AI Paper Atlas

Research map / Time series / Causal and generative time series

Theoretical analysis of deep neural networks for temporally dependent observations

Mingliang Ma, Abolfazl Safikhani

NeurIPS 2022 · Time series › Causal and generative time series · approach: State-space and latent dynamics forecasting · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use 3-layer neural network instead of linear regressionlinear regression · Inflation, gamma=0%MSE of one-step forecast: 18.05 -> 15.71Improved
use 3-layer neural network instead of linear regressionlinear regression · Inflation, gamma=5%MSE of one-step forecast: 17.05 -> 15.65Improved
use 3-layer neural network instead of linear regressionlinear regression · Inflation, gamma=7.5%MSE of one-step forecast: 15.42 -> 16.40Hurt
use 3-layer neural network instead of linear regressionlinear regression · Inflation, gamma=10%MSE of one-step forecast: 172.49 -> 16.51Improved
increase network depth from 3 to 6 layersneural network · Inflation, gamma=0%MSE of one-step forecast: 15.71 -> 17.44Hurt
increase network depth from 3 to 6 layersneural network · Inflation, gamma=10%MSE of one-step forecast: 16.51 -> 20.70Hurt
increase SIS-selected covariates from 0% to 10% of predictors3-layer neural network · InflationMSE of one-step forecast: 15.71 -> 16.51No clear effect
vary sparsity tuning parameter lambdaneural network · simulationestimation errorNo clear effect
increase sample size on non-linear AR models (3) and (4)linear regression · simulationlog mean square errorHurt
use neural network on linear AR(1)/AR(3) modelslinear regression · simulationlog mean square errorNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy