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 38 for “"Risk minimization"”.

  1. Portfolio risk minimization under departures from normality

    … and statistically sound approaches to portfolio risk minimization. When returns exhibit asymmetry, we propose using a quantile-based measure of risk which we call shortfall. Shortfall is related to Value-at-Risk and Conditional Value-at-Risk, and can be tuned to capture tail risk. We formulate …

    mit Repository record for Portfolio risk minimization under departures from normality (opens in a new tab)

  2. A Patient Risk Minimization Model for Post-Disaster Medical Delivery Using Unmanned Aircraft Systems

    … existing vehicle routing models by using patient risk as the primary minimization variable.</p> <p>The vehicle routing problem is a subset of operational research that utilizes mathematical models to identify the most efficient route between sets of points. Routing studies using unmanned aircraft …

    embry-riddle Repository record for A Patient Risk Minimization Model for Post-Disaster Medical Delivery Using Unmanned Aircraft Systems (opens in a new tab)

  3. Applications of empirical processes in learning theory : algorithmic stability and generalization bounds

    … to be equivalent to consistency of empirical risk minimization. The second part of the thesis derives tight performance guarantees for greedy error minimization methods - a family of computationally tractable algorithms. In particular, we derive risk bounds for a greedy mixture density …

    mit Repository record for Applications of empirical processes in learning theory : algorithmic stability and generalization bounds (opens in a new tab)

  4. Learning inside the prediction function

    … laws. Finally, we propose Functional risk minimization(FRM), an alternative framework to the standard Empirical risk minimization(ERM) setting where loss functions act in function space rather than output space. We show how we can make learning in this new framework efficient and can …

    mit Repository record for Learning inside the prediction function (opens in a new tab)

  5. The Use of Probabilistic Risk Functions and Linear Penalty Functions for Hospital Evacuation Planning

    … transportation plans were proposed: the minimization of the overall risk and the minimization of the evacuation duration. The resulting evacuation plans differ in terms of overall risk and duration, but also in the evacuation order of patients with different characteristics, the filling …

    vt Repository record for The Use of Probabilistic Risk Functions and Linear Penalty Functions for Hospital Evacuation Planning (opens in a new tab)

  6. Forecasting the Next Winning Stock: A Comparative Analysis of Machine Learning Models

    … analysis of model performance, as well as in risk minimization in investments, enabling portfolio diversification thanks to the Transformer model.

    york Repository record for Forecasting the Next Winning Stock: A Comparative Analysis of Machine Learning Models (opens in a new tab)

  7. Option Pricing in Non-Competitive Markets

    … motion model is studied. In Chapter 3, local risk minimization method is used to pricing European options with liquidity cost in a jump-diffusion model. In chapter 4, utility indifference pricing method is applied to pricing European options for large investors.

    york Repository record for Option Pricing in Non-Competitive Markets (opens in a new tab)

  8. Large-scale optimization Methods for data-science applications

    … lower bound (like what happened in empirical risk minimization in machine learning). We introduce a new functional measure called the growth constant for the convex objective function, that measures how quickly the level sets grow relative to the function value, and that plays a fundamental …

    mit Repository record for Large-scale optimization Methods for data-science applications (opens in a new tab)

  9. TOWARDS RELIABLE AI UNDER DISTRIBUTION SHIFTS: A DATA-CENTRIC PERSPECTIVE

    … show that when training with empirical risk minimization, label noise exacerbates the effect of spurious correlations in the training data. Second, we introduce two data-centric strategies to diagnose and improve quality of data. To detect mislabeled data, we propose an efficient …

    nus Repository record for TOWARDS RELIABLE AI UNDER DISTRIBUTION SHIFTS: A DATA-CENTRIC PERSPECTIVE (opens in a new tab)

  10. Empirical Bayes via ERM and Rademacher complexities: the Poisson model

    … optimal for minimizing the regret (excess risk over the Bayesian oracle that knows the prior) have several shortcomings. For example, the classical Robbins estimator does not retain the monotonicity property of the Bayes estimator and performs poorly under moderate sample size. Estimators …

    mit Repository record for Empirical Bayes via ERM and Rademacher complexities: the Poisson model (opens in a new tab)

  11. Phase Retrieval Under a Generative Prior

    … neural network. By formulating an empirical risk minimization problem and directly optimizing over the domain of the generator, we show that the objective’s energy landscape exhibits favorable global geometry for gradient descent with information theoretically optimal sample complexity. Based …

    rice Repository record for Phase Retrieval Under a Generative Prior (opens in a new tab)

  12. Data-driven robust solution schemes for sequential decision making

    … approximation—also referred to as empirical risk minimization in the machine learning literature—often suffer from poor out-of-sample performance when data is limited. To address this issue, the dissertation proposes a data-efficient alternative to sample average approximation for multistage …

    uiuc Repository record for Data-driven robust solution schemes for sequential decision making (opens in a new tab)

  13. Revisiting Generalization for Deep Learning: PAC-Bayes, Flat Minima, and Generative Models

    … nonvacuous generalization bounds and structural risk minimization, we arrive at an algorithm that trades-off accuracy and generalization guarantees. We also study generalization in the context of unsupervised learning. We propose to use a two sample test statistic for training neural network …

    cambridge Repository record for Revisiting Generalization for Deep Learning: PAC-Bayes, Flat Minima, and Generative Models (opens in a new tab)

  14. Below P vs NP : fine-grained hardness for big data problems

    … problems. ** Lower bounds for empirical risk minimization such as kernel support vectors machines and other kernel machine learning problems. All of these problems have polynomial time algorithms, but despite extensive amount of research, no near-linear time algorithms have been found. We …

    mit Repository record for Below P vs NP : fine-grained hardness for big data problems (opens in a new tab)

  15. Topics in non-convex optimization and learning

    … practices in deep learning, namely empirical risk minimization (ERM) and normalization. Specifically, I show (1) training on convex combinations of samples improves model robustness and generalization, and (2) a good initialization is sufficient for training deep residual networks without …

    mit Repository record for Topics in non-convex optimization and learning (opens in a new tab)

  16. High-Dimensional Inference with Heterogeneous Data

    … We then propose a sample-weighted empirical risk minimization method for inferring change points in GLMs which we call `Weighted ERM`. We prove that our previous AMP algorithm can be tailored to mimic `Weighted ERM`, allowing us to obtain precise guarantees on the performance of `Weighted …

    cambridge Repository record for High-Dimensional Inference with Heterogeneous Data (opens in a new tab)

  17. Gradient Subgroup Scanning for Distributionally and Outlier Robust Models

    … machine learning methods such as empirical risk minimization (ERM) frequently encounter the issue of achieving high accuracy on average but low accuracy on certain subgroups, especially when there exist spurious correlations between the input data and label. Previous approaches for reducing …

    mit Repository record for Gradient Subgroup Scanning for Distributionally and Outlier Robust Models (opens in a new tab)

  18. Robustness and generalization guarantees for statistical learning of generative models

    … but not identical. We devise an empirical risk minimization algorithm based on local worst-case risks, and provide generalization and excess risk guarantees of the learned hypothesis, that are robust to drifts in generative models. Second, we consider the learning of coding schemes, where …

    uiuc Repository record for Robustness and generalization guarantees for statistical learning of generative models (opens in a new tab)

  19. Decision making in the presence of complex dynamics from limited, batch data

    … policy class using the principle of structural risk minimization, for which the resulting algorithm has provable performance bounds with weak assumptions on the true world's dynamics.

    mit Repository record for Decision making in the presence of complex dynamics from limited, batch data (opens in a new tab)

Page 1 of 2