Home Knowledge Base Markov

Markov

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

True Self-Avoiding Walk for Accelerating Markov-Chain Monte Carlo Integration

Announce Type: cross Abstract: We study true self-avoiding walk (TSAW) as a mechanism for improving empirical integral estimation via Markov chain Monte Carlo (MCMC). We consider finite-state adaptive sampling dynamics associated with an irreducible Markov kernel $P$ on a finite set, with stationary distribution $\pi$, in which the transition probabilities are penalized according to empirical overuse. Our main result is that the empirical occupation counts $L_t(i)$ and transition counts...

arXiv CS 9d ago

Identifiable Markov Switching Models with Instantaneous Effects and Exponential Families

arXiv:2606.02231v1 Announce Type: cross Abstract: Temporal systems often exhibit non-stationary behaviour, such as seasonal climate variation or glucose fluctuations in patients with type-1 diabetes. One way to model non-stationarity is through discrete latent regimes, i.e., stationary segments of time. Such systems induce a Markov Switching Model (MSM), a class of Hidden Markov Models with autoregressive dependencies among latent regimes and observed variables.

arXiv CS 8d ago

Algebraic and FFT-Based Methods for Discrete-Time Matrix Convolutions with Applications to Semi-Markov Models

arXiv:2605.30379v2 Announce Type: replace Abstract: We study the convolution product of matrix-valued sequences and its role in the computation of Markov renewal equations. Explicit representations and recursive formulae for the convolutional inverse are derived and used to construct FFT-accelerated convolution and Newton-type inversion schemes, together with a Gauss--Jordan alternative in truncated power-series rings. The proposed framework is also applied to discrete approximations of...

arXiv CS 8d ago

A Doeblin-Anchored Contrastive Chart for Learning Markov Transition Kernels

arXiv:2606.02232v1 Announce Type: new Abstract: Learning a Markov transition model is not merely conditional density estimation: the learned object must be a valid transition kernel before it is iterated in downstream dynamics. This paper introduces a Doeblin-anchored contrastive chart, a statistical-to-dynamical coordinate framework for learning transition kernels from contrastive objectives. Given a restart law and an anchor strength, the chart mixes the target transition with the restart law.

arXiv CS 8d ago

Algebraic and FFT-Based Methods for Discrete-Time Matrix Convolutions with Applications to Semi-Markov Models

arXiv:2605.30379v1 Announce Type: new Abstract: We study the convolution product of matrix-valued sequences and its role in the computation of Markov renewal equations. Explicit representations and recursive formulae for the convolutional inverse are derived and used to construct FFT-accelerated convolution and Newton-type inversion schemes, together with a Gauss--Jordan alternative in truncated power-series rings. The proposed framework is also applied to discrete approximations of matrix...

arXiv CS 9d ago

Brief Announcement: Generative Markov Model for Distributed Computing Systems

Announce Type: new Abstract: Emerging distributed computing paradigms, such as the computing continuum, are inherently heterogeneous, stochastic, and complex. Efficiently and effectively utilizing all available resources across the continuum demands a unified formal model of the system. To address this gap, we propose a general framework for modeling distributed computing systems as a generative Markov model, factorized over a structured system state.

arXiv CS 7d ago

Theoretical Analysis of Engression and Reverse Markov Engression

Announce Type: cross Abstract: Engression is a recently proposed and effective framework for conditional distribution learning. Its multi-step Reverse Markov extension further improves generative flexibility by decomposing complex conditional sampling into sequential reverse transitions. Despite their strong empirical performance, rigorous finite-sample statistical guarantees for these methods remain unavailable.

arXiv CS 8d ago

Minimax-Optimal Policy Regret in Partially Observable Markov Games

arXiv:2606.02363v1 Announce Type: new Abstract: We study sequential decision-making in partially observable environments against strategic, adaptive opponents, modeled as partially observable Markov games (POMGs). The central challenge is to learn latent dynamics from partial observations while facing an adversary whose behavior depends on the learner's strategy, making standard regret notions inadequate. We prove that an epoch-based optimistic maximum-likelihood algorithm achieves...

arXiv CS 8d ago

Policy Gradient for Continuous-Time Robust Markov Decision Processes

Announce Type: new Abstract: The framework of robust Markov decision processes (RMDPs) allows the design of reinforcement learning agents that satisfy performance guarantees under worst-case transition dynamics. Traditional RMDPs consider discrete-time dynamics and recently, sample-efficient policy gradient algorithms have been considered in this context. This paper investigates policy gradient algorithms within a continuous-time RMDP framework.

arXiv CS 6d ago

Randomization for Faster Exact Optimization of Discounted Markov Decision Processes

arXiv:2606.05110v1 Announce Type: new Abstract: We provide faster deterministic and randomized algorithms for exactly solving discounted Markov Decision Processes (DMDPs). We obtain our results by efficiently reducing computing optimal values and policies in DMDPs to the easier tasks of policy evaluation and computing approximately optimal values in DMDPs. We provide both a straightforward deterministic reduction and a more efficient randomized variant that, together with advances in...

arXiv CS 6d ago