We extend probabilistic programming to handle conditioning on marginal distributions.
problem Conditioning probabilistic programs on marginal distributions of observable variables.
method We define and implement stochastic conditioning, allowing inference in probabilistic programs conditioned on marginal distributions.
result We demonstrate the effectiveness of stochastic conditioning in various real-life scenarios.
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.
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.
ProbRes calibrates probabilistic forecasts by learning volatility dynamics.
problem Quantifying risk and uncertainty in time series forecasting.
method ProbRes learns conditional mean and volatility separately, generating well-calibrated prediction intervals.
result ProbRes accurately captures predictive distributions and produces well-calibrated prediction intervals.
ACE models allow flexible conditioning and prediction of latent variables.
problem Lack of flexibility in conditioning and prediction of latent variables in probabilistic models.
method Introduces Amortized Conditioning Engine (ACE) that explicitly represents latent variables and allows runtime conditioning and prediction.
result ACE models outperform existing methods in diverse tasks like image completion, classification, Bayesian optimization, and simulation-based inference.
State-space systems generate probabilistic dependencies between inputs and outputs.
problem Understanding probabilistic dependencies in state-space systems.
method Introducing a probabilistic framework and proving sufficient conditions for output existence and uniqueness.
result State-space systems can generate probabilistic dependencies, even without functional relations.
We present Natural Gradient Boosting (NGBoost), an algorithm for generic probabilistic prediction via gradient boosting. Typical regression models return a point estimate, conditional on covariates, but probabilistic regression models output a full probability distribution over the outcome space, conditional on the cov…
A new probabilistic mixup framework improves deep learning generalization.
problem Improving deep learning generalization performance.
method Introduces a novel probabilistic mixup framework for conditional density estimation.
result Empirical results show benefits over existing mixup variants.
This work combines recurrent models with diffusion for probabilistic time series forecasting.
problem Scalability and capturing high-dimensional distributions and cross-feature dependencies in time series forecasting.
method Combines recurrent neural networks' efficiency with diffusion models' probabilistic modeling, using stochastic interpolants and conditional generation.
result Offers scalable probabilistic time series forecasting methods.
Probabilistic graphical models are a central tool in AI; however, they are generally not as expressive as deep neural models, and inference is notoriously hard and slow. In contrast, deep probabilistic models such as sum-product networks (SPNs) capture joint distributions in a tractable fashion, but still lack the expr…
Treeffuser predicts tabular data distributions using gradient-boosted trees.
problem Probabilistic prediction with flexible, non-parametric models.
method Gradient-boosted trees for score estimation in conditional diffusion model.
result Treeffuser outperforms existing methods in probabilistic prediction tasks.
Partition Tree estimates conditional densities for mixed continuous and categorical variables.
problem Estimating conditional densities for mixed data types.
method Tree-based framework modeling conditional distributions as piecewise-constant densities on adaptive partitions, minimizing conditional negative log-likelihood.
result Improved probabilistic prediction compared to CART-style trees and state-of-the-art methods.
Proposes a method to apply conformal prediction to probabilistic time series forecasting models.
problem Obtaining accurate prediction regions for multi-step time series forecasting with probabilistic models.
method Conformalises conditional normalising flows to generate potentially disjoint prediction regions.
result Improves predictive efficiency in time series forecasting with multimodal distributions.
Proposes CCE to assess point-wise reliability of neural network predictions.
problem Overconfidence and misaligned predictive distributions in neural networks.
method Introduces Conditional Congruence (CCE) metric using conditional kernel mean embeddings.
result CCE exhibits correctness, monotonicity, reliability, and robustness in high-dimensional regression tasks.
SPPL simplifies probabilistic programming for exact inference.
problem Efficient exact inference in probabilistic models.
method SPPL translates probabilistic programs into sum-product expressions, leveraging new techniques for scalability.
result SPPL achieves up to 3500x speedups in exact inference.
Proposes a new framework for open set recognition using conditional probabilistic generative models.
problem Unknown samples can mislead traditional deep neural networks during testing.
method Conditional Probabilistic Generative Models (CPGM) that combine generative models with discriminative information.
result Significantly outperforms baselines on multiple benchmark datasets.
ProFITi model forecasts irregular time series with missing values using conditional flows.
problem Probabilistic forecasting of irregularly sampled multivariate time series with missing values.
method ProFITi model uses conditional normalizing flows and invertible layers to learn joint distributions conditioned on past observations and queried channels and times.
result ProFITi model provides 4 times higher likelihood than the previous best model.
New method for probabilistic prediction sets with conditional validity.
problem Marginal coverage guarantee of existing methods.
method Combines conformal methods with approximate conditional validity.
result Consistently outperforms existing approaches in conditional coverage.
Study efficient interactive learning for structured outputs with reliable computation.
problem Interactive learning with noisy labels and structured output spaces.
method Identify and utilize CRISPs (probabilistic models) that guarantee reliable and efficient computation of probabilistic quantities.
result CRISPs enable robust and efficient active and skeptical learning in large structured output spaces.
As inductive inference and machine learning methods in computer science see continued success, researchers are aiming to describe ever more complex probabilistic models and inference algorithms. It is natural to ask whether there is a universal computational procedure for probabilistic inference. We investigate the com…
Bayesian approach for policy search in stochastic domains.
problem Policy search in stochastic domains.
method Nested probabilistic programs, Lightweight Metropolis-Hastings (LMH) adaptation.
result Similar quality policies learned with simpler algorithm.
Deep neural operators learn complex probabilistic models efficiently.
problem Learning complex probabilistic models with global Lipschitz conditions.
method Deep neural-operator framework under global Lipschitz conditions.
result Explicit network-size bounds for universal approximation of probabilistic models.
Deep learning improves probabilistic PPDE solution accuracy.
problem Approximating solutions to path-dependent PDEs with limited basis selection.
method Deep learning for conditional expectation estimation with error bounds.
result Deep learning yields more accurate PPDE solutions, especially in high dimensions.
ICON learns differential equation operators from examples, revealing probabilistic inference.
problem Learning operators for differential equations from limited examples.
method Probabilistic operator learning using ICON architectures trained on diverse datasets.
result ICON implicitly performs Bayesian inference on solution operators.
CSDI improves time series imputation by 40-65% over existing methods.
problem Imputing missing values in time series data.
method Conditional Score-based Diffusion models conditioned on observed data.
result CSDI improves by 40-65% over existing probabilistic imputation methods on popular metrics.
CW-Gen models improve probabilistic time series forecasting by incorporating prior information.
problem Challenges in probabilistic forecasting of multivariate time series due to non-stationarity, inter-variable dependencies, and distribution shifts.
method CW-Gen framework that incorporates prior information through conditional whitening. JMCE learns conditional mean and covariance, improving sample quality.
result CW-Gen consistently enhances predictive performance, capturing non-stationary dynamics and inter-variable correlations more effectively than prior-free approaches.
Efficient methods for answering complex probabilistic queries in sequential data.
problem Complex probabilistic queries in sequential data.
method Broad class of novel approximation techniques for marginalization in sequential models.
result Efficient techniques for answering long-range probabilistic queries.
The paper studies the concepts of hedging and arbitrage in a non probabilistic framework. It provides conditions for non probabilistic arbitrage based on the topological structure of the trajectory space and makes connections with the usual notion of arbitrage. Several examples illustrate the non probabilistic arbitrag…
Develops effective adversarial attacks on probabilistic forecasting models.
problem Adversarial attacks on neural models outputting probability distributions.
method Effective generation of adversarial attacks through Monte-Carlo estimation and Bayesian conditioning.
result Demonstrates successful generation of attacks with small input perturbations.
We consider the problem of training probabilistic conditional random fields (CRFs) in the context of a task where performance is measured using a specific loss function. While maximum likelihood is the most common approach to training CRFs, it ignores the inherent structure of the task's loss function. We describe alte…
Unified tractability conditions for various compositional inference queries.
problem Analyzing tractability of probabilistic and causal inference queries.
method Algebraic perspective on circuits, focusing on semiring operators.
result Unified sufficient conditions for tractable composition of operators.
This paper presents foundational theoretical results on distributed parameter estimation for undirected probabilistic graphical models. It introduces a general condition on composite likelihood decompositions of these models which guarantees the global consistency of distributed estimators, provided the local estimator…
Paper extends quantile factor analysis with probabilistic methods for better economic policy and financial condition prediction.
problem Improving accuracy in economic and financial condition prediction.
method Probabilistic quantile factor analysis with regularization and variational approximations.
result The probabilistic estimator outperforms a recent loss-based estimator in many cases.
Type system captures CI relationships for probabilistic models.
problem Challenges in inference for models with mixed discrete and continuous parameters.
method Information flow type system for probabilistic programming.
result Well-typed programs guarantee certain CI relationships.
Fast algorithm solves BVPs in linear time with probabilistic uncertainty.
problem Solving boundary value problems efficiently and accurately.
method Gauss--Markov prior tailored to BVPs, linear-time computation.
result Probabilistic solution with linear time complexity and comparable quality.
DIN framework directly models hydraulic conductivity and uncertainty.
problem Modeling hydraulic conductivity and uncertainty in groundwater flow.
method DIN utilizes DDPM as a prior learner, incorporating observational data through conditional injection mechanisms.
result DIN generates multiple constraint-satisfying realizations and accurate uncertainty quantification.
Combines coarse learners for nonparametric probabilistic regression.
problem Predicting full probability density functions without strong assumptions.
method Combining gradient boosted forests trained on coarsened target values.
result Prediction intervals have high fidelity and provide valuable insights.
Paper introduces md-vtrees for efficient probabilistic and causal inference.
problem Efficient inference in complex probabilistic models.
method Introduces md-vtrees to generalize tractability conditions for advanced inference queries.
result Derives first polytime algorithms for causal inference queries.
New model forecasts power consumption with high accuracy over months to years.
problem Probabilistic forecasting of power consumption in a middle-term horizon.
method Combines traditional time-series analysis with weather conditions using Gaussian Process.
result Promising results in Out-of-Sample density forecasts up to one year.
MD-CGAN models forecast time series with probabilistic posterior distributions.
problem Limited applications of GANs in time series forecasting, especially with probabilistic predictions.
method Mixture Density Conditional Generative Adversarial Model (MD-CGAN) using Gaussian mixture output.
result MD-CGAN outperforms benchmarks, especially in noisy time series.
This work offers a broad perspective on probabilistic modeling and inference in light of recent advances in probabilistic programming, in which models are formally expressed in Turing-complete programming languages. We consider a typical workflow and how probabilistic programming languages can help to automate this wor…
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.
We introduce a toy probabilistic model to analyze job-matching processes in recent Japanese labor markets for university graduates by means of statistical physics. We show that the aggregation probability of each company is rewritten by means of non-linear map under several conditions. Mathematical treatment of the map…
We describe a method for parameter estimation in bipartite probabilistic graphical models for joint prediction of clinical conditions from the electronic medical record. The method does not rely on the availability of gold-standard labels, but rather uses noisy labels, called anchors, for learning. We provide a likelih…
Transformer model for probabilistic dynamical systems.
problem Modeling high-dimensional dynamical systems from noisy observations.
method Parallel between dynamical systems and language modeling; transformer-based model with geometrical properties; iterative training algorithm.
result Fine-grid approximation of conditional probabilities for high-dimensional systems.
Proposes a new method for probabilistic forecasting using stochastic interpolants and Föllmer processes.
problem Probabilistic forecasting of dynamical systems.
method Generative modeling and stochastic interpolants to map current state to probabilistic ensemble of forecasts.
result The approach can be used to forecast complex, high-dimensional systems like Navier-Stokes and video sequences.
New method learns PDE solutions from low-fidelity data.
problem Challenges in learning PDE surrogates with scarce data.
method Flow matching in infinite-dimensional space with conditional neural operators.
result Accurately learns PDE solutions across different resolutions and fidelities.
New framework uses cohomology to analyze probabilistic distortions and arbitrage.
problem Analyzing probabilistic distortions and arbitrage in categorical filtrations.
method Transport cohomological framework, simplicial structure, loop effects, holonomy.
result Nontrivial probabilistic distortions and obstructions generated by loops.