The study tackles modeling high-frequency financial data using continuous distributions, finding them inadequate.
problem Challenges in modeling high-frequency integer price changes with continuous distributions.
method Proposed a modified maximum likelihood estimation procedure to account for the discreteness of high-frequency price changes.
result Traditional GARCH models are not suitable for high-frequency data due to the discreteness of price changes.
Researchers study the normalizing constant of a continuous categorical distribution.
problem Understanding the normalizing constant of the continuous categorical distribution.
method Characterize numerical behavior and present theoretical and methodological advances.
result The normalizing constant can be written in closed form using elementary functions.
Novel proof shows continuity of optimal transport feasible set mapping.
problem Continuity of feasible set mapping in optimal transport problems.
method Presented a novel and shorter proof of continuity.
result Established continuity of the feasible set mapping.
This paper develops sparse alternatives to continuous distributions, including new types of Gaussians and attention mechanisms.
problem Creating flexible continuous distributions with varying support for machine learning applications.
method Defining Ω-regularized prediction maps and Fenchel-Young losses for arbitrary domains, and deriving new types of Gaussians and attention mechanisms. result Sparse alternatives to continuous distributions, including deformed exponential families and β-Gaussians, are introduced. Develops a new method for learning discrete distributions without embedding them in a continuous space.
problem Challenges in learning discrete distributions using current methodologies.
method Introduces a MAD invertible map and a mixed variational flow (MAD Mix) for discrete distributions.
result MAD Mix produces more reliable approximations than continuous-embedding flows.
We solve continuous-time reinforcement learning using distributional Hamilton-Jacobi-Bellman equations.
problem Predicting the distribution of returns in continuous-time, stochastic environments.
method We derive a distributional Hamilton-Jacobi-Bellman equation for Itô diffusions and Feller-Dynkin processes, and propose an algorithm based on a JKO scheme.
result We propose an online control algorithm that can be used to approximately solve the distributional HJB equation.
New path-gradient estimator for continuous normalizing flows.
problem Limitation of simple Gaussian variational distributions in complex applications.
method Proposed a path-gradient estimator for continuous normalizing flows.
result Empirical evidence of superior performance of the new estimator.
Paper tackles overestimation bias in continuous control, improving performance by 25%.
problem Overestimation bias in off-policy learning.
method Truncated Quantile Critics (TQC) combines distributional representation, truncation, and ensembling of critics.
result TQC outperforms state-of-the-art methods by 25% on the Humanoid environment.
This work develops efficient methods for continuous-time distributional reinforcement learning.
problem Continuous-time reinforcement learning with return distributions.
method Parameterizing return distributions using quantile representation and showing topological properties.
result Efficient approximation algorithm for continuous-time distributional reinforcement learning.
Continuous functions on graphs in Carnot groups satisfy a Burgers' type equation.
problem Characterizing CH1-regularity of graphs in Carnot groups of step 2. method Proving equivalence between distributional solutions of Burgers' type equations and CH1-regularity of graphs. result Continuous functions on graphs in Carnot groups of step 2 satisfy a Burgers' type equation in the distributional sense.
SFSVI uses Gaussian mixtures to approximate neural network outputs for continual learning.
problem Learning new tasks without forgetting old ones in neural networks.
method Sequential function-space variational inference with Gaussian mixture approximation.
result Gaussian mixture SFSVI outperforms other methods in continual learning.
We identify a fundamental problem in policy gradient-based methods in continuous control. As policy gradient methods require the agent's underlying probability distribution, they limit policy representation to parametric distribution classes. We show that optimizing over such sets results in local movement in the actio…
Continuous-time distributed mirror descent with integral feedback converges to global optimum.
problem Distributed optimization of a global strongly convex function with local convex components.
method Continuous-time distributed mirror descent with integral feedback.
result Asymptotic convergence to global optimum with constant step-size.
Study on continuous sequence classification with distribution uncertainty.
problem Classifying continuous sequences with varying distribution uncertainty.
method Proposes distribution-free tests for three test designs: fixed-length, sequential, and two-phase tests.
result Error probabilities decay exponentially fast for all test designs.
Representations based on random walks can exploit discrete data distributions for clustering and classification. We extend such representations from discrete to continuous distributions. Transition probabilities are now calculated using a diffusion equation with a diffusion coefficient that inversely depends on the dat…
Monotone aggregation of dependent random vectors has an absolutely continuous distribution under certain conditions.
problem Monotone aggregation of dependent random vectors
method Coordinatewise monotonicity and uniform lower-increment conditions
result One-dimensional push-forwards of dependent random vectors have an absolutely continuous distribution
Study improves sample complexity for distinguishing continuous distributions and causal relationships.
problem Distinguishing continuous distributions and causal relationships in the presence of unobserved confounding.
method Proposed an estimator of KL divergence based on von Mises expansion for closeness testing.
result Established sample complexity guarantees for causal discovery in non-linear models with continuous variables and unobserved confounding.
COCOA can learn new tasks without forgetting previously learned ones in a distributed setting.
problem Continual learning with tasks arriving sequentially.
method Distributed optimization with COCOA algorithm.
result COCOA can perform continual learning without forgetting.
We present a framework for learning disentangled and interpretable jointly continuous and discrete representations in an unsupervised manner. By augmenting the continuous latent distribution of variational autoencoders with a relaxed discrete distribution and controlling the amount of information encoded in each latent…
A method models continuous-time glucose distributions in children with diabetes.
problem Capturing subtle temporal changes in glucose distributions.
method Probabilistic framework using Gaussian mixtures and neural ODEs.
result Detects treatment-related improvements in glucose dynamics.
Optimizes sampling in continuous domains by adjusting search distribution.
problem Improving sampling efficiency in continuous domains.
method Analyzes and refines the search distribution based on population size and dimension.
result Explicit values for reshaping the search distribution are provided.
Flow based models such as Real NVP are an extremely powerful approach to density estimation. However, existing flow based models are restricted to transforming continuous densities over a continuous input space into similarly continuous distributions over continuous latent variables. This makes them poorly suited for m…
Develops analysis of Hölder continuous mappings on Heisenberg groups.
problem Analyzing Hölder continuous mappings on Heisenberg groups.
method Theory of distributional Jacobians and pullbacks of differential forms.
result Simple proof of a generalization of the Gromov non-embedding theorem and new results about Hölder homotopy groups.
Continuous time framework for discrete data denoising models.
problem Efficient training and sampling for discrete data denoising models.
method Formulated as Continuous Time Markov Chains (CTMCs), efficient training using continuous time ELBO, high-dimensional CTMC simulation, novel theoretical error bound.
result Continuous time treatment enables novel theoretical error bound between generated and true data distributions.
We formulate a notion of (uniform) asymptotic involutivity and show that it implies (unique) integrability of corank-1 continuous distributions in dimensions three or less. This generalizes and extends a classical theorem of Frobenius Theorem which says that an involutive C^1 distribution is uniquely integrable.
Paper extends sparse alternatives to softmax for continuous domains, enabling efficient attention mechanisms.
problem Efficiently assigning zero probability to irrelevant categories in continuous domains.
method Extend alpha-entmax to continuous domains, introducing continuous-domain attention mechanisms.
result Continuous attention allows attending to time intervals and compact regions, improving text classification, machine translation, and visual question answering.
Modeling glucose distribution changes over time using neural ODEs.
problem Analyzing how continuous glucose distribution changes over time in diabetic patients.
method Combines Gaussian mixture, MMD, and Neural ODE to model temporal evolution of glucose distribution.
result Highly interpretable model detects subtle distribution shifts and remains computationally efficient.
Continuous semi-implicit models enable faster training and better performance in generative modeling.
problem Slow convergence in hierarchical semi-implicit models during training.
method CoSIM, a continuous semi-implicit model that incorporates a continuous transition kernel for efficient training.
result CoSIM achieves superior performance on image generation tasks compared to existing methods.
Bayesian approach models match and non-match score distributions over continuous covariates.
problem Complex evaluation of model performance over continuous covariates in biometric verification.
method Generative model of score distributions, mixture models, local basis functions, Bayesian inference.
result Accurate and effective method for studying model performance over continuous covariates.
New algorithm approximates continuous Wasserstein barycenters efficiently.
problem Computing Wasserstein barycenters for continuous distributions.
method Stochastic algorithm using dual potentials and stochastic gradient descent.
result Efficient online approximation of continuous Wasserstein barycenters.
Study non-asymptotic Langevin Monte Carlo for Gibbs distributions.
problem Sampling from Gibbs distributions with dissipative potentials.
method Langevin-type algorithms based on Liptser--Shiryaev theory and Poincaré inequalities.
result Upper bound on 2-Wasserstein distance for accurate approximation.
Unique continuation property for measures in high dimensions.
problem Understanding the structure of measures in high-dimensional spaces.
method Analyzing locally uniformly distributed measures and their supports.
result Locally uniformly distributed measures satisfy a unique continuation property.
Bayesian Federated Learning improves model reliability in dynamic environments.
problem Uncertainty quantification and robust adaptation in distributed learning.
method Proposes a continual BFL framework using SGLD for sequential updates and continual learning challenges.
result Continual Bayesian updates preserve knowledge and adapt to evolving data.
EWFM trains continuous flows with only energy evaluations, improving sample quality with fewer computations.
problem Efficiently sampling from complex, high-dimensional Boltzmann distributions using only energy evaluations.
method Energy-Weighted Flow Matching (EWFM) using importance sampling and iterative/annealed training.
result Improved sample quality with up to 3 orders of magnitude fewer energy evaluations compared to existing methods.
Generative models learn distributions of continuous functions.
problem Training generative models on discretized grids limits model size and data type.
method Parameterize data points by continuous functions, learn distributions over these functions.
result Models can learn rich distributions of functions independently of data type and resolution.
As energy markets begin clearing at sub-hourly rates, their interaction with load control systems becomes a potentially important consideration. A simple model for the control of thermal systems using market-based power distribution strategies is proposed, with particular attention to the behavior and dynamics of elect…
A new framework solves complex optimization problems with continuous worst-case distributions.
problem Optimizing under uncertain distributions with continuous worst-case scenarios.
method Flow-based distributionally robust optimization (DRO) with Wasserstein uncertainty sets and invertible transport maps.
result The framework finds continuous worst-case distributions and samples efficiently.
OSAMD adapts online to changing distributions with limited labels.
problem Models struggle with continual distribution shifts and expensive labeling in changing environments.
method Online Active Continual Adaptation with OSAMD, an online teacher-student structure and margin-based criterion.
result OSAMD achieves favorable dynamic regret bounds under changing environments with limited labels.
Simplex-valued data appear throughout statistics and machine learning, for example in the context of transfer learning and compression of deep networks. Existing models for this class of data rely on the Dirichlet distribution or other related loss functions; here we show these standard choices suffer systematically fr…
We propose a new sampling method, the thermostat-assisted continuously-tempered Hamiltonian Monte Carlo, for Bayesian learning on large datasets and multimodal distributions. It simulates the Nosé-Hoover dynamics of a continuously-tempered Hamiltonian system built on the distribution of interest. A significant advantag…
Study error bounds in evaluating distributional computational graphs.
problem Error analysis in evaluating graphs with inputs as probability distributions.
method Establish non-asymptotic error bounds using Wasserstein-1 distance.
result Non-asymptotic error bounds for discretization errors in distributional computational graphs.
Paper solves DRO for continuous distributions with iterative algorithms.
problem Distributionally robust optimization with continuous worst-case distributions.
method Iterative algorithm for global convergence, leveraging Brenier's theorem and JKO scheme.
result Achieves global convergence under mild assumptions for minimax problems.
Foster and Hart proposed an operational measure of riskiness for discrete random variables. We show that their defining equation has no solution for many common continuous distributions including many uniform distributions, e.g. We show how to extend consistently the definition of riskiness to continuous random variabl…
This paper finds a unique partition of a sample space for estimating continuous distributions.
problem Estimating continuous probability distributions from finite samples.
method Equal-probability partition of the sample space using order statistics.
result The partition yields an entropy of log2(N+1) bits, providing a discrete entropy estimate.
Continuous Sweep improves binary quantifier performance.
problem Estimating class prevalence in datasets.
method Parametric binary quantifier inspired by Median Sweep, using parametric class distributions and mean of Adjusted Count estimates.
result Continuous Sweep outperforms other quantifiers in simulations and empirical data analysis.
New algorithm estimates semi-continuous data density using entropy maximization.
problem Estimating density functions for semi-continuous data.
method Maximum entropy principle, requiring only constraint function samples.
result Estimate has significantly less bias compared to existing methods.
Two EM algorithms estimate prior distributions in mixture of linear regressions.
problem Estimating prior distributions in mixture of linear regressions.
method Two EM algorithms: one for continuous priors, one for discrete priors.
result Both algorithms accurately estimate prior distributions and the number of clusters.
EDICT learns evidential distributions for irregular time series, improving predictions and uncertainty quantification.
problem Challenges in predicting and characterizing uncertainty for irregular time series data.
method EDICT (Evidential Distributions for Irregular Time Series) learns a continuous-time evidential distribution.
result EDICT achieves competitive performance on time series classification tasks and provides better uncertainty quantification.