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 20 of 267 for “"Sample Complexity"”.

  1. Refining the sample complexity of comparative learning

    … the statistical (and sometimes computational) complexity of machine learning tasks. Comparative learning is a recently introduced variation of the PAC framework that interpolates between the two standard extreme settings of realizable and agnostic PAC learning. In comparative learning the …

    york Repository record for Refining the sample complexity of comparative learning (opens in a new tab)

  2. General methods for analyzing machine learning sample complexity

    … second field is concerned with the computational complexity of learning once the training data have been selected. Since most existing algorithms use heuristics to deal with the problem of complexity, we are primarily concerned with the amount of training data that algorithms require.

    wm-mary Repository record for General methods for analyzing machine learning sample complexity (opens in a new tab)

  3. Sample complexity of robust learning against evasion attacks

    … the perspective of learning theory, considering sample complexity.</p> <p>We start with two negative results. We show that no non-trivial concept class can be robustly learned in the distribution-free setting against an adversary who can perturb just a single input bit. We then exhibit a …

    oxford Repository record for Sample complexity of robust learning against evasion attacks (opens in a new tab)

  4. SEQUENTIAL RANKING AND SELECTION PROCEDURES AND SAMPLE COMPLEXITY

    … In this thesis, we focus on three aspects on the sample com- plexity of the R&S problem. First, we develop a method for predicting the sample complexity. Second, we present Envelope Procedure (EP), a R&S procedure that delivers a probably approximately correct selection guarantee, and we provide a …

    cornell Repository record for SEQUENTIAL RANKING AND SELECTION PROCEDURES AND SAMPLE COMPLEXITY (opens in a new tab)

  5. Model-Free Robust Reinforcement Learning with Sample Complexity Analysis

    … methods offering convergence guarantees or sample complexities. This paper proposes a model-free DR-RL algorithm leveraging the Multi-level Monte Carlo (MLMC) technique to close such a gap. Our innovative approach integrates a threshold mechanism that ensures finite sample requirements for …

    buffalo Repository record for Model-Free Robust Reinforcement Learning with Sample Complexity Analysis (opens in a new tab)

  6. Sample-Complexity Optimality Under Local Differential Privacy and Related Models

    This work explores the sample complexity of estimation and learning tasks under local differential privacy (LDP), an especially strong approach to differential privacy which does not rely on any trusted party to guarantee privacy. We give a new characterization of the sample complexity of answering …

    toronto-retro Repository record for Sample-Complexity Optimality Under Local Differential Privacy and Related Models (opens in a new tab)

  7. Near-optimal sample complexity for noisy or 1-bit tensor completion

    … tensor in ℝ^{NxNx...N}, the best sampling complexity achieved is O(rN^{d/2}) which can be obtained by a tensor nuclear-norm minimization problem. This bound is significantly larger than O(rdN), the number of free variables in a rank-r tensor. In this thesis, we prove that when r=O(1), we …

    ubc Repository record for Near-optimal sample complexity for noisy or 1-bit tensor completion (opens in a new tab) Download PDF for Near-optimal sample complexity for noisy or 1-bit tensor completion (opens in a new tab)

  8. On the Sample Complexity of Privately Learning Gaussians and their Mixtures

    Multivariate Gaussians: We provide sample complexity upper bounds for semi-agnostically learning multivariate Gaussians under the constraint of approximate differential privacy. These are the first finite sample upper bounds for general Gaussians which do not impose restrictions on the parameters …

    mcmaster Repository record for On the Sample Complexity of Privately Learning Gaussians and their Mixtures (opens in a new tab)

  9. System identification for the bar model: Algorithms, consistency and sample complexity

    Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2024-05-01

    uiuc Repository record for System identification for the bar model: Algorithms, consistency and sample complexity (opens in a new tab)

  10. A Case Study on Sample Complexity, Topology, and Interpolation in Neural Networks

    The general heuristic for determining the sample size to use for training artificial neural networks on real world data sets is “more is better”. Similarly, the heuristic for selecting the number of neurons in the hidden layer of the neural network has also been that “more is better”. However, …

    hawaii Repository record for A Case Study on Sample Complexity, Topology, and Interpolation in Neural Networks (opens in a new tab)

  11. Sample complexity of Reinforcement Learning algorithms with a focus on policy space methods

    … Reinforcement Learning algorithms with finite sample complexity guarantees. The work is divided into two main parts. In the first, we investigate stochastic approximation across various domains to establish finite sample complexity bounds. We study two settings: federated stochastic …

    gatech Repository record for Sample complexity of Reinforcement Learning algorithms with a focus on policy space methods (opens in a new tab)

  12. Sample Complexity of Incremental Policy Gradient Methods for Solving Multi-Task Reinforcement Learning

    We consider a multi-task learning problem, where an agent is presented a number of N reinforcement learning tasks. To solve this problem, we are interested in studying the gradient approach, which iteratively updates an estimate of the optimal policy using the gradients of the value functions. The …

    vt Repository record for Sample Complexity of Incremental Policy Gradient Methods for Solving Multi-Task Reinforcement Learning (opens in a new tab)

  13. On the finite sample complexity of causal discovery and the value of domain expertise

    … of a CI oracle. In this thesis, we analyze the sample complexity of causal discovery algorithms without a CI oracle: given a certain level of confidence, how many data points are needed for a causal discovery algorithm to identify a causal structure? Furthermore, our methods allow us to quantify …

    uiuc Repository record for On the finite sample complexity of causal discovery and the value of domain expertise (opens in a new tab)

  14. Extending Structural Learning Paradigms for High-Dimensional Machine Learning and Analysis

    … of the input space, such that both sample complexity and computational complexity can limit real-world success. In this work, we review many of the latest structural learning approaches for dealing with sample complexity. We expand their use to generate new paradigms for combining …

    utk-theses Repository record for Extending Structural Learning Paradigms for High-Dimensional Machine Learning and Analysis (opens in a new tab)

  15. Fundamental Limitations of Semi-Supervised Learning

    … the potential benefits, as measured by the sample complexity of SSL. Our framework is utopian in the sense that a SSL algorithm trains on a labeled sample and an unlabeled distribution, as opposed to an unlabeled sample in the usual SSL model. Thus, any lower bound on the sample complexity …

    waterloo Repository record for Fundamental Limitations of Semi-Supervised Learning (opens in a new tab)

Page 1 of 14