41x Knowledge Distillation from Recurrent Ensembles to Liquid Continuous-Time Networks for Financial Time Series Classification

Fuente: Zenodo
Salvato in:
Dettagli Bibliografici
Autore principale: Kilgore, Brian
Natura: Recurso digital
Pubblicazione: Zenodo 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866901972472299520
author Kilgore, Brian
author_facet Kilgore, Brian
contents We present a knowledge distillation framework that compresses a 137,763-parameter recurrent ensemble (LSTM + GRU) into a 3,328-parameter Liquid Continuous-time Closed-form (LiquidCfC) network, achieving 41.4x parameter reduction for directional classification on forex time series. The teacher achieves a pooled bootstrap Sharpe ratio of 71.4 (95% CI: [58.4, 85.1]) while the student achieves 16.3 (95% CI: [14.76, 17.89]), demonstrating statistically significant predictive fidelity under extreme compression. We introduce a deployment gate criterion (G3) based on KL divergence at unit temperature, providing a principled accept/reject mechanism for compressed model deployment. Validated via Monte Carlo block bootstrap (10,000 resamples) on expanding-window walk-forward cross-validation across four major currency pairs.
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_20045638
institution Zenodo
language
publishDate 2026
publisher Zenodo
record_format zenodo
spellingShingle 41x Knowledge Distillation from Recurrent Ensembles to Liquid Continuous-Time Networks for Financial Time Series Classification
Kilgore, Brian
knowledge distillation
LiquidCfC
continuous-time neural networks
model compression
financial time series
LSTM
GRU
forex
walk-forward validation
block bootstrap
We present a knowledge distillation framework that compresses a 137,763-parameter recurrent ensemble (LSTM + GRU) into a 3,328-parameter Liquid Continuous-time Closed-form (LiquidCfC) network, achieving 41.4x parameter reduction for directional classification on forex time series. The teacher achieves a pooled bootstrap Sharpe ratio of 71.4 (95% CI: [58.4, 85.1]) while the student achieves 16.3 (95% CI: [14.76, 17.89]), demonstrating statistically significant predictive fidelity under extreme compression. We introduce a deployment gate criterion (G3) based on KL divergence at unit temperature, providing a principled accept/reject mechanism for compressed model deployment. Validated via Monte Carlo block bootstrap (10,000 resamples) on expanding-window walk-forward cross-validation across four major currency pairs.
title 41x Knowledge Distillation from Recurrent Ensembles to Liquid Continuous-Time Networks for Financial Time Series Classification
topic knowledge distillation
LiquidCfC
continuous-time neural networks
model compression
financial time series
LSTM
GRU
forex
walk-forward validation
block bootstrap
url https://doi.org/10.5281/zenodo.20045638