arXiv research

Consistent algorithms for multiclass learning with complex metrics and constraints.

New framework improves generative models with prediction and consistency constraints.

Dynamic submodular maximization with consistency constraints.

Paper proves conditions for estimating precision matrices with Laplacian constraints.

Paper introduces new regression methods for consistent estimation of biophysical parameters.

Improved diffusion models for inverse problems by integrating data consistency constraints.

A new method SLIDE ensures fairness in AI models.

Proposes a method to improve hierarchical clustering using set-level structural priors.

We describe a new technique for computing lower-bounds on the minimum energy configuration of a planar Markov Random Field (MRF). Our method successively adds large numbers of constraints and enforces consistency over binary projections of the original problem state space. These constraints are represented in terms of …

Continuous-time model shows insider trading constraints impact market dynamics.

Subbagging estimation for big data reduces memory usage while maintaining statistical consistency.

Study financial contracts pricing in markets with nonproportional costs and constraints.

This paper deals with sparse feature selection and grouping for classification and regression. The classification or regression problems under consideration consists in minimizing a convex empirical risk function subject to an $\ell^1$ constraint, a pairwise $\ell^\infty$ constraint, or a pairwise $\ell^1$ constraint. …

New framework for consistent submodular maximization with insertions and deletions.

Proposes a new method for rank-consistent ordinal regression without weight-sharing constraints.

We derive a new model for pre-strained thin films, which consists of minimizing a biharmonic energy of deformations $v\in W^{2,2}$ satisfying the Monge-Ampère constraint $\det\nabla^2v = f$. We further discuss multiplicity properties of the minimizers of this model, in some special cases.

This paper studies the problem of optimal investment with CRRA (constant, relative risk aversion) preferences, subject to dynamic risk constraints on trading strategies. The market model considered is continuous in time and incomplete. the prices of financial assets are modeled by Itô processes. The dynamic risk constr…

The discrete-time mean-variance portfolio selection formulation, a representative of general dynamic mean-risk portfolio selection problems, does not satisfy time consistency in efficiency (TCIE) in general, i.e., a truncated pre-committed efficient policy may become inefficient when considering the corresponding trunc…

Meta-gradient D4PG optimizes performance and constraint adherence in RL.

We consider stationary autoregressive processes with coefficients restricted to an ellipsoid, which includes autoregressive processes with absolutely summable coefficients. We provide consistency results under different norms for the estimation of such processes using constrained and penalized estimators. As an applica…

The extended constraint equations arise as a special case of the conformal constraint equations that are satisfied by an initial data hypersurface $Z$ in an asymptotically simple spacetime satisfying the vacuum conformal Einstein equations developed by H. Friedrich. The extended constraint equations consist of a quasi-…

Consistent spectral clustering with fairness constraints on representation graphs.

Dual decomposition provides a tractable framework for designing algorithms for finding the most probable (MAP) configuration in graphical models. However, for many real-world inference problems, the typical decomposition has a large integrality gap, due to frustrated cycles. One way to tighten the relaxation is to intr…

Improved unsupervised probing for ranking tasks using Contrast-Consistent Ranking.

A framework estimates categorical distributions under constraints, ensuring generality and uniqueness.

New method learns BN structures from data efficiently.

SnareNet adds repair layers to neural networks to ensure outputs meet physical constraints.

This work proposes an online learning approach to tighten constraints in stochastic control problems.

This paper considers online convex optimization over a complicated constraint set, which typically consists of multiple functional constraints and a set constraint. The conventional online projection algorithm (Zinkevich, 2003) can be difficult to implement due to the potentially high computation complexity of the proj…

Paper develops a privacy-preserving nonparametric regression method.

New method finds balanced clusters in graphs using auxiliary information.

An important form of prior information in clustering comes in form of cannot-link and must-link constraints. We present a generalization of the popular spectral clustering technique which integrates such constraints. Motivated by the recently proposed $1$-spectral clustering for the unconstrained problem, our method is…

New loss function handles uncertain constraints in CSLO problems.

Comonotonic allocations are restored under certain constraints, improving risk-sharing.

We examine overlapping clustering schemes with functorial constraints, in the spirit of Carlsson--Memoli. This avoids issues arising from the chaining required by partition-based methods. Our principal result shows that any clustering functor is naturally constrained to refine single-linkage clusters and be refined by …

The paper optimizes investment strategies with constraints for life-cycle models.

The paper classifies constraint mappings in optimization problems.

We propose a technique for declaratively specifying strategies for semi-supervised learning (SSL). The proposed method can be used to specify ensembles of semi-supervised learning, as well as agreement constraints and entropic regularization constraints between these learners, and can be used to model both well-known h…

The paper optimizes pension policies with guarantees and sustainability constraints.

We address the problem of algorithmic fairness: ensuring that sensitive variables do not unfairly influence the outcome of a classifier. We present an approach based on empirical risk minimization, which incorporates a fairness constraint into the learning problem. It encourages the conditional risk of the learned clas…

Algorithm safely learns from sub-optimal baseline policies while satisfying constraints.

Framework generates precise synthetic populations for scalable modeling.

When the vacuum Einstein equations are cast in the form of hamiltonian evolution equations, the initial data lie in the cotangent bundle of the manifold MΣ of riemannian metrics on a Cauchy hypersurface Σ. As in every lagrangian field theory with symmetries, the initial data must satisfy constraints. But, unlike those …

Recent GAN-based architectures have been able to deliver impressive performance on the general task of image-to-image translation. In particular, it was shown that a wide variety of image translation operators may be learned from two image sets, containing images from two different domains, without establishing an expl…

We construct solutions of the constraint equation with non constant mean curvature on an asymptotically hyperbolic manifold by the conformal method. Our approach consists in decreasing a certain exponent appearing in the equations, constructing solutions of these sub-critical equations and then in letting the exponent …

Paper optimizes federated PCA for covariance estimation under privacy constraints.

A new framework for knowledge graph embedding using sheaves.

We discuss the portfolio optimization problem with the obligatory deposits constraint. Recently it has been shown that as a consequence of this nonlinear constraint, the solution consists of an exponentially large number of optimal portfolios, completely different from each other, and extremely sensitive to any changes…