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 39 for “"Convergence guarantees"”.

  1. Parameter estimation in HMMs with guaranteed convergence

    … widely used in practice, the theoretical guarantees associated with EM are quite weak. We study the setting of a hidden Markov model (HMM) with two hidden states, where the (symmetric) transition matrix [mu] is unknown and observations are Gaussian with known covariance and unknown mean …

    mit Repository record for Parameter estimation in HMMs with guaranteed convergence (opens in a new tab)

  2. Proximal Gradient Algorithms for Gaussian Variational Inference:Optimization in the Bures–Wasserstein Space

    … proposed algorithm, we obtain state-of-the-art convergence guarantees when π is log-smooth and log-concave, as well as the first convergence guarantees to first-order stationary solutions when π is only log-smooth. Additionally, in the setting where the potential admits a representation as the …

    mit Repository record for Proximal Gradient Algorithms for Gaussian Variational Inference:Optimization in the Bures–Wasserstein Space (opens in a new tab)

  3. Reinforcement learning for multi-agent and robust control systems

    … for these settings, supported by theoretical convergence guarantees. In setting i, a team of collaborative MARL agents is connected via a communication network, without the coordination of any central controller. With only neighbor-to-neighbor communications, we introduce decentralized …

    uiuc Repository record for Reinforcement learning for multi-agent and robust control systems (opens in a new tab)

  4. Optimization Methods for Machine Learning under Structural Constraints

    … and active set methods, and derive novel linear convergence guarantees for our proposed algorithms. Empirically, our framework can approximately solve instances with n=100,000 and d=10 within minutes. In the second chapter, we develop a new computational framework for computing log-concave …

    mit Repository record for Optimization Methods for Machine Learning under Structural Constraints (opens in a new tab)

  5. Learning to teach and meta-learning for sample-efficient multiagent reinforcement learning

    … dimensionality of the problems, and the lack of convergence guarantees. As a result, many experiences are often required to learn effective multiagent policies. This thesis introduces two frameworks to reduce the sample complexity in MARL. The first framework presented in this thesis provides a …

    mit Repository record for Learning to teach and meta-learning for sample-efficient multiagent reinforcement learning (opens in a new tab)

  6. Algorithms for Gibbs states of quantum many-body systems

    … matter systems. For these algorithms, we provide convergence guarantees in various restricted settings. Such restrictions are necessary due to hardness results from Hamiltonian complexity. However, in part of this work, we take a step further, presenting algorithms without a priori convergence

    cambridge Repository record for Algorithms for Gibbs states of quantum many-body systems (opens in a new tab)

  7. Operational decisions and learning for multiproduct retail

    … via regression. We establish finite-sample convergence guarantees on the model parameters. The parameter convergence guarantees are then extended to out-of-sample performance guarantees in terms of revenue, in the form of a high-probability bound on the gap between the expected revenue of …

    mit Repository record for Operational decisions and learning for multiproduct retail (opens in a new tab)

  8. Upper and Lower Bounds for Sampling

    … of sampling as optimization [JKO98], and give convergence guarantees for them. We also obtain state-of-the-art convergence results for the popular Metopolis-Adjusted Langevin Algorithm. On the lower bound side, we establish the query complexity for strongly log-concave sampling in all constant …

    mit Repository record for Upper and Lower Bounds for Sampling (opens in a new tab)

  9. Efficient Hierarchical Global Motion Planning for Autonomous Vehicles

    … non-trivial, including issues such as algorithm convergence, its correspondence to system controllability, optimality of solution, computational complexity, and dynamic environments. In response to these challenges, a hierarchical algorithm will be introduced that provides (a) decreased …

    uiuc Repository record for Efficient Hierarchical Global Motion Planning for Autonomous Vehicles (opens in a new tab)

  10. Multiple aspect ranking for opinion analysis

    … models, yet our training algorithm preserves the convergence guarantees of perceptron rankers. Our empirical results further confirm the strength of the model: the algorithm provides significant improvement over both individual rankers, a state-of-the-art joint ranking model, and ad-hoc methods …

    mit Repository record for Multiple aspect ranking for opinion analysis (opens in a new tab)

  11. High-order tuners for convex optimization : stability and accelerated learning

    … methods, with accelerated learning guarantees, have received a lot of attention due to their provable guarantees of fast learning in certain classes of problems and multiple algorithms have been derived. However, properties for these methods hold true only for constant regressors. …

    mit Repository record for High-order tuners for convex optimization : stability and accelerated learning (opens in a new tab)

  12. Understanding neural network sample complexity and interpretable convergence-guaranteed deep learning with polynomial regression

    … that existing approaches. It also offers more convergence guarantees during training. Finally, we empirically show that the widely-used Stochastic Gradient Descent algorithm makes the weights of the trained neural networks converge to the optimal polynomial regression weights.

    mit Repository record for Understanding neural network sample complexity and interpretable convergence-guaranteed deep learning with polynomial regression (opens in a new tab)

  13. Geometric numerical integration for optimisation

    … of the discrete gradient update equation, convergence rates, convergence of the iterates, and propose methods for solving the discrete gradient update equation with superior stability and convergence rates. Furthermore, we present results from numerical experiments which support the theory. …

    cambridge Repository record for Geometric numerical integration for optimisation (opens in a new tab)

  14. Multi-Player Zero-Sum Markov Games with Networked Separable Interactions

    … games, for zero-sum NMGs, and establish convergence guarantees to Markov stationary NE under a star-shaped network structure. Finally, in light of the hardness result, we focus on computing a Markov non-stationary NE and provide finite-iteration guarantees for a series of …

    mit Repository record for Multi-Player Zero-Sum Markov Games with Networked Separable Interactions (opens in a new tab)

  15. NEW PARADIGMS IN SOURCE CODING AND CHANNEL CODING

    … is the gold standard because it gives uniform convergence guarantees, even under adversarial conditions. In the minimax universal setting, the same $\Theta\left(\frac{\log n}{n} \right)$ rate redundancy result has been proven for lossless codes since 1981. However, minimax universal results for …

    cornell Repository record for NEW PARADIGMS IN SOURCE CODING AND CHANNEL CODING (opens in a new tab)

  16. Scalable Methodologies for Optimizing Over Probability Distributions

    … model by learning proximal operators with global convergence guarantees; and 3) solving mass-conserving differential equations of probability flows without temporal or spatial discretization by leveraging the self-consistency of the dynamical system.

    mit Repository record for Scalable Methodologies for Optimizing Over Probability Distributions (opens in a new tab)

  17. Aircraft System Identification Approach for Control Surface Fault Diagnosis

    … methods with exponential or finite-time convergence guarantees under a persistence of excitation condition, and an augmented-state extended Kalman filter. These methods were applied to flight data containing an artificially injected stuck left-aileron fault, implemented through a custom …

    vt Repository record for Aircraft System Identification Approach for Control Surface Fault Diagnosis (opens in a new tab)

  18. Reinforcement Learning-based Optimization of Multiple Access in Wireless Networks

    … of coordinated learning and focus on deriving convergence guarantees for learning while minimizing the complexity of coordination. We provide simulations that showcase how coordination can help achieve a fine balance, in terms of complexity and performance, between fully decentralized and …

    essex Repository record for Reinforcement Learning-based Optimization of Multiple Access in Wireless Networks (opens in a new tab)

  19. Contraction maps and applications to the analysis of iterative algorithms

    … Banach's fixed point theorem to establish the convergence of iterative methods when pairing it with carefully designed metrics. Our first result is a strong converse of Banach's theorem, showing that it is a universal analysis tool for establishing uniqueness of fixed points and convergence of …

    mit Repository record for Contraction maps and applications to the analysis of iterative algorithms (opens in a new tab)

Page 1 of 2