Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,341 papers · 148 categories

Trend · papers per month

3657311,0961,461 · Jun 202019922001200920182026
48 results for General loss functions

New loss functions based on f-divergences improve language model performance.

problem Improving multiclass classification and language modeling performance.
method Constructing new convex loss functions using f-divergences and deriving an operator for computation.
result The αα-divergence loss function with α=1.5α=1.5 performs well across various tasks.

Paper proposes a new ee-exponentiated transformation to make convex loss functions more robust to outliers.

problem Making convex loss functions robust to outliers in the presence of label noise.
method Introduces a novel ee-exponentiated transformation for loss functions and proves its effectiveness through theoretical and empirical analysis.
result The transformed loss function achieves tighter generalization error bounds and higher accuracy in noisy datasets.

This paper explores neural network loss landscapes and their effects on generalization.

problem Understanding the structure of neural network loss functions and their impact on generalization.
method Simple filter normalization and various visualization methods to explore loss landscape structure and network architecture effects.
result Visualizations reveal how network architecture and training parameters affect loss landscape curvature and minimizers.

Paper studies Fenchel-Young losses for classifier construction.

problem Creating effective loss functions for classifiers.
method Analyzes Fenchel-Young losses from generalized entropies, formulates conditions for separation margins and sparse support.
result Fenchel-Young losses can induce predictive distributions with separation margins and sparse support.

Generalizes robust loss functions for improved performance in various tasks.

problem Improving performance on tasks like registration and clustering.
method Introduces a continuous robustness parameter into loss functions, allowing them to be generalized.
result Improves performance on learning-based tasks like generative image synthesis and unsupervised depth estimation.

A new loss function for VAEs improves image quality and efficiency.

problem Training VAEs to generate realistic images requires a loss function that reflects human perception.
method Based on Watson's perceptual model, the loss function computes a weighted distance in frequency space, accounts for luminance and contrast masking, and is extended to color images.
result VAEs trained with the new loss function generated high-quality, less blurry images with fewer artifacts and less computational resources.

New bounds for general unbounded loss functions, optimizing for various estimators.

problem Excess risk bounds for general unbounded loss functions, including log loss and squared loss.
method Optimized bounds for ηη-generalized Bayesian, MDL, and empirical risk minimization estimators, using vv-GRIP and witness conditions.
result Achieves ildeO(1/n) ilde{O}(1/n) rates for certain loss functions under favorable vv and small model complexity.

Study risk bounds for distributed ERM with general loss functions and hypothesis spaces.

problem Limited theoretical analysis for distributed ERM with general loss functions and hypothesis spaces.
method Derive tight risk bounds under assumptions on hypothesis space and loss function.
result Developed more general risk bound for distributed ERM without strong convexity restriction.

Paper introduces a new robust loss function for RL.

problem Heuristic selection of threshold parameters in quantile Huber loss.
method Derived from Wasserstein distance, captures noise in quantile values.
result Enhances robustness against outliers and enables parameter adjustment.

A meta-learning method learns adaptive robust loss functions for noisy labels.

problem Handling robust learning with noisy labels and optimizing hyperparameters.
method Adaptive learning of robust loss hyperparameters through mutual improvement with network parameters.
result Generalized and effective robust loss functions with good generalization capability.

Paper improves stability analysis of SGD for various loss functions and data distributions.

problem Improving stability analysis of SGD for non-convex loss functions and data distributions.
method Analyzes stability of SGD for convex and non-convex loss functions, and improves data-dependent bounds.
result Improved stability bounds for non-convex loss functions and convex regularized loss functions.

Tilting loss functions improves machine learning performance.

problem Improving machine learning models, especially in under- and over-parameterized networks.
method Using evolving loss functions that emphasize different classes cyclically.
result Dynamical loss functions lead to better generalization and stability in training.

Logitron combines Perceptron and logistic loss for improved classification.

problem Non-convex and non-smooth zero-one loss function in classification models.
method Introduces a Perceptron-augmented convex classification framework with an extended logistic loss function.
result Hinge-Logitron outperforms logistic regression and SVM in classification accuracy.

Proposes new loss functions for GANs to improve estimation accuracy and robustness.

problem Improving the training of GANs to achieve more accurate and robust models.
method Introduces Hellinger-type loss functions and analyzes their statistical properties.
result Demonstrates improved estimation accuracy and robustness of the proposed loss functions.

GANs can generate realistic data without minimizing a divergence, contrary to current theory.

problem Current theory suggests GANs minimize a divergence to generate realistic data.
method Discussed various loss functions for G, showing they are not divergences and do not have the same equilibrium.
result GANs can use a wide range of loss functions, not just divergences, to generate realistic data.

SoftAdapt dynamically adjusts loss weights for multi-part functions.

problem Slow convergence and poor weight selection for multi-part loss functions.
method SoftAdapt dynamically changes weights based on live performance statistics.
result Improved convergence and better weight selection for multi-part loss functions.

A new loss function α\alpha-loss improves classification robustness and calibration.

problem Improving classification robustness and calibration in machine learning.
method Introduces a tunable loss function α\alpha-loss, parameterized by α\alpha, and analyzes its theoretical and practical properties.
result The α\alpha-loss function can improve model robustness to label flips and sensitivity to imbalanced classes.

Classification and regression tasks in overparameterized models show different generalization properties.

problem Comparing classification and regression in overparameterized models.
method Comparison of least-squares minimum-norm interpolation and hard-margin SVM using different loss functions.
result Interpolating solutions generalize well with 0-1 loss but not with square loss.

The paper sets lower bounds for adversarial robustness in multiclass classification.

problem Adversarial robustness in multiclass classification with arbitrary loss functions.
method Dual and barycentric reformulations for robust risk minimization.
result Sharp lower bounds for adversarial risks are computed efficiently.

This paper analyzes output activation functions for adversarial losses.

problem Understanding which output activation functions form a well-behaved adversarial loss.
method Variational divergence minimization and a comparative framework for adversarial losses.
result There is no single winning combination of output activation functions and regularization approaches across all settings.

Proposes a new loss function for deep neural networks.

problem Deep neural networks lack a direct method to discriminate between correct and competing classes.
method Introduces a discriminative loss function based on negative log likelihood ratio.
result Significantly outperforms cross-entropy loss on image classification tasks.

Theoretical analysis of cross-entropy loss functions and their robustness.

problem Guarantees for using cross-entropy as a surrogate loss function.
method Theoretical analysis of a broad family of loss functions, including cross-entropy.
result First HH-consistency bounds for comp-sum losses and smooth adversarial comp-sum losses.

Improved robustness in kernel-based regression via novel loss function and IRLS.

problem Noise sensitivity in kernel-based regression methods.
method Proposed s\ell_s-loss function and iteratively reweighted least squares (IRLS) optimization.
result Improved noise robustness in kernel-based regression methods.