English
Related papers

Related papers: Finite sample learning of moving targets

200 papers

Recently, there has been significant progress in understanding reinforcement learning in discounted infinite-horizon Markov decision processes (MDPs) by deriving tight sample complexity bounds. However, in many real-world applications, an…

Machine Learning · Statistics 2016-05-12 Christoph Dann , Emma Brunskill

In this chapter, we discuss recent work on learning sparse approximations to high-dimensional functions on data, where the target functions may be scalar-, vector- or even Hilbert space-valued. Our main objective is to study how the…

Numerical Analysis · Mathematics 2022-02-08 Ben Adcock , Juan M. Cardenas , Nick Dexter , Sebastian Moraga

A novel learning Model Predictive Control technique is applied to the autonomous racing problem. The goal of the controller is to minimize the time to complete a lap. The proposed control strategy uses the data from previous laps to improve…

Machine Learning · Computer Science 2017-11-10 Ugo Rosolia , Ashwin Carvalho , Francesco Borrelli

We study reinforcement learning (RL) with linear function approximation. Existing algorithms for this problem only have high-probability regret and/or Probably Approximately Correct (PAC) sample complexity guarantees, which cannot guarantee…

Machine Learning · Computer Science 2022-01-03 Jiafan He , Dongruo Zhou , Quanquan Gu

In this paper, a guidance and tracking control strategy for fixed-wing Unmanned Aerial Vehicle (UAV) autopilots is presented. The proposed control exploits recent results on sample-based stochastic Model Predictive Control, which allow…

Systems and Control · Computer Science 2018-05-16 Martina Mammarella , Elisa Capello , Fabrizio Dabbene

We consider a discrete optimization formulation for learning sparse classifiers, where the outcome depends upon a linear combination of a small subset of features. Recent work has shown that mixed integer programming (MIP) can be used to…

Machine Learning · Statistics 2021-06-08 Antoine Dedieu , Hussein Hazimeh , Rahul Mazumder

Computing the conditional mode of a distribution, better known as the $\mathit{maximum\ a\ posteriori}$ (MAP) assignment, is a fundamental task in probabilistic inference. However, MAP estimation is generally intractable, and remains hard…

Machine Learning · Computer Science 2026-01-23 Matthew Shorvon , Frederik Mallmann-Trenn , David S. Watson

The goal of survey design is often to minimize the errors associated with inference: the total of bias and variance. Random surveys are common because they allow the use of theoretically unbiased estimators. In practice however, such…

Methodology · Statistics 2023-02-14 Connie Okasaki , Sándor F. Tóth , Andrew M. Berdahl

We informally call a stochastic process learnable if it admits a generalization error approaching zero in probability for any concept class with finite VC-dimension (IID processes are the simplest example). A mixture of learnable processes…

Machine Learning · Statistics 2015-07-27 Cosma Rohilla Shalizi , Aryeh Kontorovich

We present a new mixed integer formulation for the discrete informative path planning problem in random fields. The objective is to compute a budget constrained path while collecting measurements whose linear estimate results in minimum…

Systems and Control · Electrical Eng. & Systems 2022-04-21 Shamak Dutta , Nils Wilde , Stephen L. Smith

We study learning problems in which the underlying class is a bounded subset of $L_p$ and the target $Y$ belongs to $L_p$. Previously, minimax sample complexity estimates were known under such boundedness assumptions only when $p=\infty$.…

Machine Learning · Statistics 2020-02-05 Shahar Mendelson

Model Predictive Control (MPC) offers safe and near-optimal control but suffers from high computational costs. Approximate MPC (AMPC) mitigates this by learning a cheaper surrogate policy, typically by training a neural network on state-MPC…

Systems and Control · Electrical Eng. & Systems 2026-04-13 Elias Milios , Felix Berkel , Felix Gruber , Melanie N. Zeilinger , Kim P. Wabersich

Visual tracking is typically solved as a discriminative learning problem that usually requires high-quality samples for online model adaptation. It is a critical and challenging problem to evaluate the training samples collected from…

Computer Vision and Pattern Recognition · Computer Science 2020-04-02 Weichao Li , Xi Li , Omar Elfarouk Bourahla , Fuxian Huang , Fei Wu , Wei Liu , Zhiheng Wang , Hongmin Liu

This article focuses on making discrete-time Adaptive Iterative Learning Control (ILC) more effective using multiple estimation models. Existing strategies use the tracking error to adjust the parametric estimates. Our strategy uses the…

Systems and Control · Electrical Eng. & Systems 2024-06-14 Ram Padmanabhan , Rajini Makam , Koshy George

We use the exact finite sample likelihood and statistical decision theory to answer questions of ``why?'' and ``what should you have done?'' using data from randomized experiments and a utility function that prioritizes safety over…

Econometrics · Economics 2024-07-26 Neil Christy , A. E. Kowalski

Sampling-based Model Predictive Control (MPC) is a flexible control framework that can reason about non-smooth dynamics and cost functions. Recently, significant work has focused on the use of machine learning to improve the performance of…

Robotics · Computer Science 2022-12-07 Jacob Sacks , Byron Boots

Reachability computations that rely on learned or estimated models require calibration in order to uphold confidence about their guarantees. Calibration generally involves sampling scenarios inside the reachable set. However, producing…

Systems and Control · Electrical Eng. & Systems 2026-03-27 Sampada Deglurkar , Ebonye Smith , Jingqi Li , Claire J. Tomlin

This paper presents a novel distributed algorithm for tracking a maneuvering target using bearing or direction of arrival measurements collected by a networked sensor array. The proposed approach is built on the dynamic average-consensus…

Optimization and Control · Mathematics 2020-01-31 Jemin George

We present an improved algorithm for {\em quasi-properly} learning convex polyhedra in the realizable PAC setting from data with a margin. Our learning algorithm constructs a consistent polyhedron as an intersection of about $t \log t$…

Machine Learning · Computer Science 2021-11-03 Lee-Ad Gottlieb , Eran Kaufman , Aryeh Kontorovich , Gabriel Nivasch

Statistical performance bounds for reinforcement learning (RL) algorithms can be critical for high-stakes applications like healthcare. This paper introduces a new framework for theoretically measuring the performance of such algorithms…

Machine Learning · Computer Science 2018-01-03 Christoph Dann , Tor Lattimore , Emma Brunskill