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.
Locus scores predictions for risk, reducing large-loss events.
problem Deployment cost from inaccurate predictions, especially large losses.
method Distribution-free loss-scale reliability score using any predictive distribution.
result Reduces large-loss frequency compared to standard heuristics.
The paper predicts loss scaling across different datasets and compute scales.
problem Predicting loss scaling across different datasets and compute scales.
method Derive shifted power law relationships between train and test losses.
result Shifted power law relationships hold for various datasets and tasks, improving prediction accuracy.
A new framework learns differentiable structured losses from data.
problem Learning effective losses for complex structured prediction tasks.
method Contrastive learning to learn differentiable structured losses from output data.
result Achieves similar or better performance than kernel-based methods.
Proposes a new framework for better prediction models in optimization problems.
problem Complex challenges in prediction and optimization for real-world analytics.
method Smart 'Predict, then Optimize' (SPO) framework, SPO loss function, SPO+ loss function.
result SPO+ loss function leads to significant improvement in prediction models for optimization problems.
Novel convex surrogate for submodular losses with tractable computation.
problem Learning with non-modular losses for set prediction.
method Proposed Lovász hinge loss function for submodular losses.
result First tractable convex surrogates for submodular losses.
Flexible framework for bounding high-loss predictions using quantiles.
problem Need for rigorous guarantees in risk-sensitive applications.
method Order statistics of loss values, flexible quantile-based metrics.
result Ability to rigorously control loss quantiles on real-world datasets.
This paper improves risk bounds and calibration for smart predict-then-optimize method.
problem Improving risk bounds and calibration for smart predict-then-optimize method.
method Develops risk bounds and uniform calibration results for the SPO+ loss relative to the SPO loss.
result Empirical minimizer of the SPO+ loss achieves low excess true risk with high probability.
The study offers new theoretical insights into structured prediction with convex loss minimization.
problem The challenge of structured prediction with efficient convex surrogate loss minimization.
method Constructing a convex surrogate loss and proving tight bounds on the calibration function.
result Formalizes the intuition that some task losses make learning harder than others, and that 0-1 loss is ill-suited for general structured prediction.
Proposes ANN for more accurate path loss prediction in urban environments.
problem Inaccurate path loss prediction in complex urban environments.
method Artificial Neural Network (ANN) for multi-dimensional regression modeling of path loss.
result The proposed ANN model is more accurate and flexible than conventional linear models.
The paper introduces a method for multi-label classification that allows partial predictions.
problem Handling multi-label classification with the option to abstain from predictions.
method Formalized MLC with abstention as a generalized loss minimization problem.
result Initial results for Hamming loss, rank loss, and F-measure.
Decision trees improve decision-making by optimizing predictions of unknown parameters.
problem Optimizing decisions based on predicted unknown parameters.
method SPO Trees (SPOTs) for training decision trees under the SPO loss function.
result SPOTs provide higher quality decisions and significantly lower model complexity compared to other machine learning approaches.
Efficient surrogate losses and regularization methods for structured prediction.
problem Efficiency and performance in structured prediction with rich label structures.
method Development of bi-criteria surrogate losses and shared Frobenius norm for regularization.
result Improved efficiency and performance in inference and optimization for structured prediction.
This work provides bounds on the performance of prediction models in the predict-then-optimize framework.
problem Generalizing the performance of prediction models in the predict-then-optimize framework with the SPO loss function.
method Deriving generalization bounds using the Natarajan dimension and exploiting the strength property of the feasible region.
result Improved generalization bounds for the SPO loss function, scaling logarithmically in the number of extreme points and linearly in the decision dimension.
Machine learning models accurately predict maize yield but less so for nitrate loss.
problem Predicting maize yield and nitrate loss for decision-making.
method Evaluation of five machine learning algorithms as meta-models for a cropping systems simulator.
result Random forests most accurately predicted maize yield and nitrate loss.
Paper introduces Fenchel-Young losses for supervised learning tasks.
problem Choosing the right loss function for supervised learning tasks.
method Introduces Fenchel-Young losses as a generic way to construct convex loss functions.
result Fenchel-Young losses unify and create new loss functions.
Paper establishes a formula linking model performance to insurance loss ratio.
problem Improving model performance does not always lead to proportional improvements in loss ratio.
method Derives a closed-form formula connecting Pearson correlation to expected loss ratio.
result Model improvements have diminishing marginal returns in reducing loss ratio.
Paper analyzes trade-offs in top-k classification accuracies and proposes a new loss function.
problem CE loss does not always optimize top-k prediction, especially with complex data.
method Introduces a novel top-k transition loss to improve top-k accuracy.
result Our loss function improves top-k accuracy, especially for k > 10.
The paper extends mixability theory to function-valued forecasts, proving various loss functions are mixable.
problem Efficient aggregation of functional and probabilistic forecasts in online prediction games.
method Adapting mixable and exponentially concave loss functions to function-valued forecasts.
result Various loss functions used for probabilistic forecasting are mixable (exp-concave).
Enhances ENet's prediction accuracy while maintaining uncertainty estimation.
problem Gradient shrinkage problem in ENet's loss function.
method Proposes a multi-task learning framework with a modified MSE loss function.
result Improves ENet's prediction accuracy without losing uncertainty estimation.
The paper explores conditions for predicting optimization performance.
problem Lack of formal theoretical guarantees linking prediction and optimization performance.
method Exploring conditions for asymptotic convergence and exact quantification of optimization performance.
result Explicit theoretical relationship between prediction and optimization performance.
Improved motion prediction for self-driving cars using trajectory sets and auxiliary losses.
problem Accurately predicting future vehicle motion for self-driving cars.
method Classification over trajectory sets with an auxiliary loss for off-road predictions and spatial-temporal relationships.
result Significant improvement in motion prediction performance on small datasets using map information.
New method improves structured prediction models using random structured outputs.
problem Improving structured prediction models in natural language processing.
method Linear-time principled algorithms using maximum loss over random structured outputs under Gaussian perturbations.
result The method produces a tighter upper bound of the Gibbs decoder distortion.
Study improves top-k set prediction with low cardinality.
problem Improving top-k set prediction accuracy with low cardinality.
method Introduces new target loss function and surrogate losses.
result Demonstrates effectiveness of cardinality-aware algorithms.
Optimizes ensemble predictions for various loss functions.
problem Minimizing prediction loss on unlabeled data.
method Minimax optimal aggregation of binary classifiers for general loss functions.
result Family of efficient semi-supervised ensemble algorithms.
A new convex loss function optimizes set predictions with balanced size and coverage.
problem Optimizing set predictions with balanced size and coverage.
method Proposes a convex loss function using Choquet integrals for nondecreasing subset-valued functions.
result Optimal trade-offs between conditional probabilistic coverage and set size.
This paper explores methods for combining predictions in multilabel classification.
problem Lack of formal framework for aggregation in multilabel ensembles.
method Introduces two approaches: 'predict then combine' (PTC) and 'combine then predict' (CTP).
result Standard voting techniques are outperformed by tailored instantiations of CTP and PTC.
Generalized algorithm for translation and scale-invariant prediction.
problem Sequential prediction with expert advice, focusing on translation and scale invariance.
method Designing a generalized online algorithm using the universal prediction perspective to compete against a generic class of expert selection strategies.
result No preliminary knowledge of loss sequences is required; performance bounds are stable under arbitrary scalings and translations.
Generative models learn to capture target distribution support with extreme value loss.
problem Mode collapse in generative models for non-trivial target distributions.
method Optimizing against the minimal value of the loss function, rather than the mean.
result Models trained with extreme value loss learn to capture the support of the target distribution.
The paper presents a multi-power law for predicting loss curves across different learning rate schedules.
problem Understanding and optimizing the relationship between model performance and hyperparameters, especially learning rates.
method Proposes a multi-power law that combines power laws based on the sum of learning rates and additional laws for loss reduction due to decay.
result The multi-power law accurately predicts loss curves for unseen learning rate schedules and finds a schedule that outperforms cosine learning rate.
Proposes a robust framework for multiclass classification.
problem General multiclass classification with adversarial robustness.
method Dual formulation as convex optimization with adversarial surrogate loss.
result Competitive performance in multiclass classification problems.
New method improves model calibration by adjusting confidence based on prediction correctness.
problem Improving model confidence alignment with true class probabilities.
method Post-hoc calibration objective using transformed samples for training.
result Competitive calibration performance on in-distribution and out-of-distribution test sets.
Paper proposes an alternative to set losses for predicting unordered variables without imposing structure.
problem Learning unordered variables with unknown interrelations without imposing structure.
method Viewing set prediction as conditional density estimation and using deep energy-based models with gradient-guided sampling.
result Empirically demonstrates capability to learn multi-modal densities and produce different plausible predictions.
Paper uses HGLM and bootstrap for loss reserve error estimation in insurance.
problem Estimating prediction error for loss reserves in non-life insurance.
method Hierarchical Generalized Linear Model (HGLM) and Bootstrap Estimator.
result Bootstrap provides full information about prediction error quantiles.
Paper develops a loss function using Wasserstein distance for multi-label prediction.
problem Challenges in learning multi-label outputs with a natural metric.
method Develops a loss function based on Wasserstein distance, regularized for efficiency.
result Wasserstein loss encourages smoothness of predictions with respect to a chosen metric.
Enhances linear regression with Kalman filter for loss minimization.
problem Minimizing loss in linear regression models.
method Integrates Kalman filter and SGD for optimal weight updates.
result Develops optimal linear regression equation with minimum area under curve.
New approach for structured prediction problems using regularization.
problem Structured prediction problems with embedded outputs in linear space.
method Surrogate loss approach and regularization techniques.
result Universal consistency and finite sample bounds for the proposed methods.
DeepTriangle uses deep learning for better insurance loss prediction.
problem Improving insurance loss prediction accuracy.
method Joint modeling of paid losses and claims outstanding using deep neural networks.
result DeepTriangle models outperform existing stochastic methods in predictive accuracy.
The paper proposes a framework for structured prediction using projection oracles.
problem Structured prediction with improved loss functions.
method A general framework for deriving loss functions using convex sets and projection oracles.
result Projections onto the marginal polytope can make the loss smaller and are computationally efficient.
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.
Linear-Core Surrogates combine fast optimization and statistical efficiency in classification and structured prediction.
problem The trade-off between smoothness and margin-based losses in classification and structured prediction.
method Linear-Core (LC) Surrogates, a family of convex loss functions that stitch a linear core to a smooth tail.
result LC Surrogates achieve fast linear consistency rates while maintaining differentiability and strict H-consistency bounds. Proposes new loss functions for better handling bimodal predictive uncertainty.
problem Bimodal predictive uncertainty in machine learning models.
method Family of distribution-aware loss functions integrating normalized RMSE with Wasserstein and Cramér distances.
result Proposed loss functions reduce predictive uncertainty estimation error by 45% on complex bimodal datasets.
Proposes a method to generate prediction intervals using weighted asymmetric loss functions.
problem Generating reliable prediction intervals for neural network models.
method Uses a weighted asymmetric loss function to estimate prediction intervals.
result The method produces reliable prediction intervals in complex machine learning scenarios.
We develop a framework for consistent polyhedral surrogates in classification and prediction.
problem Designing consistent polyhedral surrogates for classification and prediction problems.
method Formalizing and studying embeddings of predictions as points in R^d, assigning original loss values, and convexifying to create surrogates.
result Established a strong connection between embeddings and polyhedral surrogates, providing constructions and proofs of consistency or inconsistency.
Extends conformal prediction for controlling expected risk of monotone loss functions.
problem Controlling expected risk of monotone loss functions.
method Generalizes split conformal prediction with coverage guarantee, extending to distribution shift, quantile risk, multiple, adversarial, and expectations of U-statistics.
result Tight up to an O(1/n) factor, with worked examples in computer vision and natural language processing. Two models predict net loan losses using Bayesian and frequentist regression.
problem Predicting net loan losses using financial and sociological data.
method Bayesian and frequentist regression analysis.
result Improved understanding of net loan loss relationships.
Prod algorithm improves robustness and efficiency in log-loss prediction.
problem Efficient and robust algorithms for log-loss prediction under expert advice.
method Analysis of Prod algorithm for mixtures of experts with log-loss.
result Prod algorithm provides linear-time bound independent of largest loss and gradient.
A new autoregressive SPO method improves decision-making for dependent data.
problem Improving decision-making for dependent data in stochastic optimization.
method An autoregressive Smart Predict-then-Optimize (SPO) method for time series data.
result Generalization bounds and uniform calibration results for the SPO loss in autoregressive models.