paper-with-me

홈 › Papers

Path Structured Multimarginal Schrödinger Bridge for Probabilistic Learning of Hardware Resource Usage by Control Software

2023-10-01 · Georgiy A. Bondar, Robert Gifford, Linh Thi Xuan Phan, Abhishek Halder

The solution of the path structured multimarginal Schr\"{o}dinger bridge problem (MSBP) is the most-likely measure-valued trajectory consistent with a sequence of observed probability measures or distributional snapshots. We leverage recent algorithmic advances in solving such structured MSBPs for learning stochastic hardware resource usage by control software. The solution enables predicting the time-varying distribution of hardware resource availability at a desired time with guaranteed linear convergence. We demonstrate the efficacy of our probabilistic learning approach in a model predictive control software execution case study. The method exhibits rapid convergence to an accurate prediction of hardware resource utilization of the controller. The method can be broadly applied to any software to predict cyber-physical context-dependent performance at arbitrary time.

📄 PDF Abstract BibTeX arXiv:2310.00604

Code (0)

등록된 구현이 없습니다.

Tasks

Model Predictive Control

Similar Papers 제목 키워드 기반

Tree-Based Diffusion Schrödinger Bridge with Applications to Wasserstein Barycenters

2023-05-26 · NeurIPS 2023 11 · Maxence Noble, Valentin De Bortoli, Arnaud Doucet, Alain Durmus

Multi-marginal Optimal Transport (mOT), a generalization of OT, aims at minimizing the integral of a cost function with respect to a distribution with some prescribed marginals. In this paper, we consider an entropic ver…

Stochastic Learning of Computational Resource Usage as Graph Structured Multimarginal Schrödinger Bridge

2024-05-21 · Georgiy A. Bondar, Robert Gifford, Linh Thi Xuan Phan, Abhishek Halder

We propose to learn the time-varying stochastic computational resource usage of software as a graph structured Schr\"odinger bridge problem. In general, learning the computational resource usage from data is challenging …

CPU

Optimal Multimarginal Schrödinger Bridge: Minimum Spanning Tree over Measure-valued Vertices

2025-09-12 · Georgiy A. Bondar, Abhishek Halder arxiv

The Multimarginal Schrödinger Bridge (MSB) finds the optimal coupling among a collection of random vectors with known statistics and a known correlation structure. In the MSB formulation, this correlation structure is sp…

Reflected Schrödinger Bridge: Density Control with Path Constraints

2020-03-31 · Kenneth F. Caluya, Abhishek Halder

How to steer a given joint state probability density function to another over finite horizon subject to a controlled stochastic dynamics with hard state (sample path) constraints? In applications, state constraints may e…

Foundations of Schrödinger Bridges for Generative Modeling

2026-03-19 · Sophia Tang arxiv

At the core of modern generative modeling frameworks, including diffusion models, score-based models, and flow matching, is the task of transforming a simple prior distribution into a complex target distribution through …