AI Paper Atlas

Research map / Time series / Causal and generative time series

Split Conformal Prediction and Non-Exchangeable Data

Roberto I. Oliveira, Paulo Orenstein, Thiago Ramos, João Vitor Romano

JMLR 2024 · Time series › Causal and generative time series · approach: Probabilistic and conformal forecasting · 19 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 plain split CP instead of NexCP weightingNexCP · Spatiotemporal temperatureinterval size (deg C): 9.605 vs 9.289No clear effect
use plain split CP instead of DtACIDtACI · Spatiotemporal temperatureaverage time (min): 75.15 -> 2.85Improved
use plain split CP instead of NexCPNexCP · Spatiotemporal temperatureaverage time (min): 1884.92 -> 2.85Improved
add dynamically tuned adaptive conformal inference (DtACI)Split CP · Spatiotemporal temperaturecoverage SD over space: 0.130 -> 0.096Improved
add dynamically tuned adaptive conformal inference (DtACI)Split CP · Spatiotemporal temperatureinterval size (deg C): 9.605 -> 9.658Hurt
decrease NexCP decay parameter rho from 0.99 to 0.1 (ablation)NexCP · Spatiotemporal temperatureaverage coverage: 90.9% -> 89.5%Hurt
use split CP instead of EnbPIEnbPI · Cycle-graph random walkcoverage: 86.6% -> 91.4%Improved
use split CP instead of EnbPIEnbPI · Cycle-graph random walkinterval size: 0.15 -> 0.34Hurt
increase calibration set size from 500 to 5000 (ablation)Split CP · Financial eurusd high volatilityconditional coverage: 87.64% -> 89.85%Improved
increase calibration set size from 500 to 5000 (ablation)Split CP · Financial bcousd high volatilityconditional coverage: 87.10% -> 89.33%Improved
increase autoregressive coefficient (stronger dependence) (ablation)Split CP · AR(1) simulationmarginal coverageNo 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