arXiv research

Proves a function's locally least gradient property if its level sets are minimal laminations.

Paper presents a robust transfer learning method for active level set estimation.

Novel method for bilevel optimization with convex lower-level problem.

BDMBC clusters data with varying densities using a new PLLS measure.

New algorithms solve complex multi-level optimization problems with improved efficiency.

Stochastic convex optimization problems with expectation constraints (SOECs) are encountered in statistics and machine learning, business, and engineering. In data-rich environments, the SOEC objective and constraints contain expectations defined with respect to large datasets. Therefore, efficient algorithms for solvi…

The clusters of a distribution are often defined by the connected components of a density level set. However, this definition depends on the user-specified level. We address this issue by proposing a simple, generic algorithm, which uses an almost arbitrary level set estimator to estimate the smallest level at which th…

New model predicts grain boundary migration in metals.

For Hamiltonian flows we establish the existence of periodic orbits on a sequence of level sets approaching a Bott-nondegenerate symplectic extremum of the Hamiltonian. As a consequence, we show that a charge on a compact manifold with a nondegenerate (i.e. symplectic) magnetic field has periodic orbits on a sequence o…

New algorithm stabilizes bi-level hyperparameter optimization.

Following Hartigan, a cluster is defined as a connected component of the t-level set of the underlying density, i.e., the set of points for which the density is greater than t. A clustering algorithm which combines a density estimate with spectral clustering techniques is proposed. Our algorithm is composed of two step…

We study the asymptotic behavior of convex Cauchy hypersurfaces on maximal globally hyperbolic spatially compact space-times of constant curvature. We generalise the result of [11] to the (2+1) de Sitter and anti de Sitter cases. We prove that in these cases the level sets of quasi-concave times converge in the Gromov …

We study the connections between spectral clustering and the problems of maximum margin clustering, and estimation of the components of level sets of a density function. Specifically, we obtain bounds on the eigenvectors of graph Laplacian matrices in terms of the between cluster separation, and within cluster connecti…

Adaptive gradient methods like AdaGrad are widely used in optimizing neural networks. Yet, existing convergence guarantees for adaptive gradient methods require either convexity or smoothness, and, in the smooth setting, only guarantee convergence to a stationary point. We propose an adaptive gradient method and show t…

FedCluster accelerates federated learning convergence by cycling device groups.

Paper analyzes EM algorithm's trajectory in 2MLR, revealing cycloid behavior.

In this paper, we are interested in the strong convergence properties of the Ninomiya-Victoir scheme which is known to exhibit weak convergence with order 2. We prove strong convergence with order $1/2$. This study is aimed at analysing the use of this scheme either at each level or only at the finest level of a multil…

Let $M$ be a maximal globally hyperbolic Cauchy compact flat spacetime of dimension 2+1, admitting a Cauchy hypersurface diffeomorphic to a compact hyperbolic manifold. We study the asymptotic behaviour of level sets of quasi-concave time functions on $M$. We give a positive answer to a conjecture of Benedetti and Guad…

The paper optimizes training samples for image denoising across different noise levels.

New framework tackles bi-level optimization without LLS condition.

Huisken and Sinestrari have recently defined a surgery process for mean curvature flow when the initial data is a two-convex hypersurface. The process depends on a parameter H. Its role is to initiate a surgery when the maximum of the mean curvature of the evolving hypersurface becomes H, and to control the scale at wh…

FLORAS uses orthogonal sequences for SISO FL, offering both DP and convergence guarantees.

This work analyzes generalization in federated learning using information theory.

The paper proves convergence to global optima for a class of distributed algorithms for nonconvex optimization in network-based multi-agent settings. Agents are permitted to communicate over a time-varying undirected graph. Each agent is assumed to possess a local objective function (assumed to be smooth, but possibly …

Efficient method for high confidence level inference using parallel stochastic optimization.

Novel evolutionary strategy solves stochastic constrained optimization problems.

This paper analyzes user-level local differential privacy in distributed systems.

Improved convergence and curvature estimate for parabolic Allen-Cahn equation.

Unified view of monotonicity formulas for inverse mean curvature flow and $p$-capacitary potentials.

New method tackles inexact bilevel optimization for faster parameter learning.

New method solves complex optimization problems faster.

In this paper we introduce a geometric quantity, the $r$-multiplicity, that controls the length of a smooth curve as it evolves by curve shortening flow. The length estimates we obtain are used to prove results about the level set flow in the plane. If $K$ is locally-connected, connected and compact, then the level set…

In this paper we propose a modified version of the simulated annealing algorithm for solving a stochastic global optimization problem. More precisely, we address the problem of finding a global minimizer of a function with noisy evaluations. We provide a rate of convergence and its optimized parametrization to ensure a…

Study compares different levels of supervision for training graph embeddings in wireless networks.

The paper constructs hypersurfaces translating under powers of Gauss curvature.

We develop a primal dual active set with continuation algorithm for solving the \ell^0-regularized least-squares problem that frequently arises in compressed sensing. The algorithm couples the the primal dual active set method with a continuation strategy on the regularization parameter. At each inner iteration, it fir…

In this paper we prove that if $γ$ is a Jordan curve on $\mathbb{S}^2$ then there is a smooth curve shortening flow defined on $(0,T)$ which converges to $γ$ in $\mathcal{C}^0$ as $t\to 0^+$. Another perspective is that the level-set flow of $γ$ is smooth. This is a generalization of the author's previous work where t…

Paper explores generalization of AID-based bi-level optimization methods.

New method for online meta-learning reduces dynamic regret in changing environments.

In this paper we consider the Allen-Cahn equation with constraint. In 1994, Chen and Elliott studied the asymptotic behavior of the solution of the Allen-Cahn equation with constraint. They proved that the zero level set of the solution converges to the classical solution of the mean curvature flow under the suitable c…

Adaptive gradient methods such as AdaGrad and its variants update the stepsize in stochastic gradient descent on the fly according to the gradients received along the way; such methods have gained widespread use in large-scale optimization for their ability to converge robustly, without the need to fine-tune the stepsi…

The study analyzes convergence rates for sparse pivotal estimators in high-dimensional regression.

Paper analyzes faster convergence rates for reinforcement learning from offline data.

This paper improves HNNs by learning optimal curvature for better generalization.

We investigate the Dolbeault operator on a pair of pants, i.e., an elementary cobordism between a circle and the disjoint union of two circles. This operator induces a canonical selfadjoint Dirac operator $D_t$ on each regular level set $C_t$ of a fixed Morse function defining this cobordism. We show that as we approac…

o1Neuro neural network approximates complex functions and converges quickly.

Gradient flows of neural networks converge to optimal values or diverge, with thresholds and asymptotic behaviors.

Develops Aleksandrov reflection for hyperbolic flows, proving convergence to umbilic surfaces.