Pre-training on resampled Lorenz chaotic series yields zero-shot Bitcoin return predictions, with the training-sample count needed for a fixed skill level growing roughly exponentially with predictive horizon.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Scaling Law for Large-Scale Pre-Training Using Chaotic Time Series and Predictability in Financial Time Series
Pre-training on resampled Lorenz chaotic series yields zero-shot Bitcoin return predictions, with the training-sample count needed for a fixed skill level growing roughly exponentially with predictive horizon.