Focal loss improves classification but not class-posterior probability estimation.
problem Improving class-posterior probability estimation from focal loss.
method Proved classification-calibration and derived a transformation to recover true class-posterior probabilities.
result A transformation of the confidence score from focal loss minimization allows recovery of true class-posterior probabilities.
Study minimizes large losses in financial portfolios.
problem Minimizing large losses in financial portfolios.
method Generalizes quantile hedging approach for discrete and continuous time models.
result Generalized approach for minimizing large losses.
Study ruin probabilities in risk processes on stochastic networks.
problem Ruin probabilities in risk processes on stochastic networks.
method Classification of agents by types, Poisson process for loss propagation, explicit ruin probabilities for infinite network size.
result Explicit ruin probabilities for agents of any type in infinite network size.
Paper optimizes combining expert predictions using CRPS loss.
problem Optimizing combining expert predictions in online learning.
method Combines probabilistic forecasts using CRPS loss function in the prediction with expert advice framework.
result Time-independent upper bound for the regret of the Vovk's aggregating algorithm using CRPS as a loss function is obtained.
Factor copula models simplify joint default probabilities and loss distributions.
problem Modeling joint default probabilities and loss distributions for high-dimensional portfolios.
method Factor copula models that nest standard models and efficiently compute loss distributions.
result Exact and efficient computation of loss distributions for contingent claims.
A new method learns proper multiclass losses and probabilities.
problem Learning proper multiclass losses for complex classification tasks.
method Extends monotonicity to multiclass problems using convex functions.
result Consistently outperforms natural multiclass baseline on up to 1,000 class datasets.
Paper analyzes proper losses and their performance in machine learning tasks.
problem Understanding the performance of estimators and forecasters in machine learning tasks.
method Analyzes surrogate regret and convergence rates for strictly proper losses.
result Strongly proper losses achieve the optimal convergence rate.
We study cross-country GDP losses due to financial crises in terms of frequency (number of loss events per period) and severity (loss per occurrence). We perform the Loss Distribution Approach (LDA) to estimate a multi-country aggregate GDP loss probability density function and the percentiles associated to extreme eve…
Study on loss probabilities for diversified financial systems with light-tailed claims.
problem Analyzing risks in systems of diversified financial agents with light-tailed claims.
method Assuming exponentially distributed claims, we derive conditional loss distributions and compare with heavy-tailed claims.
result Conditional loss distributions reveal different risk profiles for agents and systems compared to heavy-tailed claims.
Interactive book integrates probability models with big data analytics.
problem Lack of integration between classical loss data models and modern analytic tools.
method Combines classical loss data models with modern analytic tools and big data.
result Promotes deeper learning through interactive elements and multiple language support.
New algorithms find conditions and linear rules with high probability and loss.
problem Finding conditions and rules with high probability and loss in conditional sparse regression.
method Efficient algorithms for identifying conditions and rules with optimal probability and loss.
result Achieved algorithms that nearly match the probability of the ideal condition and improve the approximation to the target loss.
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.
This research improves deep neural network calibration using a new loss function.
problem Improving probability calibration in deep neural networks.
method Introduces Focal Calibration Loss (FCL) to minimize Euclidean norm and penalize calibration error.
result FCL achieves state-of-the-art performance in both calibration and accuracy metrics.
New method estimates grouping loss in neural networks to improve confidence scores.
problem Improving confidence scores in neural networks to reflect true posterior probabilities.
method Proposed an estimator to approximate the grouping loss.
result Modern neural networks exhibit grouping loss, especially in distribution shifts.
New loss function reduces outage probability in ML-assisted resource allocation.
problem Minimizing outage probability in ML-assisted resource allocation systems.
method Developed a novel loss function and trained an ML model to address the outage probability challenge.
result Exact and asymptotic expressions for the system's outage probability were established.
In many real-world applications of machine learning classifiers, it is essential to predict the probability of an example belonging to a particular class. This paper proposes a simple technique for predicting probabilities based on optimizing a ranking loss, followed by isotonic regression. This semi-parametric techniq…
Boosted decision trees typically yield good accuracy, precision, and ROC area. However, because the outputs from boosting are not well calibrated posterior probabilities, boosting yields poor squared error and cross-entropy. We empirically demonstrate why AdaBoost predicts distorted probabilities and examine three cali…
New bounds on minimax regret for sequential probability assignment using logarithmic loss.
problem Minimizing regret in sequential probability assignment against arbitrary experts.
method Using self-concordance property of logarithmic loss to derive tight bounds.
result Tight bounds on minimax regret for various expert classes.
Study on estimating class probabilities using empirical risk minimization.
problem Estimating class probabilities within binary classification.
method Empirical risk minimization (ERM) for class probability estimation.
result The estimator converges to true class probabilities under certain conditions.
Sharp bounds on crash probability and loss from option quotes.
problem Uncertainty in risk-neutral crash probability and conditional loss from option data.
method Adaptive hull algorithm to recover probability-loss polygon; linear system for identified set.
result Complete put wing lowers median transformed area by 5.4-18.2% relative to local strikes, filling 63.40% of benchmark.
We propose a generalization of the classical notion of the V@Rλ that takes into account not only the probability of the losses, but the balance between such probability and the amount of the loss. This is obtained by defining a new class of law invariant risk measures based on an appropriate family of acceptance set…
The authors examine the concept of probability of default for asset-backed loans. In contrast to unsecured loans it is shown that probability of default can be defined as either a measure of the likelihood of the borrower failing to make required payments, or as the likelihood of an insufficiency of collateral value on…
SplineCalib calibrates probabilities using splines for better performance.
problem Calibrating probabilities for better accuracy and log-loss.
method Uses smoothing splines to determine a calibration function.
result Significant improvements to log-loss and accuracy on various problems.
TripletGAN uses triplet loss to improve generative models, preventing mode collapse.
problem Mode collapse in generative models.
method Substituting discriminator's classification loss with triplet loss.
result TripletGAN helps prevent mode collapse and converges to the given distribution.
Study of focal-entropy for class-imbalanced classification.
problem Understanding the focal-loss in class-imbalanced settings.
method Distributional viewpoint and information-theoretic analysis of focal-entropy.
result Focal-entropy minimizer exists and departs from data distribution.
Evidential Softmax preserves multimodality in sparse probability distributions for generative models.
problem Sparse probability distributions in deep generative models make exact marginalization computationally intractable.
method Introduce ev-softmax, a sparse normalization function that preserves multimodality and can be trained with probabilistic loss functions.
result ev-softmax outperforms existing techniques in distributional accuracy and dimensionality reduction.
A new loss function for set reconstruction without order consideration.
problem Reconstructing sets of elements without considering their order.
method Set Cross Entropy, a permutation-invariant loss function.
result Natural information-theoretic interpretation and successful evaluations in tasks.
Paper develops proper, lower-bounded losses for weakly supervised classification.
problem Weakly supervised classification with corrupted labels.
method Representation theorem for proper losses, derived condition for lower-boundedness, generalized logit squeezing.
result Proper and lower-bounded losses for weak-label learning.
The paper improves PAC-Bayes bounds for losses with finite moments.
problem Bounding generalization for losses with heavy tails and finite moments.
method Truncation method and PAC-Bayes bounds for unbounded losses with heavy tails and bounded variance.
result Bounds interpolate between slow and fast rates depending on the moment.
Study tackles criterion collapse in learning criteria, showing conditions for loss minimization.
problem Criterion collapse in optimization, focusing on error probability minimizers.
method Analyzes various learning criteria, including DRO, OCE risks, and non-monotonic criteria.
result Non-monotonic criteria can avoid collapse, while monotonic ones cannot.
Fewer degrees of freedom can train deep networks, showing a sharp phase transition.
problem Training deep networks with fewer degrees of freedom than parameters.
method Examined success probability of hitting training loss sub-level sets within random subspaces.
result Threshold training dimension increases as desired final loss decreases.
The MoN loss fails to accurately represent ground truth probability density functions in probabilistic trajectory prediction.
problem Improving the diversity of probabilistic trajectory predictions in autonomous driving and robot planning.
method Proof and validation of the MoN loss's inaccuracy and proposed solutions to correct it.
result The MoN loss approximates the square root of the ground truth probability density function, not the function itself.
Loss minimisation fails to capture epistemic uncertainty in second-order predictors.
problem Capturing epistemic uncertainty in machine learning models.
method Analysis of a second-order learner approach using loss minimisation.
result Loss minimisation does not faithfully represent epistemic uncertainty in second-order predictors.
This paper examines how different decoding algorithms for LLMs align with various goals.
problem Consistency of decoding algorithms with different goals in LLMs.
method Analysis of greedy, lookahead, random sampling, and temperature-scaled random sampling algorithms.
result Random sampling is consistent with the true probability distribution, but other goals require optimal algorithms for specific probability distributions.
Label smoothing improves model robustness against misspecification.
problem Improving model robustness against model misspecification.
method Introducing modified label smoothing (MLSLR) that maintains consistent probability estimation while modifying the loss function.
result MLSLR exhibits higher robustness against model misspecification than conventional label smoothing.
This manuscript provides optimization guarantees, generalization bounds, and statistical consistency results for AdaBoost variants which replace the exponential loss with the logistic and similar losses (specifically, twice differentiable convex losses which are Lipschitz and tend to zero on one side). The heart of the…
Proposes unimodal probability distributions for better ordinal classification.
problem Undesired properties of cross-entropy loss distributions for ordinal classification.
method Uses Poisson and binomial distributions to constrain discrete ordinal probability distributions to be unimodal.
result Obtains promising results on deep learning ordinal image datasets.
While defaults are rare events, losses can be substantial even for credit portfolios with a large number of contracts. Therefore, not only a good evaluation of the probability of default is crucial, but also the severity of losses needs to be estimated. The recovery rate is often modeled independently with regard to th…
We consider composite loss functions for multiclass prediction comprising a proper (i.e., Fisher-consistent) loss over probability distributions and an inverse link function. We establish conditions for their (strong) convexity and explore the implications. We also show how the separation of concerns afforded by using …
Study examines how insurance affects households prone to proportional losses, especially those near poverty.
problem Impact of insurance on households susceptible to proportional losses, focusing on poverty traps.
method Modelled proportional capital losses with insurance, derived closed formulae and non-local differential equations.
result New formulae and methods to calculate trapping probability, constraints on parameters to prevent certainty of trapping.
Methodology measures financial impacts using existing credit loss infrastructure.
problem Measuring the impact of financial scenarios on expected credit losses.
method Captures scenario effects through changes in default probabilities; uses existing provisioning infrastructure.
result Methodology validated through standardized climate scenario exercise in Canada and Quebec.
Study shows squared loss is robust for binary classification with noisy features.
problem Learning binary classifiers with noisy features.
method Sy-De and Asy-In attribute noise models, analyzing l0−1 and lsq losses. result Squared loss is robust in Sy-De model but not in Asy-In model.
New algorithms and guarantees for multiple-source adaptation.
problem Improving model performance on target mixtures from multiple sources.
method Normalized solutions with theoretical guarantees, algorithms for distribution-weighted combination.
result Our algorithm outperforms competing approaches by producing a robust model.
Study minimax rates for density estimation under Huber contamination and Besov IPM losses.
problem Minimax convergence rates of nonparametric density estimation under Huber contamination model with outliers.
method Re-scaled thresholding wavelet series estimator and GAN architectures.
result Achieves minimax optimal convergence rates under Besov IPM losses.
Paper improves PAC-Bayes bounds for various loss types.
problem Improving PAC-Bayes bounds for different types of losses.
method Introducing new high-probability PAC-Bayes bounds for bounded and general tail behaviors losses, and extending to anytime-valid bounds.
result New fast-rate and mixed-rate bounds for losses with bounded ranges, and parameter-free bounds for losses with general tail behaviors.
Separable losses are inconsistent for structured prediction models.
problem Inconsistency of separable losses in structured prediction models.
method Analysis of separable negative log-likelihood losses for structured prediction.
result Separable losses are not Bayes consistent and may not predict the most probable structure.
Maps sets to probability distributions to minimize information loss.
problem Learning to map sets to probability distributions to preserve information.
method Relates set operations to probability distribution interpolations and demonstrates a preliminary solution.
result Experimental results show the effectiveness of the set embedding approach.
Paper finds robust Λ-quantiles equal to extremal distributions.
problem Investigating robust models for Λ-quantiles with partial loss information. method Extending classical quantiles using Λ-quantiles and applying results from robust quantiles. result Robust Λ-quantiles equal to Λ-quantiles of extremal distributions.