Longer training horizons improve forecast quality but worsen learnability, with loss-landscape roughness growing exponentially for chaotic dynamics and linearly for limit cycles.
A modified multiple shooting algorithm for parameter estimation in odes using adjoint sensitivity analysis.Applied Mathematics and Computation, 390:125644, 2021
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Temporal horizons in forecasting: a performance-learnability trade-off
Longer training horizons improve forecast quality but worsen learnability, with loss-landscape roughness growing exponentially for chaotic dynamics and linearly for limit cycles.