English
Related papers

Related papers: A Variational Principle Based Study of KPP Minimal…

200 papers

We consider the fundamental problem of learning the parameters of an undirected graphical model or Markov Random Field (MRF) in the setting where the edge weights are chosen at random. For Ising models, we show that a multiplicative-weight…

Machine Learning · Computer Science 2024-11-19 Gautam Chandrasekaran , Adam Klivans

Probabilistic shaping (PS) is investigated as a potential technique to approach the Shannon limit. However, it has been proved that conventional carrier phase recovery (CPR) algorithm designed for uniform distribution may have extra penalty…

Signal Processing · Electrical Eng. & Systems 2021-02-03 Jin Hu , Zhongliang Sun , Xuekai Xu , Mengqi Guo , Xizi Tang , Yueming Lu , Yaojun Qiao

Stochastic gradient descent (SGD) is a cornerstone of machine learning. When the number N of data items is large, SGD relies on constructing an unbiased estimator of the gradient of the empirical risk using a small subset of the original…

Machine Learning · Statistics 2021-12-14 Remi Bardenet , Subhro Ghosh , Meixia Lin

While nowadays most gradient-based optimization methods focus on exploring the high-dimensional geometric features, the random error accumulated in a stochastic version of any algorithm implementation has not been stressed yet. In this…

Machine Learning · Computer Science 2020-08-14 Tong Yang , Long Sha , Pengyu Hong

We study average-reward Markov decision processes (AMDPs) and develop novel first-order methods with strong theoretical guarantees for both policy optimization and policy evaluation. Compared with intensive research efforts in finite sample…

Machine Learning · Computer Science 2024-10-01 Tianjiao Li , Feiyang Wu , Guanghui Lan

Piecewise deterministic Markov processes (PDMPs) are a class of continuous-time Markov processes that were recently used to develop a new class of Markov chain Monte Carlo algorithms. However, the implementation of the processes is…

Computation · Statistics 2024-08-08 Charly Andral , Kengo Kamatani

Gaussian processes (GPs) are frequently used in machine learning and statistics to construct powerful models. However, when employing GPs in practice, important considerations must be made, regarding the high computational burden,…

Computation · Statistics 2021-03-08 Karla Monterrubio-Gómez , Sara Wade

A piecewise-deterministic Markov process is a stochastic process whose behavior is governed by an ordinary differential equation punctuated by random jumps occurring at random times. We focus on the nonparametric estimation problem of the…

Statistics Theory · Mathematics 2016-05-24 Romain Azaïs , Aurélie Muller-Gueudin

It is well known that the fluid-particle acceleration is intimately related to the dissipation rate of turbulence, in line with the Kolmogorov assumptions. On the other hand, various experimental and numerical works have reported as well…

Fluid Dynamics · Physics 2022-08-22 Rémi Zamansky

Analysing stationary point databases to extract phenomenological rate constants can become time-consuming for systems with large potential energy barriers. In the present contribution we analyse several different approaches to this problem.…

Soft Condensed Matter · Physics 2009-11-11 Semen A. Trygubenko , David J. Wales

Markov jump processes (MJPs) are used to model a wide range of phenomena from disease progression to RNA path folding. However, maximum likelihood estimation of parametric models leads to degenerate trajectories and inferential performance…

Machine Learning · Statistics 2015-06-08 Jonathan H. Huggins , Karthik Narasimhan , Ardavan Saeedi , Vikash K. Mansinghka

A probabilistic machine learning model is introduced to augment the $k-\omega\ SST$ turbulence model in order to improve the modelling of separated flows and the generalisability of learnt corrections. Increasingly, machine learning methods…

Computational Engineering, Finance, and Science · Computer Science 2023-01-24 Joel Ho , Nick Pepper , Tim Dodwell

Kernel methods are powerful learning methodologies that allow to perform non-linear data analysis. Despite their popularity, they suffer from poor scalability in big data scenarios. Various approximation methods, including random feature…

Machine Learning · Statistics 2022-06-14 Bharath Sriperumbudur , Nicholas Sterge

This paper investigates the existence of almost periodic traveling fronts for Fisher-KPP lattice equations in one-dimensional almost periodic media. By the Lyapunov exponent of the linearized operator near the unstable steady state, we give…

Analysis of PDEs · Mathematics 2021-04-29 Xing Liang , Hongze Wang , Qi Zhou , Tao Zhou

The stable principal component pursuit (SPCP) is a non-smooth convex optimization problem, the solution of which enables one to reliably recover the low rank and sparse components of a data matrix which is corrupted by a dense noise matrix,…

Optimization and Control · Mathematics 2015-02-10 Necdet Serhat Aybat , Garud Iyengar

We study variational principles for metric mean dimension. First we prove that in the variational principle of Lindenstrauss and Tsukamoto it suffices to take supremum over ergodic measures. Second we derive a variational principle for…

Dynamical Systems · Mathematics 2022-02-04 Yonatan Gutman , Adam Śpiewak

Randomized-subspace methods reduce the cost of first-order optimization by using only low-dimensional projected-gradient information, a feature that is attractive in forward-mode automatic differentiation and communication-limited settings.…

Optimization and Control · Mathematics 2026-05-04 Gaku Omiya , Pierre-Louis Poirion , Akiko Takeda

Determinantal Point Processes (DPPs) are elegant probabilistic models of repulsion and diversity over discrete sets of items. But their applicability to large sets is hindered by expensive cubic-complexity matrix operations for basic tasks…

Machine Learning · Computer Science 2016-05-31 Chengtao Li , Stefanie Jegelka , Suvrit Sra

A key issue in dimension reduction of dissipative dynamical systems with spectral gaps is the identification of slow invariant manifolds. We present theoretical and numerical results for a variational approach to the problem of computing…

Dynamical Systems · Mathematics 2012-11-30 Dirk Lebiedz , Jochen Siehr , Jonas Unger

A variational method is used to derive a self-consistent macro-particle model for relativistic electromagnetic kinetic plasma simulations. Extending earlier work [E. G. Evstatiev and B. A. Shadwick, J. Comput. Phys., vol. 245, pp. 376-398,…

Computational Physics · Physics 2014-04-22 A. B. Stamm , B. A. Shadwick , E. G. Evstatiev