mlsanityData to 14 Oct 2026

Conformal Predictions under Markovian Data

arXiv 2407.15277 ↗First posted 21 Jul 2024cs.LG math.ST stat.MLcited by 4

Not on the map. Why?

Abstract (arXiv)

We study the split Conformal Prediction method when applied to Markovian data. We quantify the gap in terms of coverage induced by the correlations in the data (compared to exchangeable data). This gap strongly depends on the mixing properties of the underlying Markov chain, and we prove that it typically scales as √tmixln(n)/n (where tmix is the mixing time of the chain). We also derive upper bounds on the impact of the correlations on the size of the prediction set. Finally we present K-split CP, a method that consists in thinning the calibration dataset and that adapts to the mixing properties of the chain. Its coverage gap is reduced to tmix/(nln(n)) without really affecting the size of the prediction set. We finally test our algorithms on synthetic and real-world datasets.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 12 of its 34 references that are in the map. First posted on arXiv 21 Jul 2024.

Builds on

12 of 34 references.

References · 12

  1. 2016Distribution-Free Predictive Inference For Regressioncited by 668
  2. 2019Conformal Prediction Under Covariate Shiftcited by 519
  3. 2021Adaptive Conformal Inference Under Distribution Shiftcited by 375
  4. 2022Conformal prediction beyond exchangeabilitycited by 355
  5. 2022Adaptive Conformal Predictions for Time Seriescited by 161
  6. 2020Least Squares Regression with Markovian Data: Fundamental Limits and Algorithmscited by 56
  7. 2022Adaptive Conformal Prediction for Motion Planning among Dynamic Agentscited by 53
  8. 2017Mixing time estimation in reversible Markov chains from a single sample pathcited by 27
  9. 2019Estimating the Mixing Time of Ergodic Markov Chainscited by 25
  10. 2018Concentration bounds for empirical conditional value-at-risk: The unbounded casecited by 13
  11. 2023Conformal Off-Policy Evaluation in Markov Decision Processescited by 6
  12. 2018Computationally Efficient Estimation of the Spectral Gap of a Markov Chaincited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.