This paper improves operational risk modeling by selecting better loss severity distributions.
problem Inconsistent regulatory capital calculations due to changing loss severity distribution families.
method Presented truncation probability estimates and a consistent quantile scoring function for selection criteria. Also, recommended collecting loss frequencies below the minimum reporting threshold.
result More stable regulatory capital calculations through better selection of loss severity distributions.
Method enhances anomaly detection using contrastive learning and out-of-distribution data.
problem Improving anomaly detection in datasets with limited out-of-distribution data.
method Proposes a contrastive learning method that incorporates out-of-distribution data to enhance anomaly detection performance.
result The method significantly improves anomaly detection performance, even with limited out-of-distribution data.
Paper introduces a geometric approach to model similar probability distributions.
problem Incorporating similar probability distributions into graphical models.
method Information geometric approach to model similar distributions.
result Allows reinterpretation of existing models.
This paper examines how optimization methods affect the reliability of detecting inputs outside a model's training distribution.
problem The unreliability of deep neural networks on out-of-distribution inputs.
method Analysis of optimization methods' impact on OOD detection approaches.
result Optimization methods significantly influence the robustness of OOD detection approaches.
Unified approach for nonparametric regression and conditional distribution learning.
problem Nonparametric regression and conditional distribution learning problems.
method Generative learning framework with deep neural networks to estimate a conditional generator.
result The approach estimates a regression function and a conditional generator simultaneously, providing good prediction intervals.
New approach improves domain adaptation by relaxing distribution alignment constraints.
problem Improving domain adaptation when target distribution differs from source distribution.
method Asymmetrically-relaxed distribution alignment to minimize target error under varying conditions.
result Empirical and theoretical benefits demonstrated on synthetic and real datasets.
New method robust to random distributional shifts in prediction.
problem Random distributional shifts in real-world settings.
method Hybrid approach combining long-term and proxy outcomes.
result Hybrid approach yields lower mean-squared error than current methods.
A new approach for test-time adaptation detects and reacts to distribution shifts.
problem Improving test-time accuracy under distribution shifts.
method Online self-training with a detection tool based on entropy values and betting martingales.
result The classifier's entropy values match those of the source domain, building invariance to distribution shifts.
A GAN-based approach for multivariate policy evaluation and exploration in reinforcement learning.
problem Multivariate reinforcement learning with high-dimensional data.
method Formulating DiRL as a GAN model for multivariate rewards and state transitions.
result Unified approach for learning values and states with a discrepancy-driven exploration method.
NMDR estimates complex mixtures of distributions efficiently.
problem Estimating complex finite mixtures of distributions in high-dimensional settings.
method Flexible additive predictors, neural networks, and deep learning optimizers.
result Competitive performance in complex scenarios compared to existing approaches.
Study learns mixtures of smooth product distributions from samples.
problem Learning mixtures of non-parametric product distributions.
method Two-stage approach using identifiability properties of tensor decomposition and signal processing techniques.
result Recovery of component distributions under a smoothness condition.
A new method for modeling insurance claim frequencies using random proportions.
problem Inaccurate fitting of classical distributions to insurance claim frequency data.
method Modeling claim frequencies using random proportions of insurance contracts and applying goodness-of-fit tests.
result A new statistical approach for better modeling insurance claim frequencies.
Federated learning framework with uncertainty estimation.
problem Uncertainty estimation in federated learning models.
method Infers and distills posterior predictive distributions from clients to server.
result Improved accuracy and reliability in predictions and tasks like OOD detection.
New approach to machine learning optimization using distribution space.
problem Optimization challenges in machine learning with non-convex constraints.
method Relaxation to convex optimization in distribution space, numerical algorithm based on mixture distributions.
result Approximate optimization in distribution space is consistent and effective.
New MCMC method tackles heavy tailed distributions using Fourier transforms.
problem Challenges in sampling from heavy tailed distributions using MCMC.
method Proposes Fourier transform MCMC to sample from densities with known Fourier transforms.
result Shows geometric ergodicity of the resulting Markov chain for heavy tailed distributions.
New approach detects out-of-distribution inputs without needing OOD samples.
problem Detecting incorrect classification of out-of-distribution inputs in deep neural networks.
method A one-class classifier trained on an early layer's output of the original classifier.
result Substantially better results compared to state-of-the-art approaches.
Evaluation and validation of complicated control systems are crucial to guarantee usability and safety. Usually, failure happens in some very rarely encountered situations, but once triggered, the consequence is disastrous. Accelerated Evaluation is a methodology that efficiently tests those rarely-occurring yet critic…
Deep learning outperforms classic machine learning in DAS event detection.
problem Event detection in Distributed Acoustic Sensing (DAS).
method Comparison of classic machine learning and image-based deep learning approaches.
result Image-based deep learning offers significantly faster event detection and execution times.
Transformer improves parameter estimation without needing closed-form solutions.
problem Parameter estimation in statistics, especially for complex distributions.
method Transformer-based approach for parameter estimation without closed-form solutions or derivations.
result Transformer-based approach achieves similar or better accuracy than maximum likelihood estimation.
New RL algorithm minimizes distributional learning error.
problem Improving distributional reinforcement learning for better error minimization.
method Proposes a new model-based algorithm with theoretical minimax optimality.
result Proves minimax optimality for approximating return distributions.
Study compares symbolic and distributional methods for relational learning.
problem Comparing symbolic and distributional paradigms for relational learning.
method Comparison of representation learning and relational learning on various tasks.
result Preliminary results suggest possible indicators for choosing between approaches.
New method ensures generated data statistics match real data distributions.
problem Ensuring generated data statistics match real data distributions in GANs.
method Added a new loss term to the generator loss function using f-divergences and kernel density estimation.
result Improved performance on synthetic and real-world datasets.
Unified approach to non-standard classification tasks.
problem Non-standard classification tasks like semi-supervised, positive-unlabelled, multi-positive-unlabelled and noisy-label learning.
method Probabilistic, unified approach training a classifier to predict label-distributions, then inferring class-distributions.
result Unified model for various non-standard classification tasks.
A new Fusion method combines multiple distributions efficiently.
problem Combining multiple distributions for big data or privacy.
method Recursive divide-and-conquer Monte Carlo approach.
result A robust Fusion method for many sub-posteriors.
Detects out-of-distribution and adversarial samples using deep feature distributions.
problem Detecting out-of-distribution and adversarial samples in deep neural networks.
method Modeling deep features with parametric probability distributions and calculating likelihoods at inference.
result Improves detection of out-of-distribution and adversarial samples, up to 12 percentage points in AUPR and AUROC metrics.
Proposes an energy-based sliced Wasserstein distance for improved probability measure comparison.
problem Inefficiencies and limitations in existing sliced Wasserstein distance approaches.
method Introduces an energy-based slicing distribution for better performance and stability.
result Demonstrates superior performance of the EBSW distance in various applications.
Piecewise normalizing flows improve multi-modal distribution modeling.
problem Improving accuracy in modeling multi-modal distributions.
method Divide target distribution into clusters, train flows to match standard normal base.
result Piecewise flows outperform standard approaches in accuracy.
The paper proposes a new probability distribution for rooted trees.
problem Overfitting in tree selection for statistical models.
method Bayesian approach with a generalized probability distribution for rooted trees.
result Recursive methods to evaluate the probability distribution without approximations.
Paper proposes a new method to detect out-of-distribution samples.
problem Detecting out-of-distribution samples for neural network classifiers.
method Generates effective OOD samples using a manifold learning network and trains an additional classifier.
result Proposed method consistently performs better than existing classifiers on MNIST and Fashion-MNIST datasets.
This article reviews and compares various methods for estimating conditional distributions.
problem Inference of conditional distributions in statistics.
method Classical nonparametric methods and modern generative models.
result A systematic numerical comparison of methods using performance metrics.
Robust forecast framework reduces distribution error by 63%.
problem Accurate distribution forecast for planning decisions.
method Backtest-based bootstrap and adaptive residual selection.
result Reduces Absolute Coverage Error by more than 63%.
Two approaches extend knowledge distillation to Gaussian Processes, showing relationships to existing methods.
problem Applying knowledge distillation to Gaussian Processes for regression and classification.
method Data-centric and distribution-centric approaches to extend distillation to GPR and GPC.
result Distribution-centric approach for GPC approximately corresponds to data duplication and scaling.
High-probability bound for distributed stochastic approximation tracking error.
problem Analyzing the convergence of distributed stochastic approximation schemes.
method Analysis using ODE approach to stochastic approximation.
result High probability bound for tracking error between iterates and limiting differential equation.
In this letter, we derive the optimal discriminant functions for modulation classification based on the sampled distribution distance. The proposed method classifies various candidate constellations using a low complexity approach based on the distribution distance at specific testpoints along the cumulative distributi…
The distribution of the returns for a stock are not well described by a normal probability density function (pdf). Student's t-distributions, which have fat tails, are known to fit the distributions of the returns. We present pricing of European call or put options using a log Student's t-distribution, which we call a …
A new method for incorporating preferences in multi-objective Bayesian optimization.
problem Incorporating preferences in computationally expensive multi-objective optimization problems.
method Building independent surrogate models on each objective function and using Generalised value distribution to approximate the scalarizing function.
result The proposed multi-surrogate approach outperforms the mono-surrogate approach on benchmark and real-world problems.
Distributed learning adapts to diverse devices, improving performance.
problem Training neural networks on devices with varying capabilities and resources.
method Each device trains a customized neural network, sharing parameters with others.
result Achieves higher rewards on more powerful devices without sacrificing weaker ones.
A mixture of shifted asymmetric Laplace distributions is introduced and used for clustering and classification. A variant of the EM algorithm is developed for parameter estimation by exploiting the relationship with the general inverse Gaussian distribution. This approach is mathematically elegant and relatively comput…
Novel neural network models quantify uncertainty for deep classifiers.
problem Deep networks' overconfidence and ignorance about uncertainty.
method Variational autoencoders and GANs generate out-of-distribution samples.
result Better uncertainty estimates for in- and out-of-distribution samples.
This paper provides new algorithms for distributed clustering for two popular center-based objectives, k-median and k-means. These algorithms have provable guarantees and improve communication complexity over existing approaches. Following a classic approach in clustering by \cite{har2004coresets}, we reduce the proble…
This paper uses distributional distances to estimate causal effects more comprehensively.
problem Estimating nuanced causal effects beyond simple averages.
method Distributional distances, doubly robust estimator, Lq risks, bootstrap confidence intervals. result Proposed methods provide reliable estimates of causal effects.
To quantify an operational risk capital charge under Basel II, many banks adopt a Loss Distribution Approach. Under this approach, quantification of the frequency and severity distributions of operational risk involves the bank's internal data, expert opinions and relevant external data. In this paper we suggest a new …
Improved likelihood estimation for singular distributions using deep models.
problem Estimating singular distributions using deep generative models.
method Data perturbation to avoid singularity issues in likelihood estimation.
result Consistent estimation of target distribution with desirable rates.
Generates confident out-of-distribution samples to improve classifier robustness.
problem Overconfidence in deep learning models on out-of-distribution inputs.
method Uses a GAN to generate out-of-distribution samples that the classifier is confident on, maximizing entropy.
result Shows effectiveness on handwritten characters and natural images datasets.
Exponential distribution is ubiquitous in the framework of multi-agent systems. An alternative approach with an economic motivation to derive the exponential distribution in the framework of iterations in the space of distributions is disclosed.
A new method improves inference for complex Bayesian models.
problem Bayesian inference for doubly intractable distributions is computationally challenging.
method Monte Carlo Stein variational gradient descent (MC-SVGD) approach.
result The method achieves substantial computational gains over existing algorithms.
Bayesian inference models failure distributions in autonomous systems.
problem Estimating the distribution of failures in complex systems.
method Bayesian inference using system dynamics rollouts and gradient computation.
result Improves sample efficiency and parameter space coverage in autonomous systems.
Paper improves forest representation learning by optimizing margin distribution.
problem Improving generalization gap in forest representation learning.
method Reformulated as an additive model, optimizing margin distribution ratio λ.
result Substantially improved upper bound of generalization gap from O(√(ln m / m)) to O((ln m) / m).