Research map / Time series / Causal and generative time series
Theoretical analysis of deep neural networks for temporally dependent observations
Mingliang Ma, Abolfazl Safikhani
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use 3-layer neural network instead of linear regression | linear regression · Inflation, gamma=0% | MSE of one-step forecast: 18.05 -> 15.71 | Improved |
| use 3-layer neural network instead of linear regression | linear regression · Inflation, gamma=5% | MSE of one-step forecast: 17.05 -> 15.65 | Improved |
| use 3-layer neural network instead of linear regression | linear regression · Inflation, gamma=7.5% | MSE of one-step forecast: 15.42 -> 16.40 | Hurt |
| use 3-layer neural network instead of linear regression | linear regression · Inflation, gamma=10% | MSE of one-step forecast: 172.49 -> 16.51 | Improved |
| increase network depth from 3 to 6 layers | neural network · Inflation, gamma=0% | MSE of one-step forecast: 15.71 -> 17.44 | Hurt |
| increase network depth from 3 to 6 layers | neural network · Inflation, gamma=10% | MSE of one-step forecast: 16.51 -> 20.70 | Hurt |
| increase SIS-selected covariates from 0% to 10% of predictors | 3-layer neural network · Inflation | MSE of one-step forecast: 15.71 -> 16.51 | No clear effect |
| vary sparsity tuning parameter lambda | neural network · simulation | estimation error | No clear effect |
| increase sample size on non-linear AR models (3) and (4) | linear regression · simulation | log mean square error | Hurt |
| use neural network on linear AR(1)/AR(3) models | linear regression · simulation | log mean square error | No clear effect |
Closest papers by meaning
- SynTSBench: Rethinking Temporal Pattern Learning in Deep Learning Models for Time Series (NeurIPS 2025 · similarity 0.86)
- DDN: Dual-domain Dynamic Normalization for Non-stationary Time Series Forecasting (NeurIPS 2024 · similarity 0.85)
- Scaling Law for Time Series Forecasting (NeurIPS 2024 · similarity 0.84)
- TempoPFN: Synthetic Pre-training of Linear RNNs for Zero-shot Time Series Forecasting (NeurIPS 2026 · similarity 0.84)
- TimePFN: Effective Multivariate Time Series Forecasting with Synthetic Data (AAAI 2025 · similarity 0.84)
- Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts (ICLR 2025 · similarity 0.84)
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.
