English
Related papers

Related papers: A Markovian Model for Learning-to-Optimize

200 papers

We consider a moving target that we seek to learn from samples. Our results extend randomized techniques developed in control and optimization for a constant target to the case where the target is changing. We derive a novel bound on the…

Optimization and Control · Mathematics 2025-11-11 Nikolaus Vertovec , Kostas Margellos , Maria Prandini

Deep Probabilistic Programming (DPP) allows powerful models based on recursive computation to be learned using efficient deep-learning optimization techniques. Additionally, DPP offers a unified perspective, where inference and learning…

Machine Learning · Computer Science 2022-03-31 Jonathan Warrell , Mark Gerstein

We develop a model-free approach to optimally control stochastic, Markovian systems subject to a reach-avoid constraint. Specifically, the state trajectory must remain within a safe set while reaching a target set within a finite time…

Optimization and Control · Mathematics 2025-09-30 Tingting Ni , Maryam Kamgarpour

We propose probabilistic models that can extrapolate learning curves of iterative machine learning algorithms, such as stochastic gradient descent for training deep networks, based on training data with variable-length learning curves. We…

Machine Learning · Computer Science 2019-10-11 Matilde Gargiani , Aaron Klein , Stefan Falkner , Frank Hutter

We propose a new approach to apply the chaining technique in conjunction with information-theoretic measures to bound the generalization error of machine learning algorithms. Different from the deterministic chaining approach based on…

Information Theory · Computer Science 2022-01-31 Ruida Zhou , Chao Tian , Tie Liu

Bayesian optimization is proposed for automatic learning of optimal controller parameters from experimental data. A probabilistic description (a Gaussian process) is used to model the unknown function from controller parameters to a…

Systems and Control · Computer Science 2019-01-24 Matthias Neumann-Brosig , Alonso Marco , Dieter Schwarzmann , Sebastian Trimpe

Optimization is becoming increasingly common in scientific and engineering domains. Oftentimes, these problems involve various levels of stochasticity or uncertainty in generating proposed solutions. Therefore, optimization in these…

Machine Learning · Statistics 2020-06-05 Peter D. Tonner , Daniel V. Samarov , A. Gilad Kusne

We propose new continuous-time formulations for first-order stochastic optimization algorithms such as mini-batch gradient descent and variance-reduced methods. We exploit these continuous-time models, together with simple Lyapunov analysis…

Optimization and Control · Mathematics 2020-03-12 Antonio Orvieto , Aurelien Lucchi

We present a Markov-chain analysis of blockwise-stochastic algorithms for solving partially block-separable optimization problems. Our main contributions to the extensive literature on these methods are statements about the Markov operators…

Optimization and Control · Mathematics 2023-11-01 D. Russell Luke

The goal of this paper is to analyze distributional Markov Decision Processes as a class of control problems in which the objective is to learn policies that steer the distribution of a cumulative reward toward a prescribed target law,…

Optimization and Control · Mathematics 2026-02-09 Nicole Bäuerle , Athanasios Vasileiadis

Over the last few years, sampling-based stochastic optimal control (SOC) frameworks have shown impressive performances in reinforcement learning (RL) with applications in robotics. However, such approaches require a large amount of samples…

Systems and Control · Computer Science 2014-12-10 Yunpeng Pan , Evangelos A. Theodorou , Michail Kontitsis

We introduce a statistical physics inspired supervised machine learning algorithm for classification and regression problems. The method is based on the invariances or stability of predicted results when known data is represented as…

Machine Learning · Statistics 2018-11-19 Patrick Chao , Tahereh Mazaheri , Bo Sun , Nicholas B. Weingartner , Zohar Nussinov

This paper describes stochastic search approaches, including a new stochastic algorithm and an adaptive mutation operator, for learning Bayesian networks from incomplete data. This problem is characterized by a huge solution space with a…

Artificial Intelligence · Computer Science 2013-01-30 James W. Myers , Kathryn Blackmond Laskey , Tod S. Levitt

We present the first PAC optimal algorithm for Bayes-Adaptive Markov Decision Processes (BAMDPs) in continuous state and action spaces, to the best of our knowledge. The BAMDP framework elegantly addresses model uncertainty by incorporating…

Machine Learning · Computer Science 2018-10-09 Gilwoo Lee , Sanjiban Choudhury , Brian Hou , Siddhartha S. Srinivasa

A Bayesian network is a widely used probabilistic graphical model with applications in knowledge discovery and prediction. Learning a Bayesian network (BN) from data can be cast as an optimization problem using the well-known…

Artificial Intelligence · Computer Science 2018-11-14 Zhenyu A. Liao , Charupriya Sharma , James Cussens , Peter van Beek

This paper examines Bayesian belief network inference using simulation as a method for computing the posterior probabilities of network variables. Specifically, it examines the use of a method described by Henrion, called logic sampling,…

Artificial Intelligence · Computer Science 2013-04-11 Homer L. Chin , Gregory F. Cooper

Iterative trajectory optimization techniques for non-linear dynamical systems are among the most powerful and sample-efficient methods of model-based reinforcement learning and approximate optimal control. By leveraging time-variant local…

Systems and Control · Electrical Eng. & Systems 2019-08-01 Onur Celik , Hany Abdulsamad , Jan Peters

PAC-Bayes learning is an established framework to both assess the generalisation ability of learning algorithms, and design new learning algorithm by exploiting generalisation bounds as training objectives. Most of the exisiting bounds…

Machine Learning · Statistics 2023-05-31 Maxime Haddouche , Benjamin Guedj

This article focuses on the multi-objective optimization of stochastic simulators with high output variance, where the input space is finite and the objective functions are expensive to evaluate. We rely on Bayesian optimization algorithms,…

Optimization and Control · Mathematics 2022-07-21 Bruno Barracosa , Julien Bect , Héloïse Dutrieux Baraffe , Juliette Morin , Josselin Fournel , Emmanuel Vazquez

We present a new PAC-Bayesian generalization bound. Standard bounds contain a $\sqrt{L_n \cdot \KL/n}$ complexity term which dominates unless $L_n$, the empirical error of the learning algorithm's randomized predictions, vanishes. We manage…

Machine Learning · Computer Science 2021-12-16 Zakaria Mhammedi , Peter D. Grunwald , Benjamin Guedj
‹ Prev 1 4 5 6 7 8 10 Next ›