arXiv research

Stabilized neural differential equations enforce constraints on dynamical systems.

Algorithm samples constrained stochastic differential equations.

Differentially private algorithms for submodular maximization under various constraints.

Algorithm ensures privacy while strictly adhering to constraints.

New DAG constraints improve differentiable DAG learning.

PNDEs project neural dynamics onto constraint manifolds, improving accuracy and stability.

HardCoRe-NAS finds fitting neural networks adhering to hard resource constraints.

Solvable structures are exploited in order to find families of explicit solutions to evolution PDEs admitting suitable differential constraints. The effectiveness of the method is verified on several explicit examples.

New method for linear connections in ODEs with constraints.

Paper tackles nonparametric classification with privacy constraints, achieving optimal accuracy.

We show that many machine learning goals, such as improved fairness metrics, can be expressed as constraints on the model's predictions, which we call rate constraints. We study the problem of training non-convex models subject to these rate constraints (or any non-convex and non-differentiable constraints). In the non…

Improved sampling from Gaussian distributions with privacy constraints.

New principle for optimal control with higher order differential constraints.

Geometric theory explains substitutability in market outcomes based on production constraints.

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

Framework for robust decision making in changing environments with privacy constraints.

Study binary hypothesis testing with privacy and communication constraints.

Paper studies optimal federated learning for nonparametric regression with privacy constraints.

HardNet adds hard constraints to neural networks without sacrificing performance.

New policy minimizes error in finding best arm with privacy constraints.

Many methods for reducing and simplifying differential equations are known. They provide various generalizations of the original symmetry approach of Sophus Lie. Plenty of relations between them have been noticed and in this note a unifying approach will be discussed. It is rather close to the classical differential co…

The paper solves a consumption-investment problem with state-dependent lower bounds.

Solves second-order PDEs using quotients and differential invariants.

This paper considers utility indifference valuation of derivatives under model uncertainty and trading constraints, where the utility is formulated as an additive stochastic differential utility of both intertemporal consumption and terminal wealth, and the uncertain prospects are ranked according to a multiple-priors …

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

Study on surfaces in Heisenberg group with constant mean curvature.

New methods reduce computational cost for Gaussian Markov Random Fields with sparse constraints.

We consider the problem of learning Markov Random Fields (including the prototypical example, the Ising model) under the constraint of differential privacy. Our learning goals include both structure learning, where we try to estimate the underlying graph structure of the model, as well as the harder goal of parameter l…

COSMO learns DAG structure without acyclicity constraints.

New method combines gradient optimization with constraint-based techniques for causal discovery.

Reduces Lie (bi-)algebroids and Dirac manifolds using constraint vector bundles.

New method for private learning with fairness constraints.

Extends compactness theory to variable-coefficient pseudo-differential operators on manifolds.

Optimization on manifolds is a class of methods for optimization of an objective function, subject to constraints which are smooth, in the sense that the set of points which satisfy the constraints admits the structure of a differentiable manifold. While many optimization problems are of the described form, technicalit…

Solves optimal stopping problem with Poisson constraints using jumps.

Data processing inequalities link Fisher information to local differential privacy constraints.

We consider $n$ risk-averse agents who compete for liquidity in an Almgren--Chriss market impact model. Mathematically, this situation can be described by a Nash equilibrium for a certain linear-quadratic differential game with state constraints. The state constraints enter the problem as terminal boundary conditions f…

Survey of Gaussian process constraints for modeling expensive data.

A novel controller for wheeled robots handles joystick inputs for smooth steering.

New method estimates discrete distributions while protecting privacy.

Paper addresses FL over MAC with DP constraints, proposing a novel consensus scheme.

The concept of $\Zn$-supermanifold has been recently proposed as a natural generalization of classical ($\Zs$-graded) supergeometry, allowing for more complicated commutativity constraints. Here we continue the study of $\Zn$-supergeometry by developing the foundations of differential calculus on $\Zn$-supermanifolds.

Neural networks can approximate complex stochastic equations well.

The ``classical BRST construction'' as developed by Batalin-Fradkin-Vilkovisky is a homological construction for the reduction of the Poisson algebra $P = C^\infty (W)$ of smooth functions on a Poisson manifold $W$ by the ideal $I$ of functions which vanish on a constraint locus. This ideal is called first class if $I$…

Paper studies federated nonparametric testing with privacy constraints, achieving optimal rates and adaptive testing.

Finding anonymization mechanisms to protect personal data is at the heart of recent machine learning research. Here, we consider the consequences of local differential privacy constraints on goodness-of-fit testing, i.e. the statistical problem assessing whether sample points are generated from a fixed density $f_0$, o…

We suggest ways to enforce given constraints in the output of a Generative Adversarial Network (GAN) generator both for interpolation and extrapolation (prediction). For the case of dynamical systems, given a time series, we wish to train GAN generators that can be used to predict trajectories starting from a given ini…

Study discretizes Dirac and port-Hamiltonian systems using manifolds.