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 5 of 5 for “"minimax optimality"”.

  1. The Conditional Mode Estimator of Technical Efficiency: Theory and Application to NYC Public Schools

    … closed-form expressions, convergence, near-minimax optimality when interpreted using Lasso, and selection rules. The second chapter applies the true fixed effect stochastic frontier model (Greene, 2005a,b) to analyze the persistent and transient technical inefficiencies of 425 NYC public …

    syracuse-diss Repository record for The Conditional Mode Estimator of Technical Efficiency: Theory and Application to NYC Public Schools (opens in a new tab)

  2. The Conditional Mode Estimator Of Technical Efficiency: Theory And Application To Nyc Public Schools

    … closed-form expressions, convergence, near-minimax optimality when interpreted using Lasso, and selection rules. The second chapter applies the true fixed effect stochastic frontier model (Greene, 2005a,b) to analyze the persistent and transient technical inefficiencies of 425 NYC public …

    syracuse-diss Repository record for The Conditional Mode Estimator Of Technical Efficiency: Theory And Application To Nyc Public Schools (opens in a new tab)

  3. Online Reinforcement Learning in Factored Markov Decision Processes and Unknown Markov Games

    … the bandit literature has been shown to achieve minimax optimality for Markov decision processes (MDPs) in the tabular case. However, such a model may be too general for some problems where certain structures allow for much more efficient learning. In the first part of this thesis, we consider …

    mit Repository record for Online Reinforcement Learning in Factored Markov Decision Processes and Unknown Markov Games (opens in a new tab)

  4. Optimal estimation in high-dimensional and nonparametric models

    Minimax optimality is a key property of an estimation procedure in statistical modelling. This thesis looks at several problems in high-dimensional and nonparametric statistics and proposes novel estimation procedures. It then provides statistical guarantees on the performance of these methods and …

    cambridge Repository record for Optimal estimation in high-dimensional and nonparametric models (opens in a new tab)

  5. Direct and inverse problems in machine learning

    … Parallelizing spectral algorithms also leads to minimax optimal rates of convergence provided the number of machines is chosen appropriately. We emphasize that so far all estimators depend on the assumed a-priori smoothness of the target function and on the eigenvalue decay of the kernel …

    potsdam-diss Repository record for Direct and inverse problems in machine learning (opens in a new tab)