Metraipolis › archive › dc_df368291b823

Memory Prediction Excess: A Probabilistic Quantity for Predictive Gain and Memory Length in Stochastic Processes — arXiv:2610.06894

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.06894
License (as archived)
CC0-1.0
Archived
2026-10-07T11:42:04.907Z
SHA-256 of the archived text
acd0a23dc41b8dff2799f0d7603fa6e38d2aaa744583449966f01faf36b47bcb
Stable URL of this page
https://metraipolis.com/documento/dc_df368291b823

How to cite

Memory Prediction Excess: A Probabilistic Quantity for Predictive Gain and Memory Length in Stochastic Processes — arXiv:2610.06894 — arXiv (en), https://arxiv.org/abs/2610.06894 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_df368291b823 (Metraipolis archive dc_df368291b823, sha256 acd0a23dc41b8dff2799f0d7603fa6e38d2aaa744583449966f01faf36b47bcb)
BibTeX
@misc{dcdf368291b823,
  title = {Memory Prediction Excess: A Probabilistic Quantity for Predictive Gain and Memory Length in Stochastic Processes — arXiv:2610.06894},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.06894},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_df368291b823; sha256 acd0a23dc41b8dff2799f0d7603fa6e38d2aaa744583449966f01faf36b47bcb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.06894. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A central question in the prediction of stochastic processes is the extent to which past information can improve the probability of correctly predicting the next state. We introduce the Memory Prediction Excess (MPE) to address this question quantitatively. The MPE measures the average improvement in prediction accuracy obtained by using the entire observed history relative to using only the static marginal distribution, in discrete-time finite-state processes. It is defined as the difference between the expected optimal conditional prediction accuracy and the optimal static prediction accuracy. Its basic properties are examined: the MPE is always non-negative; it admits an upper bound depending on the static accuracy, attained if and only if the future is almost surely a deterministic function of the past; and degenerate cases in which the MPE vanishes are characterized. A normalized version, taking values in the unit interval, is introduced as a dimensionless measure of predictive efficiency. A lower bound is derived by comparing predictions based on histories of different lengths, showing that the expected optimal prediction accuracy is monotone with respect to the history length. The framework is extended to finite-length histories, where the finite-history MPE (FH-MPE) measures the predictive gain attainable when only the most recent observations are retained. This leads to the notion of a minimal memory length required to achieve the same predictive performance as the full history. For finite-order Markov chains, this minimal memory length is shown to be bounded by the Markov order. The MPE and its variants are formulated in terms of conditional probabilities and prediction accuracies, offering a probabilistic perspective on the predictive utility of memory that is complementary to classical information-theoretic approaches.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (stat.ML) ; Information Theory (cs.IT); Machine Learning (cs.LG); Probability (math.PR).
Pagina del lavoro: https://arxiv.org/abs/2610.06894 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T11:19:24.859Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).