VNA produces Sharpe-ratio-competitive portfolios on indices up to 2,008 assets, but the claimed speed advantage and universal finite-size scaling are not robustly supported.
Solving the Optimal Trading Trajectory Problem Using Simulated Bifurcation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We use an optimization procedure based on simulated bifurcation (SB) to solve the integer portfolio and trading trajectory problem with an unprecedented computational speed. The underlying algorithm is based on a classical description of quantum adiabatic evolutions of a network of non-linearly interacting oscillators. This formulation has already proven to beat state of the art computation times for other NP-hard problems and is expected to show similar performance for certain portfolio optimization problems. Inspired by such we apply the SB approach to the portfolio integer optimization problem with quantity constraints and trading activities. We show first numerical results for portfolios of up to 1000 assets, which already confirm the power of the SB algorithm for its novel use-case as a portfolio and trading trajectory optimizer.
citation-role summary
background 1
citation-polarity summary
fields
cond-mat.dis-nn 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Large-scale portfolio optimization with variational neural annealing
VNA produces Sharpe-ratio-competitive portfolios on indices up to 2,008 assets, but the claimed speed advantage and universal finite-size scaling are not robustly supported.