MIRA scores assess conditional distribution accuracy using joint samples.
problem Assessing the accuracy of candidate conditional distributions.
method Analytic expression for Mira score based on equal probability mass regions.
result Mira enables Bayesian model comparison by quantifying alignment with true process.
Calibrated ensembles improve both ID and OOD accuracy in distribution shift.
problem Desired balance between in-distribution and out-of-distribution accuracy.
method Ensemble standard and robust models, calibrating on ID data only.
result ID-calibrated ensembles outperform state-of-the-art methods on multiple datasets.
Current OOD benchmarks overestimate model robustness to spurious correlations.
problem Spurious correlations degrade OOD performance, but benchmarks show the opposite.
method Analyze OOD datasets for spurious correlations and derive conditions for robustness.
result Current OOD benchmarks are misspecified and overestimate model robustness.
New model predicts radiative properties of nanoparticle layers with high accuracy and uncertainty.
problem Predicting radiative properties of nanoparticle embedded layers accurately and with uncertainty.
method Conditional normalizing flows learn conditional distributions of optical outputs given input parameters.
result The model achieves high predictive accuracy and reliable uncertainty estimates.
New trade-off found between accuracy and adversarial robustness in regression.
problem Finding a balance between accuracy and robustness in regression models.
method Deriving a fundamental trade-off between standard and adversarial risk in regression with polynomial ridge functions.
result A necessary condition for achieving adversarial robustness without significant accuracy loss.
Unified probabilistic gradient boosting for entire conditional distribution modeling.
problem Creating accurate probabilistic forecasts from regression tasks.
method Unified probabilistic gradient boosting framework using XGBoost and LightGBM, modeling conditional moments or CDF via Normalizing Flows.
result Achieves state-of-the-art forecast accuracy.
Accuracy on in-distribution data correlates with out-of-distribution data when data is noisy or contains nuisance features.
problem Correlation between in-distribution and out-of-distribution accuracy in noisy or feature-rich data.
method Analyzes the impact of noise and nuisance features on model performance.
result Accuracy on in-distribution and out-of-distribution data can become negatively correlated in noisy or feature-rich data.
Paper optimizes training data distribution for better model performance across various deployment conditions.
problem Improving model accuracy when deployed with parameters far from training data.
method Developed adaptive algorithms based on bilevel or alternating optimization in the space of probability measures.
result Optimized training distributions lead to models with improved sample complexity and robustness to distribution shift.
A trade-off between accuracy and fairness is almost taken as a given in the existing literature on fairness in machine learning. Yet, it is not preordained that accuracy should decrease with increased fairness. Novel to this work, we examine fair classification through the lens of mismatched hypothesis testing: trying …
The paper studies and mitigates accuracy disparity in regression models.
problem Accuracy disparity between different demographic subgroups in high-stakes domains.
method Error decomposition theorem and distribution alignment algorithm.
result The proposed algorithm effectively mitigates accuracy disparity while maintaining predictive power.
We study the problem of learning fair prediction models for unseen test sets distributed differently from the train set. Stability against changes in data distribution is an important mandate for responsible deployment of models. The domain adaptation literature addresses this concern, albeit with the notion of stabili…
The impact of a stress scenario of default events on the loss distribution of a credit portfolio can be assessed by determining the loss distribution conditional on these events. While it is conceptually easy to estimate loss distributions conditional on default events by means of Monte Carlo simulation, it becomes imp…
C-SymmPI provides near-conditional coverage for structured data with group symmetries.
problem Establishing near-conditional coverage guarantees for structured data with group symmetries.
method Developed a framework C-SymmPI that achieves near-conditional coverage under general data structures with group symmetries.
result Near-conditional coverage guarantees for structured data with group symmetries.
CP-ROC bands improve graph classification accuracy and uncertainty quantification.
problem Uncertainty quantification and robustness to distributional shifts in graph classification.
method Conditional Prediction ROC (CP-ROC) bands for graph classification, developed for TGNNs and adaptable to GNNs.
result Statistically guaranteed coverage for CP-ROC under local exchangeability condition, improving prediction reliability.
NCP uses neural networks to efficiently learn conditional distributions.
problem Learning conditional distributions for statistical inference.
method Neural Conditional Probability (NCP) approach.
result NCP efficiently handles complex probability distributions and matches leading methods.
The gamma distribution arises frequently in Bayesian models, but there is not an easy-to-use conjugate prior for the shape parameter of a gamma. This inconvenience is usually dealt with by using either Metropolis-Hastings moves, rejection sampling methods, or numerical integration. However, in models with a large numbe…
In distributed machine learning, data is dispatched to multiple machines for processing. Motivated by the fact that similar data points often belong to the same or similar classes, and more generally, classification rules of high accuracy tend to be "locally simple but globally complex" (Vapnik & Bottou 1993), we propo…
New bounds on majority voting's accuracy for multi-class classification problems.
problem Determining the accuracy of majority voting for multi-class classification.
method Analyzing the majority voting function under different voter conditions and distributions.
result The error rate of majority voting exponentially decays or grows with the number of voters under certain conditions.
Unified framework for fairness, robustness, and distribution shifts.
problem Diverse failure modes of machine learning systems.
method Formalizes biases as violations of conditional independence and proves equivalence conditions.
result Equivalent effects of biases in different failure modes under specific conditions.
Neural Processes (NPs) (Garnelo et al 2018a;b) approach regression by learning to map a context set of observed input-output pairs to a distribution over regression functions. Each function models the distribution of the output given an input, conditioned on the context. NPs have the benefit of fitting observed data ef…
This paper introduces a neural operator for probabilistic conditioning.
problem Probabilistic conditioning of random variables X given Y. method Develops a single operator that maps any joint density to its conditional, approximated by neural operators.
result Neural operators can approximate the conditioning operator to arbitrary accuracy.
Guiding the design of neural networks is of great importance to save enormous resources consumed on empirical decisions of architectural parameters. This paper constructs shallow sigmoid-type neural networks that achieve 100% accuracy in classification for datasets following a linear separability condition. The separab…
NM-VQTSG improves synthetic time series fidelity by aligning distributions.
problem Fidelity challenges in VQ-based time series generation.
method Neural mapping model using U-Net to refine synthetic data.
result Significant improvements in FID, IS, and conditional FID metrics.
Due to their flexibility and predictive performance, machine-learning based regression methods have become an important tool for predictive modeling and forecasting. However, most methods focus on estimating the conditional mean or specific quantiles of the target quantity and do not provide the full conditional distri…
New CPS model tackles conditional probability shift in machine learning.
problem Discrepancy between source and target distributions in machine learning.
method Conditional Probability Shift Model (CPSM) using multinomial regression and EM algorithm.
result Superior balanced classification accuracy on target data compared to existing methods.
NSFs learn SDE transition laws for efficient sampling.
problem Efficiently sampling between arbitrary time points in SDEs.
method Conditional normalising flows with architectural constraints.
result Up to two orders of magnitude speed-ups at large time gaps.
DS-Sync improves distributed DNN training efficiency by 94% with minimal accuracy loss.
problem Network bottlenecks in distributed DNN training.
method Divide workers into non-overlapping groups for independent synchronization, then shuffle workers among groups iteratively.
result DS-Sync achieves up to 94% improvement in training time with minimal accuracy loss.
CIR method constructs efficient prediction intervals with guaranteed coverage.
problem Efficiently constructing near-minimal prediction intervals with guaranteed coverage.
method Conditional Interquantile Regression (CIR) and CIR+ (enhanced version).
result Optimal balance between predictive accuracy and computational efficiency.
Unified approach for multimodal data prediction using synthetic data generation.
problem Challenges in integrating heterogeneous data types for accurate predictive performance.
method Generative Distribution Prediction (GDP) framework that uses multimodal synthetic data generation.
result Empirical validation across four tasks demonstrates versatility and effectiveness of GDP.
Deep generative models (DGMs) of images are now sufficiently mature that they produce nearly photorealistic samples and obtain scores similar to the data distribution on heuristics such as Frechet Inception Distance (FID). These results, especially on large-scale datasets such as ImageNet, suggest that DGMs are learnin…
Majority of state-of-the-art deep learning methods are discriminative approaches, which model the conditional distribution of labels given inputs features. The success of such approaches heavily depends on high-quality labeled instances, which are not easy to obtain, especially as the number of candidate classes increa…
CQNPs enhance predictive performance and distribution modeling using quantile regression.
problem Limited predictive likelihood of Gaussian models for complex distributions.
method Introducing Conditional Quantile Neural Processes (CQNPs) that focus on estimating informative quantiles.
result Significant improvements in predictive performance and better modeling of multimodal distributions.
A framework reduces bias in sampling from posterior distributions.
problem Reducing bias in sampling from posterior distributions.
method A black-box debiasing scheme generating weighted samples.
result Improves accuracy of posterior sampling without increasing variance.
SQFA learns features maximizing Fisher-Rao distance for better classification.
problem Improving classification accuracy through feature learning.
method SQFA learns linear features maximizing Fisher-Rao distance between class-conditional distributions.
result SQFA-H features achieve the best classification accuracy.
New method improves nonlinear filtering accuracy with reduced computation.
problem Complex nonlinear filtering with small system noise.
method Asymptotic expansion with ordinary differential equations and Edgeworth-type correction.
result Significantly lower computational cost with improved accuracy.
Improves QMC for complex distributions using transport maps.
problem Challenges in applying QMC to general target distributions.
method Train a transport map to approximate target distributions, ensuring RQMC achieves superior error rates.
result Transport QMC achieves faster convergence rates than standard Monte Carlo under mild conditions.
Directly estimates CQC, improving interpretability and accuracy.
problem Inability to model and interpret CQC due to inversion issue.
method Direct doubly robust estimation of CQC without inversion.
result Improved estimation accuracy and interpretability.
FDN improves probabilistic regressors' adaptability to distribution shifts.
problem Overconfidence in modern probabilistic regressors under distribution shift.
method FDN uses input-conditioned distributions over network weights, trained with a Monte Carlo beta-ELBO objective.
result FDN produces predictive mixtures whose dispersion adapts to the input, providing shift-aware uncertainty.
DeepDIVE disentangles input into marginal and conditional distributions for multi-task learning.
problem Challenges in multi-task learning due to conflicting objectives.
method Inspired by probability theory, DeepDIVE uses a variational autoencoder with disentangled features and cross-attention mechanism.
result DeepDIVE disentangles input and improves forecast accuracy compared to baseline models.
MF-GLaM models improve stochastic simulator emulation with multifidelity data.
problem Challenging to emulate stochastic simulators' full conditional probability distribution.
method Proposes MF-GLaMs to efficiently emulate HF stochastic simulators using LF data.
result MF-GLaMs achieve improved accuracy or comparable performance at reduced cost.
New framework uses geometry of embeddings to predict robustness.
problem Monitoring robustness in models without OOD labels.
method Constructs graphs from embeddings, measures spectral complexity and curvature.
result Representation geometry predicts robustness reliably.
Paper justifies ideal point forecasts as measurable, clarifying conditions for their existence.
problem Justifying ideal point forecasts as measurable random variables.
method Clarifying and establishing measurability conditions for a wide class of functionals.
result Ideal point forecasts are shown to be measurable, providing theoretical justification.
Linear trends in classifier accuracy observed under distribution shift.
problem Understanding why classifier accuracies show linear trends under distribution shift.
method Assumed model similarity and verified empirically.
result Linear trend in classifier accuracy occurs unless distribution shift is large.
Unified study of out-of-distribution generalization across 172 datasets.
problem Measuring and improving robustness of transfer learning models.
method Collect and fine-tune 31k models on 172 dataset pairs, varying architectures and settings.
result In- and out-of-distribution accuracies increase jointly but their relation is dataset-dependent.
Hamiltonian Monte Carlo (HMC) is a widely deployed method to sample from high-dimensional distributions in Statistics and Machine learning. HMC is known to run very efficiently in practice and its popular second-order "leapfrog" implementation has long been conjectured to run in d1/4 gradient evaluations. Here we …
Study approximates operators on labelled conditional distributions for non-exchangeable systems.
problem Approximating operators on constrained probability measures for non-exchangeable systems.
method Combines cylindrical approximations and DeepONet-type neural architecture for finite-dimensional representations.
result Establishes a universal approximation theorem for continuous operators on Mλ. This paper improves active learning for Gaussian process regression to handle distributional uncertainty.
problem Active learning for Gaussian process regression does not guarantee accurate predictions for target distributions.
method Proposes two methods to reduce worst-case expected error for Gaussian process regression.
result Shows an upper bound of the worst-case expected squared error, suggesting finite data labels can achieve arbitrarily small error.
A new method improves SVI for high-dimensional, poorly-conditioned distributions.
problem Challenges in existing SVI methods for high-dimensional, poorly-conditioned distributions.
method Trust-region optimization approach leveraging conditional independences and second-order information.
result Superior numerical performance and better scalability in high-dimensional distributions.