Expands newsvendor model with moment constraints using Wasserstein distance.
problem Optimizing order quantity under distributional ambiguity.
method Formulates infinite dimensional primal problem, derives finite dimensional dual problem using problem of moments duality.
result Distributional ambiguity affects optimal order quantity and profits/costs.
New proof of Sobolev inequality with constraints on sphere.
problem Improving Sobolev inequality on sphere with constraints.
method Careful study of extremal problem on sphere.
result Explicit determination of constant in second order moments case.
Sharp inequalities in unit ball with constraints on moments.
problem Establishing Sobolev trace inequalities with constraints.
method Constructing smooth test functions for higher order moments.
result Almost optimal Sobolev trace inequalities for 2nd and 4th orders.
Method estimates posterior model for boundary value problems with uncertain constraints.
problem Estimating posterior probability model for stochastic boundary value problems with uncertain constraints.
method Probabilistic learning inference using Kullback-Leibler divergence and MCMC.
result Method successfully estimates posterior probability measure with constraints.
Optimal Transport (OT) problems arise in a wide range of applications, from physics to economics. Getting numerical approximate solution of these problems is a challenging issue of practical importance. In this work, we investigate the relaxation of the OT problem when the marginal constraints are replaced by some mome…
New inequality criterion for a mean field equation on spheres.
problem Finding uniqueness in a mean field equation on spheres.
method Established a new Moser-Trudinger-Onofri inequality with a constraint on moments deviation.
result A threshold for deviation is a uniqueness criterion for the mean field equation.
We present and analyze a central cutting surface algorithm for general semi-infinite convex optimization problems, and use it to develop a novel algorithm for distributionally robust optimization problems in which the uncertainty set consists of probability distributions with given bounds on their moments. Moments of a…
MGD combines maximum entropy and diffusion methods for efficient sampling.
problem Generating samples from limited information in high dimensions.
method Moment Guided Diffusion (MGD) using stochastic differential equations.
result MGD efficiently samples maximum entropy distributions in finite time.
Paper finds robust Λ-quantiles equal to extremal distributions.
problem Investigating robust models for Λ-quantiles with partial loss information. method Extending classical quantiles using Λ-quantiles and applying results from robust quantiles. result Robust Λ-quantiles equal to Λ-quantiles of extremal distributions. The paper analyzes extreme risk measures with limited distributional information.
problem Investigating risk measures under partial knowledge of distribution moments and shape.
method Employing probability inequalities and modified Schwarz inequality to derive bounds on distortion risk measures.
result Unified framework for calculating best- and worst-case scenarios of distortion risk measures.
We show how to compute lower bounds for the supremum Bayes error if the class-conditional distributions must satisfy moment constraints, where the supremum is with respect to the unknown class-conditional distributions. Our approach makes use of Curto and Fialkow's solutions for the truncated moment problem. The lower …
Exact simulation of correlated binary outcomes using PMF constraints and linear programming.
problem Simulating dependent Bernoulli outcomes with specific means and correlations.
method Formulate the problem over the joint Bernoulli PMF, impose constraints, and solve as a linear program. Use convex-hull characterization and truncated-moment completion scheme for feasibility and simulation.
result Exact simulation framework for correlated binary outcomes, providing a convex-hull characterization and truncated-moment completion scheme.
MOMENT selects and estimates mixed-effects models using moment identities.
problem Selecting and estimating random-effects covariance matrix and fixed-effects coefficients in multiresponse linear mixed-effects models.
method MOMENT is a stage-wise moment-based framework that reduces the random-effects selection problem to a smooth constrained convex optimization problem.
result MOMENT performs competitively and can outperform separate univariate analyses for correlated responses.
The paper refines and generalizes worst-case law invariant convex risk measures.
problem Developing robust convex risk measures under uncertainty sets.
method Generalizing closed forms for worst-case law invariant convex risk measures with uncertainty sets based on norms and moment constraints.
result Explicit closed forms for convex risk measures are developed and assessed through numerical simulations.
A classical result of Aubin states that the constant in Moser-Trudinger-Onofri inequality on S2 can be imporved for furnctions with zero first order moments of the area element. We generalize it to higher order moments case. These new inequalities bear similarity to a sequence of Lebedev-Milin type inequa…
We present an objective function for learning with unlabeled data that utilizes auxiliary expectation constraints. We optimize this objective function using a procedure that alternates between information and moment projections. Our method provides an alternate interpretation of the posterior regularization framework (…
Develops a new method for estimating models with conditional moment restrictions.
problem Estimating models with conditional moment restrictions, especially non-parametric instrumental variable regression.
method Introduces a min-max criterion function to solve a zero-sum game between modeler and adversary, analyzing estimation rates for various hypothesis spaces.
result Shows that with regularization and rich test function spaces, estimation rates scale with the critical radius of hypothesis and test function spaces.
New algorithm for risk-sensitive reinforcement learning with natural policy gradients.
problem Risk-sensitive reinforcement learning with downside risk constraints.
method Introduce a new Bellman equation to estimate the lower partial moment of returns, use natural policy gradients, and extend Reward Constrained Policy Optimization.
result Sample-efficient estimation of partial moments and effective risk-sensitive control.
A novel method for learning DAGs from positive-valued data.
problem Causal discovery from observational data of positive-valued variables.
method Hybrid Moment-Ratio Scoring (H-MRS) algorithm combining moment-based scoring and log-scale regression.
result H-MRS integrates log-scale Ridge regression for moment-ratio estimation with a greedy ordering procedure based on raw-scale moment ratios, followed by Elastic Net-based parent selection.
This is an introduction to the author's recent work on constrained systems. Firstly, a generalization of the Marsden-Weinstein reduction procedure in symplectic geometry is presented - this is a reformulation of ideas of Mikami-Weinstein and Xu. Secondly, it is shown how this procedure is quantized by Rieffel induction…
Entropy based ideas find wide-ranging applications in finance for calibrating models of portfolio risk as well as options pricing. The abstracted problem, extensively studied in the literature, corresponds to finding a probability measure that minimizes relative entropy with respect to a specified measure while satisfy…
Lasso method applied to polynomial models with hierarchy constraints.
problem Estimating parameters in polynomial models with hierarchy constraints.
method Using lasso and standard quadratic programming techniques to estimate parameters.
result The proposed methodology outperforms existing techniques in terms of validation error and model size.
In this paper we study a robust expected utility maximization problem with random endowment in discrete time. We give conditions under which an optimal strategy exists and derive a dual representation for the optimal utility. Our approach is based on a general representation result for monotone convex functionals, a fu…
Researchers develop a method to generate diffusion-based samples from a tilted distribution.
problem Generating samples from a distribution that has been tilted by a parameter.
method Developed a plug-in estimator and proved Wasserstein bounds and TV-accuracy under certain conditions.
result The method is minimax-optimal and can be applied in various domains like finance and climate modeling.
Proposes a method to use external machine-learning predictions in multinomial logistic regression.
problem Improving statistical inference using summary-level external machine-learning predictions.
method Empirical-likelihood framework incorporating moment constraints from external nonparametric machine-learning predictions.
result Fused estimator achieves strict efficiency gain over primary-only estimator under mild conditions.
The paper studies K-stability of spherical varieties and their degenerations.
problem Understanding K-stability and degenerations of polarized spherical varieties.
method Reduction to a variational problem on the moment polytope, convexity constraint, and solving the HMA equation.
result Determines strict semistability and polystable degenerations for Fano spherical varieties of rank two.
New stability framework relaxes boundedness assumptions for generalization bounds.
problem Overly restrictive assumptions for modern learning settings with heavy-tailed or unbounded losses.
method Develops a stability-based framework requiring only finite Lp moment conditions. result Sharp generalization bounds derived for various learning paradigms.
The ability of many powerful machine learning algorithms to deal with large data sets without compromise is often hampered by computationally expensive linear algebra tasks, of which calculating the log determinant is a canonical example. In this paper we demonstrate the optimality of Maximum Entropy methods in approxi…
A new portfolio optimization method using the Sherman-Morrison identity.
problem Portfolio optimization with covariance and variance.
method Sherman-Morrison identity applied to replace covariance with second moment matrix.
result Sherman-Morrison-Markowitz portfolio solves standard portfolio optimization problems.
New approach to optimal dividend timing with limited payouts.
problem Optimal timing of dividends with a constraint on the number of payouts.
method Developed a new type of time-inconsistent stochastic impulse control problem, derived the optimal solution in the precommitment sense, and formulated it as a sequential dynamic game.
result An equilibrium strategy derived for the problem, showing strong subgame perfect Nash equilibrium.
Econophysics, is based on the premise that some ideas and methods from physics can be applied to economic situations. We intend to show in this paper how a physics concept such as entropy can be applied to an economic problem. In so doing, we demonstrate how information in the form of observable data and moment constra…
Canary optimizes VaR-constrained RL problems with a conservative bound using Cantelli's inequality.
problem Optimizing reinforcement learning policies under VaR constraints in dense cost regimes.
method Employing Cantelli's inequality to create a conservative and smooth bound on VaR constraints based on moments of cost returns. Extending trust-region framework for worst-case bounds on policy improvement and constraint violation.
result Canary reliably satisfies VaR constraints with fewest violations and earliest permanent satisfaction, while maintaining reward competitiveness.
The study finds dense clusters of solutions in a simple neural network model, providing bounds for their existence.
problem Exploring the existence of minimizers in a simple neural network model with binary weights.
method Formulating the learning problem as a constraint satisfaction problem and computing moment bounds for the existence of solutions.
result First rigorous steps toward proving the existence of dense clusters of solutions in certain parameter regimes.
This paper compares VaR estimation methods under tail misspecification, finding importance sampling underestimates VaR.
problem Tail misspecification in VaR estimation.
method Importance sampling and moment-based VaR bracketing.
result Importance sampling underestimates VaR under heavy-tailed returns, while moment-based methods are robust.
The majority of stylized facts of financial time series and several Value-at-Risk measures are modeled via univariate or multivariate GARCH processes. It is not rare that advanced GARCH models fail to converge for computational reasons, and a usual parsimonious approach is the GJR-GARCH model. There is a disagreement i…
Proposes a method to identify elements in a skewness matrix for multivariate skew-elliptical distributions.
problem Label switching issue in Bayesian estimation of skewness matrix.
method Imposes a positive lower-triangular constraint and uses Bayesian sparse estimation with horseshoe prior.
result Successfully estimates the true structure of skewness dependency.
Optimizing rewards under budget constraints with correlated costs and rewards.
problem Maximizing total expected reward under a budget constraint on total cost with correlated and potentially heavy-tailed cost-reward pairs.
method Proposes algorithms exploiting correlation between cost and reward via linear minimum mean-square error estimation to achieve tight regret bounds.
result Achieves O(logB) regret for a budget B>0 under certain moment conditions. VaR-CPO optimizes VaR-constrained RL problems with conservative policy updates.
problem Optimizing VaR-constrained reinforcement learning problems.
method Combines Cantelli's inequality and trust-region framework for efficient and conservative optimization.
result Achieves zero constraint violations during training in feasible environments.
Extends probabilistic approach for Kahler-Einstein metrics on Fano manifolds.
problem Constructing Kahler-Einstein metrics on log Fano manifolds with non-discrete automorphism groups.
method Introduces Gibbs polystability and uses moment map constraint to break symmetry.
result Gibbs polystability conjectured to be equivalent to existence of Kahler-Einstein metric.
Suppose k centers are fit to m points by heuristically minimizing the k-means cost; what is the corresponding fit over the source distribution? This question is resolved here for distributions with p≥4 bounded moments; in particular, the difference between the sample cost and distribution cost decays with $…
Enhances flexibility in data reweighting with optimal transport and maximum entropy principles.
problem Adapting empirical distributions to predefined constraints on moments, tail behavior, etc.
method Nonparametric distributional constraints, maximum entropy principle, optimal transport.
result Maximum entropy weight adjusted empirical distribution close to a specified distribution in optimal transport metric.
Unsupervised estimation of latent variable models is a fundamental problem central to numerous applications of machine learning and statistics. This work presents a principled approach for estimating broad classes of such models, including probabilistic topic models and latent linear Bayesian networks, using only secon…
Generative Adversarial Networks (GANs) are powerful models for learning complex distributions. Stable training of GANs has been addressed in many recent works which explore different metrics between distributions. In this paper we introduce Fisher GAN which fits within the Integral Probability Metrics (IPM) framework f…
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.
Consider a random vector with finite second moments. If its precision matrix is an M-matrix, then all partial correlations are non-negative. If that random vector is additionally Gaussian, the corresponding Markov random field (GMRF) is called attractive. We study estimation of M-matrices taking the role of inverse sec…
Bayesian models use hyperparameters to indirectly assign priors, and this work shows how these priors can be derived from maximum entropy principles.
problem Understanding the assumptions and dependencies in Bayesian hierarchical models.
method Demonstrates how canonical distributions and maximum entropy principles can be used to derive marginal priors in hierarchical models.
result Marginal priors in hierarchical models derived from maximum entropy principles have different constraints compared to the original priors.
New algorithm samples constrained distributions efficiently.
problem Sampling from distributions with statistical constraints.
method Primal-dual Langevin Monte Carlo (PD-LMC) using gradient descent-ascent dynamics.
result PD-LMC algorithm successfully samples constrained distributions.
Unified framework for DRO using OT with constraints.
problem Handling ambiguity in likelihood ratios and outcomes.
method Unified framework leveraging optimal transport with conditional moment constraints.
result Unified approach enables adversarial perturbation of likelihood ratios and outcomes.