SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2208.14919 · 2022

ARMA Cell: A Modular and Effective Approach for Neural Autoregressive Modeling

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 13 functions out of this paper's own repositories and ran 11 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
phschiele/armacell_paper canonical 8 of 10
phschiele/armacell canonical 3 of 3
FunctionStatusWhere it lives
create_shifted_frames Ran phschiele/armacell_paper/benchmarks/common.py
code served (permissive licence) · get_code("9bc27a1edb4337c6")
get_mae Ran phschiele/armacell_paper/models/helpers.py
code served (permissive licence) · get_code("60dbccf5b79f6dde")
get_mse Ran phschiele/armacell_paper/models/helpers.py
code served (permissive licence) · get_code("e3192303e3a9ebfb")
get_rmse Ran phschiele/armacell_paper/models/helpers.py
code served (permissive licence) · get_code("363fdb90133a1244")
get_varma Ran phschiele/armacell_paper/models/models.py
code served (permissive licence) · get_code("68b2ccab5e7ad304")
prepare_arma_input Ran phschiele/armacell/armacell/helpers.py
code served (permissive licence) · get_code("16cbd75e75aac828")
prepare_arma_input Ran phschiele/armacell_paper/arma_cell/helpers.py
code served (permissive licence) · get_code("8190c6aa9a92a9c5")
restore_arma_parameters Ran phschiele/armacell/armacell/helpers.py
code served (permissive licence) · get_code("8b0d52a3aa809568")
restore_arma_parameters Ran phschiele/armacell_paper/arma_cell/helpers.py
code served (permissive licence) · get_code("8071c9616f2ce570")
simulate_arma_process Ran phschiele/armacell/armacell/helpers.py
code served (permissive licence) · get_code("d3949134e1069510")
simulate_arma_process Ran phschiele/armacell_paper/arma_cell/helpers.py
code served (permissive licence) · get_code("a665bb02e0d653cb")
generate_movies Not yet run phschiele/armacell_paper/benchmarks/moving_squares.py
code served (permissive licence) · get_code("f9508098e7091d77")
get_convlstm Not yet run phschiele/armacell_paper/models/models.py
code served (permissive licence) · get_code("f86ddb0f233f60b1")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The autoregressive moving average (ARMA) model is a classical, and arguably one of the most studied approaches to model time series data. It has compelling theoretical properties and is widely used among practitioners. More recent deep learning approaches popularize recurrent neural networks (RNNs) and, in particular, Long Short-Term Memory (LSTM) cells that have become one of the best performing and most common building blocks in neural time series modeling. While advantageous for time series data or sequences with long-term effects, complex RNN cells are not always a must and can sometimes even be inferior to simpler recurrent approaches. In this work, we introduce the ARMA cell, a simpler, modular, and effective approach for time series modeling in neural networks. This cell can be used in any neural network architecture where recurrent structures are present and naturally handles multivariate time series using vector autoregression. We also introduce the ConvARMA cell as a natural successor for spatially-correlated time series. Our experiments show that the proposed methodology is competitive with popular alternatives in terms of performance while being more robust and compelling due to its simplicity

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2208.14919")
get_code_for_paper("2208.14919")
have("2208.14919")

Connect an agent — have() is free.