Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 10 of 10 for “"finite-sample analysis"”.

  1. Finite-sample analysis for distributed and neural reinforcement learning

    This dissertation develops a modular finite-sample theory for reinforcement learning under two realities of modern practice that challenge classical analysis: nonlinear function approximation and trajectory-based, temporally dependent data, including distributed and continuing settings. The central …

    bu Repository record for Finite-sample analysis for distributed and neural reinforcement learning (opens in a new tab)

  2. A Unified Lyapunov Framework for Finite-Sample Analysis of Reinforcement Learning Algorithms

    … learning algorithms and establishing their finite-sample guarantees. Specifically, we aim at answering the following question: suppose we carry out some reinforcement learning algorithm with finite amount of samples (or with finite number of iterations), then what can we say about the …

    gatech Repository record for A Unified Lyapunov Framework for Finite-Sample Analysis of Reinforcement Learning Algorithms (opens in a new tab)

  3. Advances in Proximal Inference for Continuous Exposures, Estimation of Ill-Posed Regression, and Non-Inferiority Assessment in Active-Controlled Trials

    … misspecifications. Chapter 3, motivated by the analysis of immune correlates of protection in COVID-19 vaccine trials, extends the proximal inference framework to identify and estimate the mean outcome under modified treatment policies, enabling causal analysis of continuous exposures in the …

    washington Repository record for Advances in Proximal Inference for Continuous Exposures, Estimation of Ill-Posed Regression, and Non-Inferiority Assessment in Active-Controlled Trials (opens in a new tab)

  4. Reinforcement Learning with Finite Time and Sample Guarantees

    … demonstrations and human feedback, establishing finite-sample guarantees for reward estimation. I first present a single-loop regularized Q-learning algorithm for minimizing the projected Bellman error with finite time convergence guarantees in the case of linear function approximation. The …

    tamu Repository record for Reinforcement Learning with Finite Time and Sample Guarantees (opens in a new tab)

  5. Temporal abstraction and generalisation in reinforcement learning

    … of state abstraction, temporal abstraction, and finite-data generalisation performance for reinforcement learning algorithms. To focus on data abstraction, we explore an imitation learning setting. We provide a novel algorithm for completely offline imitation learning, as well as an empirical …

    oxford Repository record for Temporal abstraction and generalisation in reinforcement learning (opens in a new tab)

  6. Folded Variance Estimators for Stationary Time Series

    This thesis is concerned with simulation output analysis. In particular, we are interested in estimating the variance parameter of a steady-state output process. The estimation of the variance parameter has immediate applications in problems involving (i) the precision of the sample mean as a point …

    gatech Repository record for Folded Variance Estimators for Stationary Time Series (opens in a new tab)

  7. Towards Foundation Models for Text-Rich Multimodal Tabular Data

    … guarantee on the upper bound on error using finite-sample analysis. Empirically, we demonstrated improvements on both the standard benchmark for multi-armed bandits and a newly proposed benchmark for realistic news recommendation tasks. On the question of input representations, we started …

    waterloo Repository record for Towards Foundation Models for Text-Rich Multimodal Tabular Data (opens in a new tab)

  8. Three Essays in Time Series Econometric Analysis

    … Consistent (HAC) estimators with improved finite sample properties. This is achieved by exploiting existing transformations from the related Heteroskedasticity Consistent estimator literature. Monte Carlo simulation results provide strong evidence in favour of using these alternative …

    unsw Repository record for Three Essays in Time Series Econometric Analysis (opens in a new tab)

  9. On the information theory of clustering, registration, and blockchains

    Progress in data science depends on the collection and storage of large volumes of reliable data, efficient and consistent inference based on this data, and trusting such computations made by untrusted peers. Information theory provides the means to analyze statistical inference algorithms, …

    uiuc Repository record for On the information theory of clustering, registration, and blockchains (opens in a new tab)

  10. Latent Structure in Linear Prediction and Corpora Comparison

    This work first studies the finite-sample properties of the risk of the minimum-norm interpolating predictor in high-dimensional regression models. If the effective rank of the covariance matrix of the p regression features is much larger than the sample size n, we show that the min-norm …

    cornell Repository record for Latent Structure in Linear Prediction and Corpora Comparison (opens in a new tab)