Generative sequence modeling for infinite memory processes via predictive states
Read the original on arXiv Statistics ML →The Flow has not summarised this story yet — read it at arXiv Statistics ML.
The Flow has not summarised this story yet — read it at arXiv Statistics ML.
arXiv:2610.06894v1 Announce Type: cross Abstract: A central question in the prediction of stochastic processes is the extent to which past information can improve the probability of correctly predict...
arXiv:2606. 01002v1 Announce Type: cross Abstract: Engression is a recently proposed and effective framework for conditional distribution learning.
arXiv:2606. 01999v1 Announce Type: cross Abstract: Modern deep learning models for forecasting groups of time series rely on increasingly longer observation windows.
arXiv:2607. 16725v1 Announce Type: cross Abstract: Conditional generative modeling remains a challenging problem in semi-supervised settings where labeled data is scarce but unlabeled samples are abundant.
The paper presents empirical concentration inequalities for stationary chains with infinite memory, extending previous results that were limited to Markov chains. It establishes a bounded‑differences inequality under a summable Wasserstein contraction condition and shows how to estimate the necessary dependence coefficients from a single trajectory, using transition counts for finite state spaces or kernel density derivatives for continuous spaces. The authors provide general error bounds that reflect the memory tail and demonstrate that, after applying a fixed safety factor, the resulting empirical bounds are asymptotically as tight as the theoretical ones, while remaining fully adaptive without requiring knowledge of the underlying constants.
arXiv:2506. 05678v3 Announce Type: replace Abstract: The evolution of sequence modeling architectures, from recurrent neural networks and convolutional models to Transformers and structured state-space models, reflects ongoing efforts to address the diverse temporal dependencies inherent in sequential data.