paper-with-me

홈 › Papers

Local Entropy Search over Descent Sequences for Bayesian Optimization

2025-11-24 · David Stenger, Armin Lindicke, Alexander von Rohr, Sebastian Trimpe arxiv

Searching large and complex design spaces for a global optimum can be infeasible and unnecessary. A practical alternative is to iteratively refine the neighborhood of an initial design using local optimization methods such as gradient descent. We propose local entropy search (LES), a Bayesian optimization paradigm that explicitly targets the solutions reachable by the descent sequences of iterative optimizers. The algorithm propagates the posterior belief over the objective through the optimizer, resulting in a probability distribution over descent sequences. It then selects the next evaluation by maximizing mutual information with that distribution, using a combination of analytic entropy calculations and Monte-Carlo sampling of descent sequences. Empirical results on high-complexity synthetic objectives and benchmark problems show that LES achieves strong sample efficiency compared to existing local and global Bayesian optimization methods.

📄 PDF Abstract BibTeX arXiv:2511.19241

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Model-Predictive Control via Cross-Entropy and Gradient-Based Optimization

2020-04-19 · L4DC 2020 6 · Homanga Bharadhwaj, Kevin Xie, Florian Shkurti

Recent works in high-dimensional model-predictive control and model-based reinforcement learning with learned dynamics and reward models have resorted to population-based optimization methods, such as the Cross-Entropy M…

Model-based Reinforcement LearningModel Predictive ControlReinforcement Learning

Non-KKT Accumulation in Entropic Mirror Descent

2026-08-03 · Kuangyu Ding, Kim-Chuan Toh arxiv

For mirror descent generated by a Legendre kernel, perhaps one of the most basic question in optimization is this: must every accumulation point of a bounded mirror descent sequence be Karush--Kuhn--Tucker (KKT) stationa…

Entropy-SGD: Biasing Gradient Descent Into Wide Valleys

2016-11-06 · Pratik Chaudhari, Anna Choromanska, Stefano Soatto, Yann Lecun 외

This paper proposes a new optimization algorithm called Entropy-SGD for training deep neural networks that is motivated by the local geometry of the energy landscape. Local extrema with low generalization error have a la…

Riesz-Kernel Stein Variational Gradient Descent: Renormalized Entropy and Long-Time Particle Limits

2026-07-16 · Trevor Teolis, Maarten V. de Hoop arxiv

Stein variational gradient descent (SVGD) transports interacting particles toward a target distribution through deterministic kernelized dynamics. Singular Riesz kernels are attractive because they can provide quantitati…

Fast 3D Salient Region Detection in Medical Images using GPUs

2013-10-24 · Rahul Thota, Sharan Vaswani, Amit Kale, Nagavijayalakshmi Vydyanathan

Automated detection of visually salient regions is an active area of research in computer vision. Salient regions can serve as inputs for object detectors as well as inputs for region based registration algorithms. In th…