mQO combines differentiable QUBO optimization with mutation-based resets and local search to outperform heuristics and solvers on large-scale combinatorial problems by addressing stalling in local maxima.
According to the proof of Proposition 3.2, we initialize fromx=c1 n, wherec is randomly sampled from the uniform distribution in(−1,1)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DM 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Mutation-Guided Differentiable Quadratic Combinatorial Optimization
mQO combines differentiable QUBO optimization with mutation-based resets and local search to outperform heuristics and solvers on large-scale combinatorial problems by addressing stalling in local maxima.