# Adaptive Conformal Inference Under Delayed Feedback: Coverage Guarantees and a Delay-to-Memory Diagnostic

arXiv: https://arxiv.org/abs/2609.07251 · HTML: https://mlsanity.com/paper/2609.07251/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 17 references that are in the map.
- First posted on arXiv 7 Sep 2026.

## Builds on (most cited first, 8 of 8)

- [Conformal PID Control for Time Series Prediction](https://mlsanity.com/paper/2307.16895/) (2023)
- [Online conformal prediction with decaying step sizes](https://mlsanity.com/paper/2402.01139/) (2024)
- [Bellman Conformal Inference: Calibrating Prediction Intervals For Time Series](https://mlsanity.com/paper/2402.05203/) (2024)
- [Online conformal inference for multi-step time series forecasting](https://mlsanity.com/paper/2410.13115/) (2024)
- [Mirror Online Conformal Prediction with Intermittent Feedback](https://mlsanity.com/paper/2503.10345/) (2025)
- [Adaptive Conformal Inference for Multi-Step Ahead Time-Series Forecasting Online](https://mlsanity.com/paper/2409.14792/) (2024)
- [Optimization-based Online Conformal Prediction for Multi-step Forecasting](https://mlsanity.com/paper/2508.13362/) (2025)
- [Online Conformal Prediction Beyond Feedback](https://mlsanity.com/paper/2608.07139/) (2026)

## Abstract (arXiv)

Adaptive Conformal Inference (ACI) extends conformal prediction to non-exchangeable settings by adjusting the nominal miscoverage level online in response to recent coverage errors. When forecasts are issued with horizon τ, however, the outcome needed to evaluate a prediction is observed only τ steps later, so these adaptive updates must rely on delayed feedback. We study this setting and ask how the effect of delay depends on the persistence of the residual process. First, we show that the τ-delayed ACI recursion can be decomposed into τ interleaved ACI-like sequences. This representation yields a finite-sample bound on long-run empirical coverage with explicit dependence on τ. We also derive an approximate marginal coverage bound that relates coverage deviation to changes in the underlying environment across the forecast horizon and to the adaptation rate γ. We then introduce the delay-to-memory ratio r=τ/L, where L is the time scale over which the temporal signal driving non-exchangeability decays. Simulation results show that the usefulness of this ratio depends on the form of temporal dependence: it strongly organizes performance under AR(1) dependence, is less predictive of overall performance under GARCH(1,1) and Markov switching, but more clearly characterizes when scale normalization remains useful in those settings. Abrupt mean- and variance-shift experiments further show that the preferred adaptation rate depends on the residual dynamics. Overall, the results show that the effect of forecast delay is best understood relative to the time scale over which past residual information remains relevant.