Breakdown of Gradient-Flow Dynamics in Oscillator Ising Machines from Harmonic Misalignment
Abir Hasan, E.M. Hasantha Ekanayake, Kyle Lee, Kerem Camsari, Nikhil Shukla

TL;DR
This paper demonstrates that oscillator Ising machines often do not follow gradient descent dynamics due to harmonic misalignment, which introduces non-conservative interactions and challenges the energy-based interpretation.
Contribution
It identifies harmonic misalignment as a key factor causing the breakdown of gradient-flow dynamics in oscillator Ising machines and introduces a metric to quantify this effect.
Findings
Harmonic misalignment leads to non-gradient, non-conservative phase dynamics.
A normalized metric quantifies the non-gradient contributions in oscillator models.
Substantial non-gradient effects are found in ring oscillators and other hardware models.
Abstract
Oscillator Ising machines (OIMs) are often viewed as physical systems that perform gradient descent on an energy landscape encoding Ising solutions. Here, we show that this interpretation is not generic and breaks down in a broad class of oscillator implementations. We establish that gradient-flow dynamics require a harmonic-by-harmonic quadrature relation between the oscillator waveform and its phase response. Deviations from this condition, which we term harmonic misalignment, introduce even components in the pairwise interaction function, leading to non-conservative phase dynamics and precluding a gradient-flow description. We introduce a normalized metric for this non-gradient contribution and evaluate it across representative oscillator models relevant to OIMs. This metric reveals substantial non-gradient contributions in ring oscillators and across other hardware-realistic…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
