English
Related papers

Related papers: Generalization Bounds for Markov Algorithms throug…

200 papers

We introduce ImitationFlow, a novel Deep generative model that allows learning complex globally stable, stochastic, nonlinear dynamics. Our approach extends the Normalizing Flows framework to learn stable Stochastic Differential Equations.…

Machine Learning · Computer Science 2020-10-27 Julen Urain , Michelle Ginesi , Davide Tateo , Jan Peters

Recent years have seen advances in generalization bounds for noisy stochastic algorithms, especially stochastic gradient Langevin dynamics (SGLD) based on stability (Mou et al., 2018; Li et al., 2020) and information theoretic approaches…

Machine Learning · Computer Science 2022-11-02 Arindam Banerjee , Tiancong Chen , Xinyan Li , Yingxue Zhou

Generalization of the Lorden's inequality is an excellent tool for obtaining strong upper bounds for the convergence rate for various complicated stochastic models. This paper demonstrates a method for obtaining such bounds for some…

Probability · Mathematics 2020-10-13 Galina Zverkina

The paper describes an approach to measuring convergence of an algorithm to its result in terms of an entropy-like function of partitions of its inputs of a given length. The goal is to look at the algorithmic data processing from the…

Computational Complexity · Computer Science 2016-05-06 Anatol Slissenko

The concept of entropy in statistical physics is related to the existence of irreversible macroscopic processes. In this work, we explore a recently introduced entropy formula for a class of stochastic processes with more than one absorbing…

Populations and Evolution · Quantitative Biology 2022-10-21 Diogo Costa-Cabanas , Fabio A. C. C. Chalub , Max O. Souza

Modeling the dynamics of non-stationary stochastic systems requires balancing the representational power of deep learning with the mathematical transparency of classical models. While classical Markov transition operators provide explicit,…

Machine Learning · Computer Science 2026-05-07 Jan Rovirosa , Jesse Schmolze

Temporal point processes (TPPs) are a fundamental tool for modeling event sequences in continuous time, but most existing approaches rely on autoregressive parameterizations that are limited by their sequential sampling. Recent…

Machine Learning · Computer Science 2026-02-05 David Lüdke , Marten Lienen , Marcel Kollovieh , Stephan Günnemann

It has been shown \citep{broeck90:physicalreview,patarnello87:europhys} that feedforward Boolean networks can learn to perform specific simple tasks and generalize well if only a subset of the learning examples is provided for learning.…

Neural and Evolutionary Computing · Computer Science 2019-11-12 Alireza Goudarzi , Christof Teuscher , Natali Gulbahce , Thimo Rohlf

We study the problem of efficient exploration in order to learn an accurate model of an environment, modeled as a Markov decision process (MDP). Efficient exploration in this problem requires the agent to identify the regions in which…

We study Bayesian inverse problems with mixed noise, modeled as a combination of additive and multiplicative Gaussian components. While traditional inference methods often assume fixed or known noise characteristics, real-world…

Machine Learning · Computer Science 2025-10-17 Paul Hagemann , Robert Gruhlke , Bernhard Stankewitz , Claudia Schillings , Gabriele Steidl

This paper introduces a novel methodology for the identification of switching dynamics for switched autoregressive linear models. Switching behavior is assumed to follow a Markov model. The system's outputs are contaminated by possibly…

Signal Processing · Electrical Eng. & Systems 2019-03-28 Sarah Hojjatinia , Constantino M. Lagoa

Inspired by recent strides in empirical efficacy of implicit learning in many robotics tasks, we seek to understand the theoretical benefits of implicit formulations in the face of nearly discontinuous functions, common characteristics for…

Robotics · Computer Science 2022-04-08 Bibit Bianchini , Mathew Halm , Nikolai Matni , Michael Posa

In this document, we introduce a notion of entropy for stochastic processes on marked rooted graphs. For this, we employ the framework of local weak limit theory for sparse marked graphs, also known as the objective method, due to…

Information Theory · Computer Science 2019-08-05 Payam Delgosha , Venkat Anantharam

Transferring knowledge from one neural network to another has been shown to be helpful for learning tasks with few training examples. Prevailing fine-tuning methods could potentially contaminate pre-trained features by comparably high…

Machine Learning · Computer Science 2019-07-15 Farshid Varno , Behrouz Haji Soleimani , Marzie Saghayi , Lisa Di Jorio , Stan Matwin

Ideas and formalisms from far-from-equilibrium thermodynamics are ported to the context of stochastic computational processes, via following and extending Tadaki's algorithmic thermodynamics. A Principle of Maximum Algorithmic Caliber is…

Artificial Intelligence · Computer Science 2020-05-12 Ben Goertzel

We derive new concentration bounds for time averages of measurement outcomes in quantum Markov processes. This generalizes well-known bounds for classical Markov chains which provide constraints on finite time fluctuations of time-additive…

Quantum Physics · Physics 2023-07-19 Federico Girotti , Juan P. Garrahan , Mădălin Guţă

The information-theoretic framework of Russo and J. Zou (2016) and Xu and Raginsky (2017) provides bounds on the generalization error of a learning algorithm in terms of the mutual information between the algorithm's output and the training…

Machine Learning · Statistics 2020-10-26 Mahdi Haghifam , Jeffrey Negrea , Ashish Khisti , Daniel M. Roy , Gintare Karolina Dziugaite

We address the problem of community detection in networks by introducing a general definition of Markov stability, based on the difference between the probability fluxes of a Markov chain on the network at different time scales. The…

Physics and Society · Physics 2020-05-05 Aurelio Patelli , Andrea Gabrielli , Giulio Cimini

Stochastic approximation is a framework unifying many random iterative algorithms occurring in a diverse range of applications. The stability of the process is often difficult to verify in practical applications and the process may even be…

Probability · Mathematics 2014-03-10 Christophe Andrieu , Matti Vihola

We consider an agent trying to bring a system to an acceptable state by repeated probabilistic action. Several recent works on algorithmizations of the Lovasz Local Lemma (LLL) can be seen as establishing sufficient conditions for the agent…

Discrete Mathematics · Computer Science 2016-11-29 Dimitris Achlioptas , Fotis Iliopoulos , Nikos Vlassis