Hedging Memory Horizons for Non-Stationary Prediction via Online Aggregation

• URL: http://arxiv.org/abs/2605.06541v1
• Date: Thu, 07 May 2026 16:38:21 GMT
• Title: Hedging Memory Horizons for Non-Stationary Prediction via Online Aggregation
• Abstract summary: MELO is a model-agnostic method that hedges across adaptation scales.<n>It wraps any non-anticipating base-predictor pool with exponentially weighted least-squares adaptation experts.<n>It aggregates raw and EWLS-adapted forecasts with MLpol, a parameter-free online aggregation rule.
• Score: 6.623965101885557
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study online prediction under distribution shift, where inputs arrive chronologically and outcomes are revealed only after prediction. In this setting, predictors must remain stable in quiet regimes yet adapt when regimes shift, and the right adaptation memory is unknown in advance. We propose MELO (Memory-hedged Exponentially Weighted Least-Squares Online aggregation), a model-agnostic method that hedges across adaptation scales: it wraps any non-anticipating base-predictor pool with exponentially weighted least-squares (EWLS) adaptation experts at multiple forgetting factors, and aggregates raw and EWLS-adapted forecasts with MLpol, a parameter-free online aggregation rule. Under boundedness conditions, we establish deterministic oracle inequalities showing that it competes with both the best raw predictor and the best bounded, time-varying affine combinations of the base predictions, up to a path-length-dependent tracking cost and a sublinear aggregation overhead. We evaluate MELO on French national electricity-load forecasting through the COVID-19 lockdown using no regime indicators, lockdown dates, or policy covariates. MELO reduces overall RMSE by 34.7\% relative to base-only MLpol and achieves lower overall RMSE than a TabICL reference supplied with an external COVID policy-response covariate. Moreover, MELO requires only lightweight per-step recursive updates without model retraining.

Related papers

• Joint Model and Data Sparsification via the Marginal Likelihood [53.29070892356214]
  We propose jointly learning individual feature and sample relevancies, enabling simultaneous model and data sparsification.<n>This symmetric pruning of model and data offers a natural extension that preserves conjugacy.<n> Empirical results across diverse regression tasks affirm that a joint ARD approach consistently yields both sparse and robust prediction models.
  arXiv  Detail & Related papers  (2026-05-28T13:26:53Z)
• Is Capability a Liability? More Capable Language Models Make Worse Forecasts When It Matters Most [11.4807141145402]
  In inverse scaling, more capable models produce worse distributional forecasts on forecasting problems with superlinear growth and tail risk of regime change.<n>The pattern appears on ForecastBench-Sim, in forecasting synthetic SIR epidemics with a matched linear control, and replicates in real-world datasets on COVID-19, measles, housing markets, and hyperinflation.<n>This inverse scaling does not appear on single-threshold metrics common in LLM forecasting benchmarks, reversing the sign of the capability--accuracy relationship on identical outputs.
  arXiv  Detail & Related papers  (2026-05-21T16:14:33Z)
• A Predictive View on Streaming Hidden Markov Models [0.8122270502556375]
  We develop a predictive-first optimisation framework for streaming hidden Markov models.<n>Our objective is to sequentially identify latent regimes while maintaining accurate step-ahead predictive distributions.
  arXiv  Detail & Related papers  (2026-04-10T10:51:50Z)
• A Step Back: Prefix Importance Ratio Stabilizes Policy Optimization [58.116300485427764]
  Reinforcement learning post-training can elicit reasoning behaviors in large language models.<n> token-level correction often leads to unstable training dynamics when the degree of off-policyness is large.<n>We propose a simple yet effective objective, Minimum Prefix Ratio (MinPRO)
  arXiv  Detail & Related papers  (2026-01-30T08:47:19Z)
• Distribution-informed Online Conformal Prediction [53.674678995825666]
  We propose Conformal Optimistic Prediction (COP), an online conformal prediction algorithm incorporating underlying data pattern into the update rule.<n>COP produces tighter prediction sets when predictable pattern exists, while retaining valid coverage guarantees even when estimates are inaccurate.<n>We prove that COP can achieve valid coverage and construct shorter prediction intervals than other baselines.
  arXiv  Detail & Related papers  (2025-12-08T17:51:49Z)
• Conformal Prediction Beyond the Horizon: Distribution-Free Inference for Policy Evaluation [14.811119246685534]
  We propose a unified conformal prediction framework for infinite-horizon policy evaluation.<n>Our method integrates distributional RL with conformal calibration, addressing challenges such as unobserved returns, temporal dependencies, and distributional shifts.
  arXiv  Detail & Related papers  (2025-10-29T23:45:44Z)
• Unsupervised Conformal Inference: Bootstrapping and Alignment to Control LLM Uncertainty [49.19257648205146]
  We propose an unsupervised conformal inference framework for generation.<n>Our gates achieve close-to-nominal coverage and provide tighter, more stable thresholds than split UCP.<n>The result is a label-free, API-compatible gate for test-time filtering.
  arXiv  Detail & Related papers  (2025-09-26T23:40:47Z)
• Error-quantified Conformal Inference for Time Series [55.11926160774831]
  Uncertainty quantification in time series prediction is challenging due to the temporal dependence and distribution shift on sequential data.<n>We propose itError-quantified Conformal Inference (ECI) by smoothing the quantile loss function.<n>ECI can achieve valid miscoverage control and output tighter prediction sets than other baselines.
  arXiv  Detail & Related papers  (2025-02-02T15:02:36Z)
• Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment [104.18002641195442]
  We introduce Self-Augmented Preference Optimization (SAPO), an effective and scalable training paradigm that does not require existing paired data. Building on the self-play concept, which autonomously generates negative responses, we further incorporate an off-policy learning pipeline to enhance data exploration and exploitation.
  arXiv  Detail & Related papers  (2024-05-31T14:21:04Z)
• Kernel-based Optimally Weighted Conformal Prediction Intervals [12.814084012624916]
  We present Kernel-based Optimally Weighted Conformal Prediction Intervals (KOWCPI)<n>KOWCPI adapts the classic Reweighted Nadaraya-Watson (RNW) estimator for quantile regression on dependent data and learns optimal data-adaptive weights.<n>We demonstrate the superior performance of KOWCPI on real and synthetic time-series data against state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-05-27T04:49:41Z)
• Distribution-Free Finite-Sample Guarantees and Split Conformal Prediction [0.0]
  split conformal prediction represents a promising avenue to obtain finite-sample guarantees under minimal distribution-free assumptions. We highlight the connection between split conformal prediction and classical tolerance predictors developed in the 1940s.
  arXiv  Detail & Related papers  (2022-10-26T14:12:24Z)
• A general framework for multi-step ahead adaptive conformal heteroscedastic time series forecasting [0.0]
  This paper introduces a novel model-agnostic algorithm called adaptive ensemble batch multi-input multi-output conformalized quantile regression (AEnbMIMOCQR) It enables forecasters to generate multi-step ahead prediction intervals for a fixed pre-specified miscoverage rate in a distribution-free manner. Our method is grounded on conformal prediction principles, however, it does not require data splitting and provides close to exact coverage even when the data is not exchangeable.
  arXiv  Detail & Related papers  (2022-07-28T16:40:26Z)
• Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning from Offline Datasets [101.5329678997916]
  We study episodic two-player zero-sum Markov games (MGs) in the offline setting. The goal is to find an approximate Nash equilibrium (NE) policy pair based on a dataset collected a priori.
  arXiv  Detail & Related papers  (2022-02-15T15:39:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.