (De Luca & Silverstein, 2022) as a global non-convex optimization method. Unlike gradient descent, appropriately configured ECD dynamics escape strict local minima and converge to a global minimum, making it appealing for machine learning optimization.
We present the first analytical study of ECD, focusing on the one-dimensional setting for this first installment. We formalize a stochastic ECD dynamics (sECD) with energy-preserving noise, as well as a quantum analog of the ECD Hamiltonian (qECD), providing the foundation for a quantum algorithm through Hamiltonian simulation.
For positive double-well objectives, we compute the expected hitting time from a local to the global minimum. We prove that both sECD and qECD yield exponential speedup over respective gradient descent baselines--stochastic gradient descent and its quantization. For objectives with tall barriers, qECD achieves a further speedup over sECD.
Problem
Research questions and friction points this paper is trying to address.
non-convex optimization
global minimum
local minima
energy barriers
optimization speedup
Innovation
Methods, ideas, or system contributions that make the work stand out.
Energy Conserving Descent
non-convex optimization
quantum speedup
stochastic dynamics
Hamiltonian simulation
🔎 Similar Papers
No similar papers found.
