SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2307.16895 · 2023

Conformal PID Control for Time Series Prediction

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 10 functions out of this paper's own repositories and ran 6 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
aangelopoulos/conformal-time-series canonical 6 of 10
FunctionStatusWhere it lives
fit_ar_model Ran aangelopoulos/conformal-time-series/core/ar.py
code served (permissive licence) · get_code("37bbb86d90955318")
generate_process Ran aangelopoulos/conformal-time-series/core/ar.py
code served (permissive licence) · get_code("210e10c5742f02e4")
generate_process_heteroskedastic Ran aangelopoulos/conformal-time-series/core/ar.py
code served (permissive licence) · get_code("37f5e5facb6455c3")
generate_scores Ran aangelopoulos/conformal-time-series/core/synthetic_scores.py
code served (permissive licence) · get_code("bec5ac586d39399b")
linear_scores Ran aangelopoulos/conformal-time-series/core/synthetic_scores.py
code served (permissive licence) · get_code("ba06bf589432338c")
sinusoidal_scores Ran aangelopoulos/conformal-time-series/core/synthetic_scores.py
code served (permissive licence) · get_code("f16fb8fbbed1a83d")
aci Not yet run aangelopoulos/conformal-time-series/core/methods.py
code served (permissive licence) · get_code("541bf2269045ac94")
aci_clipped Not yet run aangelopoulos/conformal-time-series/core/methods.py
code served (permissive licence) · get_code("b1c525a1109057fc")
trailing_window Not yet run aangelopoulos/conformal-time-series/core/methods.py
code served (permissive licence) · get_code("a6b92b9ac05573f0")
weighted_conformal Not yet run aangelopoulos/conformal-time-series/core/quantile.py
code served (permissive licence) · get_code("0d308c17ddd99063")

Repositories linked to this paper

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

Abstract

We study the problem of uncertainty quantification for time series prediction, with the goal of providing easy-to-use algorithms with formal guarantees. The algorithms we present build upon ideas from conformal prediction and control theory, are able to prospectively model conformal scores in an online setting, and adapt to the presence of systematic errors due to seasonality, trends, and general distribution shifts. Our theory both simplifies and strengthens existing analyses in online conformal prediction. Experiments on 4-week-ahead forecasting of statewide COVID-19 death counts in the U.S. show an improvement in coverage over the ensemble forecaster used in official CDC communications. We also run experiments on predicting electricity demand, market returns, and temperature using autoregressive, Theta, Prophet, and Transformer models. We provide an extendable codebase for testing our methods and for the integration of new algorithms, data sets, and forecasting rules.

For agents

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

get_harvested_code_for_paper("2307.16895")
get_code_for_paper("2307.16895")
have("2307.16895")

Connect an agent — have() is free.