arXiv research

Improves SVGP methods for faster and more accurate Gaussian process inference.

Method converts neural networks to function space for better uncertainty quantification.

Data-driven optimization improves mean-variance portfolios by penalizing norms.

Study describes singularities of height functions on specific singular surfaces.

Optimizes wireless network resource management with state-augmented policies.

Learning optimal resource allocation policies in wireless systems can be effectively achieved by formulating finite dimensional constrained programs which depend on system configuration, as well as the adopted learning parameterization. The interest here is in cases where system models are unavailable, prompting method…

Generalizing some results from R. Leung's thesis, we compute, in rational cohomology, the Poincare dual of the degeneracy locus of the family of Dirac operators parameterized by the moduli space of projectively anti-self-dual $\SO(3)$ connections. This is the first step in a program to derive a relation between the Don…

The paper improves Gaussian process models for efficient batch optimization.

It is well known that quantifying uncertainty in the action-value estimates is crucial for efficient exploration in reinforcement learning. Ensemble sampling offers a relatively computationally tractable way of doing this using randomized value functions. However, it still requires a huge amount of computational resour…

A machine learning model for PMD compensation in dual-polarization systems.

Graph neural networks optimize radio resource management policies for wireless networks.

This paper considers the design of optimal resource allocation policies in wireless communication systems which are generically modeled as a functional optimization problem with stochastic constraints. These optimization problems have the structure of a learning problem in which the statistical loss appears as a constr…

A new method converts neural networks to function space for scalable sequential learning.

Dual-objective GANs reduce training instabilities with tunable α-loss parameters.

This paper is concerned with the construction of special metrics on non-compact 4-manifolds which arise as resolutions of complex orbifold singularities. Our study is close in spirit to the construction of the hyperkaehler gravitational instantons, but we focus on a different class of singularities. We show that any re…

The important application of semi-static hedging in financial markets naturally leads to the notion of quasi self-dual processes. The focus of our study is to give new characterizations of quasi self-duality for exponential Lévy processes such that the resulting market does not admit arbitrage opportunities. We derive …

We describe a new approach to the problem of constructing gluing parameterizations for open neighborhoods of boundary points of moduli spaces of anti-self-dual connections over closed four-dimensional manifolds. Our approach employs general results from differential topology for $C^1$ maps of smooth Banach manifolds wi…

This study explores star-shaped regularizers learned from critic-based losses.

We present GradientDICE for estimating the density ratio between the state distribution of the target policy and the sampling distribution in off-policy reinforcement learning. GradientDICE fixes several problems of GenDICE (Zhang et al., 2020), the state-of-the-art for estimating such density ratios. Namely, the optim…

CardiCat generates synthetic data for high-cardinality tabular datasets.

A submanifold of a Riemannian symmetric space is called parallel if its second fundamental form is a parallel section of the appropriate tensor bundle. We classify parallel submanifolds of the Grassmannian $\rmG^+_2(\R^{n+2})$ which parameterizes the oriented 2-planes of the Euclidean space $\R^{n+2}$\,. Our main resul…

Paper analyzes how neural networks learn from a teacher in a specific setting.

A new method uses deep learning for optimal stopping problems.

Optimal Morse matchings reveal essential structures of cell complexes which lead to powerful tools to study discrete geometrical objects, in particular discrete 3-manifolds. However, such matchings are known to be NP-hard to compute on 3-manifolds, through a reduction to the erasability problem. Here, we refine the stu…

Extends Lannes-Quillen theorem to all profinite groups.

Dual Space Preconditioning speeds up gradient descent in overparameterized models.

DeepMartingale uses deep learning to solve complex optimal stopping problems efficiently.

The paper explores algorithms to transform 3-manifold triangulations while controlling sparsity.

A generalized cusp $C$ is diffeomorphic to $[0,\infty)$ times a closed Euclidean manifold. Geometrically $C$ is the quotient of a properly convex domain by a lattice, $Γ$, in one of a family of affine groups $G(ψ)$, parameterized by a point $ψ$ in the (dual closed) Weyl chamber for $SL(n+1,\mathbb{R})$, and $Γ$ determi…

The paper introduces various canonical parameterizations for 2D-curved shapes.

There are currently two parameterizations used to derive fixed kernels corresponding to infinite width neural networks, the NTK (Neural Tangent Kernel) parameterization and the naive standard parameterization. However, the extrapolation of both of these parameterizations to infinite width is problematic. The standard p…

New method uses LP to achieve optimal sample complexity in multi-agent reinforcement learning.

New algorithm reduces kernel optimization complexity.

New parameterization for $(1,1)$-knots simplifies their study.

APAC-Net solves high-dimensional stochastic MFGs using neural networks.

Stochastic parameterizations account for uncertainty in the representation of unresolved sub-grid processes by sampling from the distribution of possible sub-grid forcings. Some existing stochastic parameterizations utilize data-driven approaches to characterize uncertainty, but these approaches require significant str…

The current paper discusses some new results about conformal polynomic surface parameterizations. A new theorem is proved: Given a conformal polynomic surface parameterization of any degree it must be harmonic on each component. As a first geometrical application, every surface that admits a conformal polynomic paramet…

Polynomially parameterizes knots and spheres, proving analogous results.

Conformal surface parameterization is useful in graphics, imaging and visualization, with applications to texture mapping, atlas construction, registration, remeshing and so on. With the increasing capability in scanning and storing data, dense 3D surface meshes are common nowadays. While meshes with higher resolution …

Two novel algorithms for conformal parameterization of multiply-connected surfaces.

The paper analyzes how over-parameterization affects GD convergence in matrix sensing problems.

Novel framework for policy optimization with general parameterization and linear convergence.

We introduce a new parameterization method for deep learning layers using spectral tensor train decomposition.

State-augmented algorithm optimizes wireless network resource management.

This paper presents a novel two-step approach for the fundamental problem of learning an optimal map from one distribution to another. First, we learn an optimal transport (OT) plan, which can be thought as a one-to-many map between the two distributions. To that end, we propose a stochastic dual approach of regularize…

Develops a method for conformal parameterization of point clouds without fixed boundaries.

We study the space of conformal immersions of a 2-torus into the 4-sphere. The moduli space of generalized Darboux transforms of such an immersed torus has the structure of a Riemann surface, the spectral curve. This Riemann surface arises as the zero locus of the determinant of a holomorphic family of Dirac type opera…

Point cloud is the most fundamental representation of 3D geometric objects. Analyzing and processing point cloud surfaces is important in computer graphics and computer vision. However, most of the existing algorithms for surface analysis require connectivity information. Therefore, it is desirable to develop a mesh st…