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 98 for “"Loss functions"”.

  1. Exploring Loss Functions in Machine Learning

    <p>The loss function plays a critical role in machine learning. It is fundamental in training, evaluating, and optimizing machine learning models, directly impacting their effectiveness and efficiency in solving specific tasks. We explore three new loss functions and their applications. Softmax …

    claremont Repository record for Exploring Loss Functions in Machine Learning (opens in a new tab)

  2. Robustness of Consistent Loss Functions for Multinomial Outcome Models

    … estimation, which uses the logarithmic loss function, is the default method used to estimate latent parameters consistently in multinomial outcome models. However, it is sensitive to even a tiny fraction of corruption in the training data. Alternatively, other loss functions in the …

    mit Repository record for Robustness of Consistent Loss Functions for Multinomial Outcome Models (opens in a new tab)

  3. Neural Network Supervision: Notes on Loss Functions, Labels and Confidence Estimation

    … update rules may replace the need for a loss function and its gradient. We introduce a parameter update rule that generalises the standard cross-entropy gradient, and allows directly controlling the relative effect of easy and hard examples on the training process. We show that the …

    passau-thes Repository record for Neural Network Supervision: Notes on Loss Functions, Labels and Confidence Estimation (opens in a new tab)

  4. Optimal versus naive diversification : do different loss functions improve portfolio choice?

    … different settings. In each setting, I vary the loss function used when estimating returns and covariances, length of the estimation window, and number of factors used in our estimation model. I find that when measuring performance by Sharpe ratio, choice of loss function strongly influences …

    mit Repository record for Optimal versus naive diversification : do different loss functions improve portfolio choice? (opens in a new tab)

  5. Asymmetric Loss Functions and Combination of Forecasts with Applications in Equity Premium Prediction

    … methods, called the Discount Asymmetric Square Loss Function (DASLF), the Discount Linex Loss Function (DLLF), the Discount Lin-Lin Loss Function (DLLLF) and the Discount General Entropy Loss Function (DGELF) are proposed to maximize forecast accuracy and boost the efficiency of forecasts …

    essex Repository record for Asymmetric Loss Functions and Combination of Forecasts with Applications in Equity Premium Prediction (opens in a new tab)

  6. Analysis of loss functions in XVAE-GAN: A novel two-view image generation network

    DSpace SAF Submission Ingestion Package generated from Vireo submission #14457 on 2020-02-28 at 17:35:35

    uiuc Repository record for Analysis of loss functions in XVAE-GAN: A novel two-view image generation network (opens in a new tab)

  7. Geometric aspects of uncertainty quantification in high-dimensional statistics

    … this is critically affected by the choice of loss functions. Thus the problem can be understood from a geometric perspective. Specifically, under the sparse regression model, we layout results for foundational choices of loss functions while adding to the field by introducing the reweighted …

    cambridge Repository record for Geometric aspects of uncertainty quantification in high-dimensional statistics (opens in a new tab)

  8. I-Con: A Unifying Framework for Representation Learning

    … there has been a proliferation of different loss functions to solve different classes of problems. We introduce a single information-theoretic equation that generalizes a large collection of modern loss functions in machine learning. In particular, we introduce a framework that shows that …

    mit Repository record for I-Con: A Unifying Framework for Representation Learning (opens in a new tab)

  9. Imbalanced learning using actuarial modified loss function in tree-based models

    … mass at zero and the heavy tail of insurance loss distribution poses the challenge to apply traditional methods directly to claim loss modeling. Via an illustrative simple dataset, this thesis first pinpoints the pitfall in the traditional tree-based algorithm’s splitting function. This thesis …

    uiuc Repository record for Imbalanced learning using actuarial modified loss function in tree-based models (opens in a new tab)

  10. Inference for the ratio of two exponential parameters using a Bayesian approach

    … better in terms of average interval lengths. Loss functions will also be used to derive Bayes estimates. The squared error loss and all-or-nothing loss functions will be compared with each other through a simulation study. The performance of each loss function will be compared by looking at …

    nwu-za Repository record for Inference for the ratio of two exponential parameters using a Bayesian approach (opens in a new tab)

  11. Program Synthesis over Noisy Data

    … as an optimization problem formulated over the loss of a candidate program over the noisy dataset and the complexity of the candidate program. I present a noisy program synthesis algorithm based on finite tree automaton. Results from an implemented system running this algorithm on problems from …

    mit Repository record for Program Synthesis over Noisy Data (opens in a new tab)

  12. On Semi-supervised Estimation of Distributions

    … We adopt the minimax framework with [notation] loss functions, and we show that the composition of uni-variate minimax estimators achieves minimax risk with the optimal first-order constant for 𝑝 ≥ 2, in the regime 𝑚 = 𝑜(𝑛).

    mit Repository record for On Semi-supervised Estimation of Distributions (opens in a new tab)

  13. Deep Learning For Microscopic Image Restoration

    … problem, two new combinations of frequency based loss functions were proposed for denoising low SNR images. The first loss function is the combination of frequency and pixel-wise based losses. The second combination combines frequency domain with feature-based losses. These new loss functions were …

    bielefeld Repository record for Deep Learning For Microscopic Image Restoration (opens in a new tab)

  14. Bayes Multiple Decision Functions: Theory, Computation and Application

    … for this problem is implemented with the overall loss function being a cost-weighted linear combination of Type I and Type II loss functions. The class of loss functions considered allows for the use of the false discovery rate (FDR), false nondiscovery rate (FNR), and missed discovery rate (MDR) …

    south-carolina Repository record for Bayes Multiple Decision Functions: Theory, Computation and Application (opens in a new tab)

  15. Elektronen-Energieverlustspektroskopie von quasi-eindimensionalen Kupraten und Vanadaten

    … cuprates and vanadates. Electron energy-loss spectroscopy in transmission was employed to measure the momentum-dependent loss function of Li2CuO2, CuGeO3, V2O5 and NaV2O5. The comparison between the experimental data and the results from bandstructure as well as cluster calculations …

    qucosa-diss

  16. Learning image super resolution from joint examples

    … both external and internal SR. We de ne the two loss functions using sparse coding and epitomic matching, respectively. A corresponding adaptive weight is constructed to balance their e ect according to the reconstruction errors. Various image results demonstrate the e ectiveness of the proposed …

    uiuc Repository record for Learning image super resolution from joint examples (opens in a new tab)

  17. Complete classes of two-stage estimation procedures for certain finite sample problems

    … which depends on the combined sample. The loss functions usually are linear combinations of loss due to terminal decision and loss due to sampling. They find the optimal second sample size as well as the optimal first sample size.

    uiuc Repository record for Complete classes of two-stage estimation procedures for certain finite sample problems (opens in a new tab)

  18. On Machine Learning Loss Landscapes

    Loss functions are pivotal to the training of every machine learning model. When evaluating the loss function over a large range of parameters, a loss landscape is obtained. In this thesis, loss landscapes for various classes of machine learning models are explored. Geometric properties of the loss …

    cambridge Repository record for On Machine Learning Loss Landscapes (opens in a new tab)

  19. Fast Adaptive Laws for Adaptive Control Under Stochastic Disturbances

    … gradient methods for the optimization of convex loss functions, and derive a new adaptive law designed for stable adaptive control. Second, we review the state of the literature on recursive least-squares adaptive laws - especially those with variable-direction forgetting factor - and we derive …

    mit Repository record for Fast Adaptive Laws for Adaptive Control Under Stochastic Disturbances (opens in a new tab)

Page 1 of 5