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.
We present a novel tractable generative model that extends Sum-Product Networks (SPNs) and significantly boosts their power. We call it Sum-Product-Quotient Networks (SPQNs), whose core concept is to incorporate conditional distributions into the model by direct computation using quotient nodes, e.g. $P(A|B) = \frac{P(…
New tractable density models from squaring neural networks.
problem Flexible models for probability distributions in machine learning.
method Squared Neural Family (SNEFY) models formed by squaring neural network outputs and normalizing.
result SNEFYs are fully tractable with closed form normalizing constants in many cases.
A non-Euclidean generalization of conditional expectation is introduced and characterized as the minimizer of expected intrinsic squared-distance from a manifold-valued target. The computational tractable formulation expresses the non-convex optimization problem as transformations of Euclidean conditional expectation. …
Study shows tractable generalization in RL is impossible but possible with Strong Proximity.
problem RL agents struggle to generalize to new environments.
method Introduced Weak and Strong Proximity conditions to capture similarity between environments.
result Proved Strong Proximity is sufficient for efficient generalization.
Hybrid model combines continuous and tractable probabilistic models.
problem Intractable probabilistic inference in continuous latent-space models.
method Continuous mixtures of tractable probabilistic models with finite integration points.
result Hybrid models achieve state-of-the-art performance in density estimation.
TRUST improves structure learning with tractable uncertainty.
problem Capturing uncertainty in structure learning for causal DAGs.
method Probabilistic circuits for posterior inference.
result Probabilistic circuits enhance structure learning quality and uncertainty.
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.
Proposes Exogenous Matching for efficient counterfactual estimation.
problem Efficient estimation of counterfactual expressions in general settings.
method Transforms variance minimization into conditional distribution learning.
result Outperforms other importance sampling methods in counterfactual estimation.
A central problem in machine learning involves modeling complex data-sets using highly flexible families of probability distributions in which learning, sampling, inference, and evaluation are still analytically or computationally tractable. Here, we develop an approach that simultaneously achieves both flexibility and…
New method for fitting graphical models with latent variables using regularized conditional likelihood.
problem Graphical modeling with latent variables and confounding dependencies.
method Regularized conditional likelihood for exponential family graphical models.
result Framework applicable to broader settings without knowing latent variables' distribution.
We introduce RNADE, a new model for joint density estimation of real-valued vectors. Our model calculates the density of a datapoint as the product of one-dimensional conditionals modeled using mixture density networks with shared parameters. RNADE learns a distributed representation of the data, while having a tractab…
New framework for conditional risk minimization using optimal transport.
problem High-stakes decisions with side information, especially economic conditions.
method Universal framework based on union-ball formulation in optimal transport.
result Offers interpretability, tractability, and scalability for various risk functionals.
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.
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…
MDMA provides closed-form marginals and conditionals for deep networks.
problem Lack of closed-form marginals and conditionals in deep neural models.
method MDMA architecture combining deep scalar representations and hierarchical tensor decompositions.
result MDMA outperforms state-of-the-art models in tasks requiring marginalization and conditional inference.
Variational inference (VI) is a widely used framework in Bayesian estimation. For most of the non-Gaussian statistical models, it is infeasible to find an analytically tractable solution to estimate the posterior distributions of the parameters. Recently, an improved framework, namely the extended variational inference…
ACNML method improves uncertainty estimation for deep networks.
problem Uncertainty estimation and calibration for deep neural networks under distribution shift.
method Approximate Bayesian inference to approximate CNML distribution.
result ACNML compares favorably to prior techniques for uncertainty estimation.
LatentFlow simplifies conditioning of stochastic processes without training.
problem Intractable conditional laws for complex stochastic models.
method Writing stochastic process as latent innovation, reducing conditioning to latent-space inference.
result Exact conditional sampling across various model classes.
This paper advances sample-efficient learning for partially observable RL by introducing B-stability and new algorithms.
problem Hard sample complexity for learning near-optimal policies in partially observable RL.
method Proposes B-stability as a unified structural condition and develops new algorithms for sample-efficient learning.
result Any B-stable PSR can be learned with polynomial samples, improving over current best complexities.
Unified framework for tractable inference scenarios in machine learning models.
problem Complex inference scenarios in machine learning models.
method Characterization of tractable modular operations over circuits and derivation of a unified framework.
result Unified framework for reasoning about tractable models.
We present a class of models that, via a simple construction, enables exact, incremental, non-parametric, polynomial-time, Bayesian inference of conditional measures. The approach relies upon creating a sequence of covers on the conditioning variable and maintaining a different model for each set within a cover. Infere…
This paper develops tools for nonreversible MCMC with convergence guarantees.
problem Designing nonreversible MCMC kernels with convergence guarantees.
method Develops tools for nonreversible Markov kernels using conditional invertible transforms.
result Ensures nonreversible kernels have the desired invariance property and lead to convergent algorithms.
The discrete-time multifactor Vasiček model is a tractable Gaussian spot rate model. Typically, two- or three-factor versions allow one to capture the dependence structure between yields with different times to maturity in an appropriate way. In practice, re-calibration of the model to the prevailing market conditions …
Flexible selective inference using flow-based transport maps.
problem Selective inference with complex selection events.
method Flow-based generative modeling for conditional distribution approximation.
result Valid p-values and confidence sets for adaptively selected hypotheses and parameters.
OMLE combines optimism and MLE for efficient sequential decision making.
problem Efficiently solving sequential decision making problems, especially in partially observable settings.
method Combines optimism for exploration and maximum likelihood estimation for model learning.
result OMLE learns near-optimal policies for a wide range of sequential decision making problems.
Proves efficient learning of hierarchical structure in meta-reinforcement learning.
problem Lack of provable guarantees for learning hierarchical structures in reinforcement learning.
method Analyzed HRL in meta-RL setting with tabular transition dynamics, providing diversity conditions and regret bounds.
result Sample-efficient recovery of natural hierarchical structure with provable guarantees.
PNCs balance tractability and expressiveness in probabilistic modeling.
problem Balancing tractability and expressiveness in probabilistic models.
method Introduce probabilistic neural circuits (PNCs) as a mix of Bayesian networks and neural networks.
result PNCs are powerful function approximators.
New methods for fairness in regression using probabilistic classification.
problem Estimating fairness in continuous regression problems.
method Tractable approximations of fairness criteria using conditional probabilities from distinct classifiers.
result Model agnostic, tractable approximations of fairness criteria.
Generates samples conditioned on labels using optimal transport.
problem Estimating conditional distributions for specific labels.
method Wasserstein geodesic generator based on optimal transport theory.
result Learned conditional distributions and optimal transport maps.
Variational inference is a popular technique to approximate a possibly intractable Bayesian posterior with a more tractable one. Recently, boosting variational inference has been proposed as a new paradigm to approximate the posterior by a mixture of densities by greedily adding components to the mixture. However, as i…
Sharp policy value estimation for contextual bandits with unobserved confounders.
problem Estimating policy value under unobserved confounders with sensitivity analysis.
method Kernel method to approximate conditional moment constraints, leveraging f-divergence.
result Sharp lower bound of policy value, avoiding coarse relaxation of uncertainty set.
Improved video tracking accuracy with active learning.
problem Efficiently predicting object matches in videos with active learning.
method Adversarial approach for active learning with structured prediction domains.
result Better accuracy and computational efficiency for object tracking.
A new method trains and samples from energy-based models using diffusion recovery likelihood.
problem Training and sampling high-dimensional datasets with energy-based models is challenging.
method Trains EBMs with a diffusion recovery likelihood method, maximizing conditional probabilities of data at different noise levels.
result Generates high-fidelity images with low FID and inception scores, and accurately estimates normalized data density.
Proposes a method to generate text that adheres to logical constraints.
problem Generating text that respects logical constraints is hard for autoregressive models.
method Bayesian conditioning to draw samples subject to a constraint, considering the entire sequence and inducing a local, factorized distribution.
result Our approach generates samples that closely approximate the target distribution and are guaranteed to satisfy the constraints.
We consider the class of affine LIBOR models with multiple curves, which is an analytically tractable class of discrete tenor models that easily accommodates positive or negative interest rates and positive spreads. By introducing an interpolating function, we extend the affine LIBOR models to a continuous tenor and de…
We study discretizations of polynomial processes using finite state Markov processes satisfying suitable moment matching conditions. The states of these Markov processes together with their transition probabilities can be interpreted as Markov cubature rules. The polynomial property allows us to study such rules using …
We consider the problem of transforming samples from one continuous source distribution into samples from another target distribution. We demonstrate with optimal transport theory that when the source distribution can be easily sampled from and the target distribution is log-concave, this can be tractably solved with c…
Alternating minimization represents a widely applicable and empirically successful approach for finding low-rank matrices that best fit the given data. For example, for the problem of low-rank matrix completion, this method is believed to be one of the most accurate and efficient, and formed a major component of the wi…
Optimized variable orderings improve autoregressive model performance.
problem Challenges in variable ordering affect autoregressive model efficiency.
method Learn graphical model structure to inform optimal variable orderings.
result Graph-informed orderings yield higher-fidelity samples.
Gradient flows on distributions of distributions for machine learning tasks.
problem Designing gradient flows for datasets of probability distributions.
method Representing classes as conditional distributions, modeling datasets as mixture distributions, using Wasserstein over Wasserstein (WoW) distance and gradients.
result Demonstrated gradient flows for dataset transfer and distillation tasks.
New neural process models produce correlated predictions for better estimation tasks.
problem Need for models that can handle correlated predictions for tasks like weather forecasting.
method Developed new Neural Process models that can produce correlated predictions and support exact maximum likelihood training.
result Improved predictive performance on various experiments with synthetic and real data.
Fixed-parameter tractability of private synthetic data generation
problem Generating synthetic data under differential privacy
method Linear programming and subsampled private multiplicative weights method
result Optimal error rates across all regimes
Probabilistic models learned as density estimators can be exploited in representation learning beside being toolboxes used to answer inference queries only. However, how to extract useful representations highly depends on the particular model involved. We argue that tractable inference, i.e. inference that can be compu…
New findings on flatness for specific driftless systems.
problem Determining flatness for driftless systems with m inputs and 2m or 2m-1 states.
method Using pure prolongation, the paper presents new sufficient conditions for flatness.
result The conditions proposed broaden the class of recognized flat systems.
Quantitatively assessing relationships between latent variables and observed variables is important for understanding and developing generative models and representation learning. In this paper, we propose latent-observed dissimilarity (LOD) to evaluate the dissimilarity between the probabilistic characteristics of lat…
Proposes second-order Esscher transform for Lévy models in financial markets.
problem Risk management and quantification in markets with jumps and Lévy dynamics.
method Derives densities, equivalent measures, and pricing formulas for European call options.
result Option prices are bounded and monotonic with the second-order Esscher parameter.
New method identifies causal relationships in presence of hidden variables.
problem Identifying causal relationships when hidden variables exist.
method Established sufficient conditions and introduced a search algorithm.
result Proved soundness and completeness of the search algorithm.