arXiv research

OLLA framework efficiently samples from constrained distributions with nonconvex constraints.

The paper introduces MU for NMF with $β$-divergences and disjoint constraints.

Paper studies PSGD for constrained optimization problems and its statistical properties.

Eigen-decomposition simplifies quadratic programming with equality constraints.

Detects causal scenarios with inequality constraints among classical correlations.

Proposes a new algorithm for solving optimization problems with stochastic objectives and equality constraints.

Develops spherical density-equalizing maps for closed surfaces.

We introduce a novel generative formulation of deep probabilistic models implementing "soft" constraints on their function dynamics. In particular, we develop a flexible methodological framework where the modeled functions and derivatives of a given order are subject to inequality or equality constraints. We then chara…

This work is a further study on the Generalized Constraint Neural Network (GCNN) model [1], [2]. Two challenges are encountered in the study, that is, to embed any type of prior information and to select its imposing schemes. The work focuses on the second challenge and studies a new constraint imposing scheme for equa…

Paper finds robust $Λ$-quantiles equal to extremal distributions.

An algorithm solves optimization problems with large sample sets, improving worst-case complexity.

Paper tackles efficient SGD methods for constrained bilevel optimization.

The distributional category bounds manifold invariants and imposes constraints.

A new algorithm solves constrained optimization problems with stochastic gradients.

A new bias score method optimizes fairness in classification.

Improved greedy 2-coordinate updates for optimization problems with constraints.

Doubly fair dynamic pricing ensures equal prices for different groups over time.

Unified framework for constrained diffusion models on nonconvex sets with efficient landing mechanism.

Investigates portfolio optimization with and without gearing constraints.

Method solves complex optimization problems with high probability bounds.

Proposes a fair classification model using Wasserstein ambiguity sets.

We study an online classification problem with partial feedback in which individuals arrive one at a time from a fixed but unknown distribution, and must be classified as positive or negative. Our algorithm only observes the true label of an individual if they are given a positive classification. This setting captures …

We consider settings in which the right notion of fairness is not captured by simple mathematical definitions (such as equality of error rates across groups), but might be more complex and nuanced and thus require elicitation from individual or collective stakeholders. We introduce a framework in which pairs of individ…

The paper proposes a method to measure fairness through equality of effort using algorithmic recourse.

The study of fairness in intelligent decision systems has mostly ignored long-term influence on the underlying population. Yet fairness considerations (e.g. affirmative action) have often the implicit goal of achieving balance among groups within the population. The most basic notion of balance is eventual equality bet…

New algorithms reduce complexity for solving nonconvex optimization problems with stochastic objectives and constraints.

Proposes a Gaussian process model for constrained dynamics learning.

DC3 uses deep learning to solve hard-constrained optimization problems efficiently.

Houdini finds high-dimensional saddle points under few constraints.

Method flattens complex surfaces with consistent density and shape.

c-lasso is a Python tool for robust and sparse regression with linear constraints.

New rigidity result for fat bundles with equal vertical curvatures.

We address the problem of solving convex optimization problems with many convex constraints in a distributed setting. Our approach is based on an extension of the alternating direction method of multipliers (ADMM) that recently gained a lot of attention in the Big Data context. Although it has been invented decades ago…

Paper proposes a new method to find approximate SOSP for nonconvex constrained optimization problems.

Fair machine learning models can be vulnerable to adversarial attacks that reduce their accuracy and fairness.

Study risk aggregation with order constraint under unknown dependence.

The paper finds the unique minimizer of area for hyperbolic bodies with curvature constraints.

Study on harmonic maps from surfaces to homogeneous spaces, focusing on bubble formation and geometric constraints.

Multiple fairness constraints have been proposed in the literature, motivated by a range of concerns about how demographic groups might be treated unfairly by machine learning classifiers. In this work we consider a different motivation; learning from biased training data. We posit several ways in which training data m…

Develops methods for fair classification under linear disparity constraints.

Simplifies neural network constraints with computationally efficient method.

An augmented Lagrangian (AL) can convert a constrained optimization problem into a sequence of simpler (e.g., unconstrained) problems, which are then usually solved with local solvers. Recently, surrogate-based Bayesian optimization (BO) sub-solvers have been successfully deployed in the AL framework for a more global …

In classification models fairness can be ensured by solving a constrained optimization problem. We focus on fairness constraints like Disparate Impact, Demographic Parity, and Equalized Odds, which are non-decomposable and non-convex. Researchers define convex surrogates of the constraints and then apply convex optimiz…

We demonstrate how easy it is for modern machine-learned systems to violate common deontological ethical principles and social norms such as "favor the less fortunate," and "do not penalize good attributes." We propose that in some cases such ethical principles can be incorporated into a machine-learned model by adding…

New method for private learning with fairness constraints.

DiffSlack learns neural networks with nonlinear constraints via learnable slack variables.

New method discovers causal relationships in confounded systems.

Hidden variables are ubiquitous in practical data analysis, and therefore modeling marginal densities and doing inference with the resulting models is an important problem in statistics, machine learning, and causal inference. Recently, a new type of graphical model, called the nested Markov model, was developed which …