20 results for “autoregressive dynamics”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
This paper establishes the identifiability of latent regimes and regime-dependent causal structures in complex non-stationary time series modeled by Markov Switching Models, even with instantaneous ef…
Hongyu Liu, Chun Wang, Feng Gao, Xuanhua He +5 more
This paper proposes OPSD-V, an on-policy self-distillation method for reducing long-horizon degradation in few-step autoregressive video diffusion models by introducing real long-video data as tempora…
The paper argues that shallow safety alignment in LLMs is due to autoregressive consistency, a mechanism that allows small harmful inputs to redirect the model's generation to unsafe outputs, necessit…
Riju Marwah, Ritvik Garimella, Vishal Pallagani, Atishay Jain +2 more
The paper formalizes LLM degradation during long generation as 'cognitive fatigue' and introduces the Fatigue Index (FI), a measurable, model-agnostic diagnostic tool for real-time monitoring.
AdaKoop introduces an efficient streaming algorithm that models complex nonlinear dynamics from nonstationary data streams by leveraging the Koopman operator theory, achieving state-of-the-art accurac…
The paper proposes methodologies to measure lag relevance in machine learning forecasting models using Ghost variables, Shapley values, and additive importance measures. It also introduces auto-releva…
This paper introduces a stochastic differential equation approximation for linear Temporal Difference (TD) learning under Markovian noise, explaining the constant-stepsize error floor.
This paper proposes an online changepoint detection method for autoregressive processes of order p, improving detection power and computational efficiency for data with temporal correlation.
This chapter provides a pedagogical review of time series analysis techniques from a machine learning perspective.
Andreas Müller, Denis Lukovnikov, Shingo Kodama, Minh Pham +4 more
This paper analyzes existing watermarking schemes for autoregressive image generators and demonstrates that they are vulnerable to various removal and forgery attacks, suggesting they are unreliable f…
The paper introduces QuITE, a plug-and-play embedding module that uses learnable query tokens to effectively embed irregular multivariate time series data into latent representations compatible with e…
The paper argues that long context windows are necessary for time series forecasting not just to capture long-range dependencies, but primarily to reduce uncertainty about the underlying data-generati…
Daniel Waxman, Dmitry Batenkov, John Feser, Andy Zane +3 more
A probabilistic programming library, dynestyx, is introduced for Bayesian treatment of dynamical systems.
Zhengkai Pan, Peter Potaptchik, Wenxi Yao, Michael S. Albergo +1 more
The paper introduces the Itô map, a one-step stochastic flow map for predicting future states from intermediate states and Brownian paths.
The paper proposes NLBST, a hierarchical Bayesian framework for continuous spatio-temporal fields with nonlocal interactions, enabling tractable inference and uncertainty quantification.
Haoji Hu, Huaqing Mao, Yijun Lin, Xiaowei Jia +3 more
The paper proposes a novel nonparametric mutual information estimator to robustly quantify dependence between heterogeneous temporal data, specifically continuous time series and discrete event sequen…