English
Related papers

Related papers: A theoretical framework for overfitting in energy-…

200 papers

We develop a probabilistic framework for analysing model-based reinforcement learning in the episodic setting. We then apply it to study finite-time horizon stochastic control problems with linear dynamics but unknown coefficients and…

Machine Learning · Computer Science 2021-12-22 Lukasz Szpruch , Tanut Treetanthiploet , Yufei Zhang

Data-driven models analyze power grids under incomplete physical information, and their accuracy has been mostly validated empirically using certain training and testing datasets. This paper explores error bounds for data-driven models…

Machine Learning · Computer Science 2020-05-27 Yuxiao Liu , Bolun Xu , Audun Botterud , Ning Zhang , Chongqing Kang

Meta learning has demonstrated tremendous success in few-shot learning with limited supervised data. In those settings, the meta model is usually overparameterized. While the conventional statistical learning theory suggests that…

Machine Learning · Computer Science 2022-11-10 Lisha Chen , Songtao Lu , Tianyi Chen

Learning at the edge is a challenging task from several perspectives, since data must be collected by end devices (e.g. sensors), possibly pre-processed (e.g. data compression), and finally processed remotely to output the result of…

Signal Processing · Electrical Eng. & Systems 2022-04-26 Mattia Merluzzi , Claudio Battiloro , Paolo Di Lorenzo , Emilio Calvanese Strinati

In this paper we study the problem of learning minimum-energy controls for linear systems from heterogeneous data. Specifically, we consider datasets comprising input, initial and final state measurements collected using experiments with…

Optimization and Control · Mathematics 2020-06-22 Giacomo Baggio , Fabio Pasqualetti

We derive closed-form expressions for the Bayes optimal decision boundaries in binary classification of high dimensional overlapping Gaussian mixture model (GMM) data, and show how they depend on the eigenstructure of the class covariances,…

Machine Learning · Statistics 2024-05-29 Khen Cohen , Noam Levi , Yaron Oz

Model-based reinforcement learning is an effective approach for controlling an unknown system. It is based on a longstanding pipeline familiar to the control community in which one performs experiments on the environment to collect a…

Systems and Control · Electrical Eng. & Systems 2024-08-14 Bruce D. Lee , Ingvar Ziemann , George J. Pappas , Nikolai Matni

Model-based planning holds great promise for improving both sample efficiency and generalization in reinforcement learning (RL). We show that energy-based models (EBMs) are a promising class of models to use for model-based planning. EBMs…

Machine Learning · Computer Science 2021-03-09 Yilun Du , Toru Lin , Igor Mordatch

There have been two separate lines of work on estimating Ising models: (1) estimating them from multiple independent samples under minimal assumptions about the model's interaction matrix; and (2) estimating them from one sample in…

Statistics Theory · Mathematics 2020-12-11 Yuval Dagan , Constantinos Daskalakis , Nishanth Dikkala , Anthimos Vardis Kandiros

This paper deals with the problem of adaptive output regulation for multivariable nonlinear systems by presenting a learning-based adaptive internal model-based design strategy. The approach builds on the recently proposed adaptive internal…

Systems and Control · Electrical Eng. & Systems 2022-10-31 Lorenzo Gentilini , Michelangelo Bin , Lorenzo Marconi

Despite its remarkable empirical success as a highly competitive branch of artificial intelligence, deep learning is often blamed for its widely known low interpretation and lack of firm and rigorous mathematical foundation. However, most…

Machine Learning · Computer Science 2018-10-04 Wendi Xu , Ming Zhang

We introduce a new family of energy-based probabilistic graphical models for efficient unsupervised learning. Its definition is motivated by the control of the spin-glass properties of the Ising model described by the weights of Boltzmann…

We propose the use of Bayesian networks, which provide both a mean value and an uncertainty estimate as output, to enhance the safety of learned control policies under circumstances in which a test-time input differs significantly from the…

Machine Learning · Computer Science 2019-02-18 Keuntaek Lee , Kamil Saigol , Evangelos A. Theodorou

Locally adapted parameterizations of a model (such as locally weighted regression) are expressive but often suffer from high variance. We describe an approach for reducing the variance, based on the idea of estimating simultaneously a…

Machine Learning · Computer Science 2012-07-03 Doina Precup , Philip Bachman

In data-mining applications, we are frequently faced with a large fraction of missing entries in the data matrix, which is problematic for most discriminant machine learning algorithms. A solution that we explore in this paper is the use of…

Machine Learning · Computer Science 2018-01-09 Olivier Delalleau , Aaron Courville , Yoshua Bengio

Significant advances in edge computing capabilities enable learning to occur at geographically diverse locations. In general, the training data needed in those learning tasks are not only heterogeneous but also not fully generated locally.…

Networking and Internet Architecture · Computer Science 2022-01-14 Yuezhou Liu , Yuanyuan Li , Lili Su , Edmund Yeh , Stratis Ioannidis

The evaluation of Deep Learning models has traditionally focused on criteria such as accuracy, F1 score, and related measures. The increasing availability of high computational power environments allows the creation of deeper and more…

Machine Learning · Computer Science 2023-02-03 Yinlena Xu , Silverio Martínez-Fernández , Matias Martinez , Xavier Franch

This paper proposes the divergence triangle as a framework for joint training of generator model, energy-based model and inference model. The divergence triangle is a compact and symmetric (anti-symmetric) objective function that seamlessly…

Machine Learning · Statistics 2019-02-01 Tian Han , Erik Nijkamp , Xiaolin Fang , Mitch Hill , Song-Chun Zhu , Ying Nian Wu

Changepoint detection is commonly formulated by minimizing the sum of in-sample losses to quantify the model's overall fit. However, for flexible modeling procedures -- especially those involving high-dimensional parameter spaces or…

Methodology · Statistics 2026-05-05 Chengde Qian , Guanghui Wang , Zhaojun Wang , Changliang Zou

Training energy-based models (EBMs) on discrete spaces is challenging because sampling over such spaces can be difficult. We propose to train discrete EBMs with energy discrepancy (ED), a novel type of contrastive loss functional which only…

Machine Learning · Statistics 2023-07-18 Tobias Schröder , Zijing Ou , Yingzhen Li , Andrew B. Duncan
‹ Prev 1 4 5 6 7 8 10 Next ›