English
Related papers

Related papers: Power-law Dynamic arising from machine learning

200 papers

We provide a new characterization of law-invariant backward stochastic differential equations (i.e. BSDEs) with quadratic growth. This answers the open question raised in Xu--Xu--Zhou (2022) on necessary conditions for law-invariance of…

Optimization and Control · Mathematics 2026-04-16 Zakaria Bensaid , Roxana Dumitrescu , Anis Matoussi , Wissal Sabbagh

We investigate the relaxation of long-tailed distributions under stochastic dynamics that do not support such tails. Linear relaxation is found to be a borderline case in which long tails are exponentially suppressed in time but not…

Statistical Mechanics · Physics 2015-06-22 Christian Van den Broeck , Upendra Harbola , Raul Toral , Katja Lindenberg

Starting from a heuristic learning scheme for N-person games, we derive a new class of continuous-time learning dynamics consisting of a replicator-like drift adjusted by a penalty term that renders the boundary of the game's strategy space…

Optimization and Control · Mathematics 2014-04-08 Pierre Coucheney , Bruno Gaujal , Panayotis Mertikopoulos

Power-law distributions occur in wide variety of physical, biological, and social phenomena. In this paper, we propose a statistical hypothesis test based on the log-likelihood ratio to assess whether two samples of discrete data are drawn…

Methodology · Statistics 2015-03-03 Alessandro Bessi

In constrained reinforcement learning (C-RL), an agent seeks to learn from the environment a policy that maximizes the expected cumulative reward while satisfying minimum requirements in secondary cumulative reward constraints. Several…

Machine Learning · Computer Science 2022-12-06 Tianqi Zheng , Pengcheng You , Enrique Mallada

We discuss several models in order to shed light on the origin of power-law distributions and power-law correlations in financial time series. From an empirical point of view, the exponents describing the tails of the price increments…

Condensed Matter · Physics 2007-05-23 Jean-Philippe Bouchaud

We present a version of the stochastic maximum principle (SMP) for ergodic control problems. In particular we give necessary (and sufficient) conditions for optimality for controlled dissipative systems in finite dimensions. The strategy we…

Probability · Mathematics 2019-08-05 Carlo Orrieri , Gianmario Tessitore , Petr Veverka

We propose a generative framework for learning stochastic dynamics from endpoint and intermediate distributional observations. The method formulates generation as a McKean-Vlasov control problem in which terminal and time-marginal laws are…

Optimization and Control · Mathematics 2026-05-12 Samer El Boustany , Samy Mekkaoui , Yadh Hafsi , Alexandre Alouadi , Huyên Pham

We study ergodic properties of a family of traffic maps acting in the space of bi-infinite sequences of real numbers. The corresponding dynamics mimics the motion of vehicles in a simple traffic flow, which explains the name. Using…

Dynamical Systems · Mathematics 2015-06-11 Michael Blank

In this paper we study the behavior of a continuous time random walk (CTRW) on a stationary and ergodic time varying dynamic graph. We establish conditions under which the CTRW is a stationary and ergodic process. In general, the stationary…

Social and Information Networks · Computer Science 2012-12-04 Daniel Figueiredo , Philippe Nain , Bruno Ribeiro , Edmundo de Souza e Silva , Don Towsley

Stochastic dynamics has emerged as one of the key themes ranging from models in applications to theoretical foundations in mathematics. One class of stochastic dynamics problems that has received considerable attention recently are…

Analysis of PDEs · Mathematics 2021-11-16 Christian Kuehn , James MacLaurin , Giulio Zucal

Stochastic gradient Langevin dynamics (SGLD) is a fundamental algorithm in stochastic optimization. Recent work by Zhang et al. [2017] presents an analysis for the hitting time of SGLD for the first and second order stationary points. The…

Machine Learning · Statistics 2020-03-17 Xi Chen , Simon S. Du , Xin T. Tong

The Primal-Dual (PD) algorithm is widely used in convex optimization to determine saddle points. While the stability of the PD algorithm can be easily guaranteed, strict contraction is nontrivial to establish in most cases. This work…

Optimization and Control · Mathematics 2018-11-21 Hung D. Nguyen , Thanh Long Vu , Konstantin Turitsyn , Jean-Jacques Slotine

We prove a general existence result in stochastic optimal control in discrete time where controls take values in conditional metric spaces, and depend on the current state and the information of past decisions through the evolution of a…

Optimization and Control · Mathematics 2018-12-19 Asgar Jamneshan , Michael Kupper , José Miguel Zapata

In this paper we consider a multidimensional random walk killed on leaving a right circular cone with a distribution of increments belonging to the normal domain of attraction of an $\alpha$-stable and rotationally-invariant law with…

Probability · Mathematics 2024-09-30 Wojciech Cygan , Denis Denisov , Zbigniew Palmowski , Vitali Wachtel

The dynamics of one dimensional iterative maps in the regime of fully developed chaos is studied in detail. Motivated by the observation of dynamical structures around the unstable fixed point we introduce the geometrical concept of a…

chao-dyn · Physics 2015-06-24 P. Schmelcher , F. K. Diakonos

This paper proves that the episodic learning environment of every finite-horizon decision task has a unique steady state under any behavior policy, and that the marginal distribution of the agent's input indeed converges to the steady-state…

Machine Learning · Computer Science 2021-01-14 Huang Bojun

Power laws and distributions with heavy tails are common features of many experimentally studied complex systems, like the distribution of the sizes of earthquakes and solar flares, or the duration of neuronal avalanches in the brain.…

Adaptation and Self-Organizing Systems · Physics 2014-03-05 Dimitrije Markovic , Claudius Gros

We consider the combined influence of linear damping and noise on a dynamical finite-time-singularity model for a single degree of freedom. We find that the noise effectively resolves the finite-time-singularity and replaces it by a…

Statistical Mechanics · Physics 2014-10-07 Hans C. Fogedby

We prove a metric space scaling limit for a critical random graph with independent and identically distributed degrees having power-law tail behaviour with exponent $\alpha+1$, where $\alpha \in (1,2)$. The limiting components are…

Probability · Mathematics 2021-08-02 Guillaume Conchon--Kerjan , Christina Goldschmidt