- 追加された行はこの色です。
- 削除された行はこの色です。
- 024-08 へ行く。
[[第24回研究会>024]]
*DSGEによるニューラルネットの正則化と経済予想 [#r18d637a]
**著者 [#tcb351de]
塩野剛志(クレディ・スイス証券)
**概要 [#od1ed992]
This paper examines the possibility of combining a DSGE model and neural networks to supplement each other, with regard to out-of-sample forecasts for economic variables. The aim is to build a model with theoretical interpretability and state-of-the-art performance. The novel neural-net structure of TDVAE (Temporal Difference Variational Auto-Encoder) proposed by Gregor et.al [2019] enables to
realize this idea. TDVAE virtually replicates a Gaussian stochastic state-space model through combination of neural networks. Because a DSGE model provides theoretical restrictions on the state transition and observation matrices of a linear state-space model, I choose to transplant those DSGE-oriented matrices into the formulations of state transition and observation probabilities in TDVAE. This TDVAE-DSGE approach certainly achieved the superior performance in the task of out-of-sample forecasts on Japan's real GDP during 1Q/2011 and 4Q/2018.
**キーワード [#b5d0750d]
VAE, TDVAE, DSGE, Variational Inference
**論文 [#ccc36b7e]
//(3月11日以降に公表いたします)
&ref(07_SIG-FIN-24.pdf);