The paper proves uniform approximation for minimal surfaces with applications to a Mittag-Leffler theorem.
problem Approximating complete conformal minimal surfaces with finite curvature.
method Uniform approximation theorem with interpolation for minimal surfaces.
result Obtained a Mittag-Leffler type theorem for minimal immersions.
Discrete approximation solves Björling's minimal surface problem.
problem Constructing minimal surfaces from real-analytic curves with specified normal fields.
method Approximate solution by discrete minimal surfaces and discrete isothermic surfaces.
result Approximation error is proportional to the square of the mesh size.
New method approximates non-submodular functions, offering first guarantees.
problem Minimizing non-submodular functions without theoretical guarantees.
method Extends submodularity relations to non-submodular functions, offering approximation guarantees.
result First approximation guarantees for non-submodular minimization, optimal under noise.
Almost perimeter-minimizing boundaries in plentiful groups can be approximated by Lipschitz graphs.
problem Regularity of boundaries in plentiful groups.
method Lipschitz approximation of boundaries.
result Boundary of almost minimizers can be approximated by intrinsic Lipschitz graphs.
Smooth cones can be approximated by smooth hypersurfaces.
problem Approximating cones with smooth surfaces.
method Hyperbolic unfoldings and Jacobi field operator potential theory.
result Every area minimizing cone can be approximated by smooth hypersurfaces.
New learning algorithm for real analytic functions without gradient descent.
problem Learning real analytic functions without gradient descent.
method Taylor approximation and sampling data distribution.
result Nonuniform learning result for real analytic functions.
Minimal surfaces in the sub-Riemannian Heisenberg group can be constructed by means of a Riemannian approximation scheme, as limit of Riemannian minimal surfaces. We study the regularity of Lipschitz, non-characteristic minimal surfaces which arise as such limits. Our main results are a-priori estimates on the solution…
An approximation theorem for minimal surfaces by complete minimal surfaces of finite total curvature in R3 is obtained. This Mergelyan type result can be extended to the family of complete minimal surfaces of weak finite total curvature, that is to say, having finite total curvature on proper regions of fin…
In this paper, we prove that every confomal minimal immersion of an open Riemann surface into Rn for n≥5 can be approximated uniformly on compacts by conformal minimal embeddings. Furthermore, we show that every open Riemann surface carries a proper conformal minimal embedding into R5. One …
Optimal function approximation with Relu neural networks achieves minimal error.
problem Finding the minimal error in approximating convex functions with Relu networks.
method Established necessary and sufficient conditions for optimal approximations, presented neural network architectures, and proposed an algorithm for convergence.
result Proved the convergence of the proposed algorithm and validated it with experimental results.
The Mittag-Leffler theorem is extended to meromorphic curves and minimal surfaces.
problem Extending the Mittag-Leffler theorem to meromorphic curves and minimal surfaces.
method Established a Mittag-Leffler-type theorem for meromorphic curves and minimal immersions, including interpolation and approximation.
result Complete minimal ends in R^5 are generically embedded, and open Riemann surfaces are characterized for minimal surfaces.
Paper approximates continuous functions on Jordan arcs using conformal minimal immersions.
problem Approximating continuous functions on Jordan arcs using minimal immersions.
method Conformal minimal immersions and directed holomorphic curves.
result Continuous functions on Jordan arcs can be approximated by conformal minimal immersions.
Unified framework for shrinkage, thresholding, and regularization in normal mean estimation and linear regression.
problem Estimation of normal mean in multivariate settings with correlated observations.
method Approximate risk minimization over a functional class of shrinkage-thresholding rules.
result Unified estimator NOMAD for shrinkage, thresholding, and regularization.
We construct Lipschitz Q-valued functions which approximate carefully integral currents when their cylindrical excess is small and they are almost minimizing in a suitable sense. This result is used in two subsequent works to prove the discreteness of the singular set for the following three classes of 2-dimensiona…
New algorithm finds approximate minimizers for noisy convex functions.
problem Minimizing convex functions with noisy approximations that are nonconvex.
method Combining simulated annealing with stochastic gradient Langevin dynamics.
result Polynomial time algorithm for finding approximate minimizers.
The paper shows how heat flow approximates area functional on specific geometric spaces.
problem Approximating the area functional on $\RCD(K,\infty)$ spaces.
method Using heat flow and properties of $\RCD(K,\infty)$ spaces.
result The area functional coincides with its relaxation in $\RCD(K,\infty)$ spaces.
The paper analyzes discrete approximations to minimize curve length in Euclidean space.
problem Minimizing the length of curves between two sets in Euclidean space.
method Finite differences and numerical integration for discrete approximations.
result The squared length of the reconstructed curve converges to the squared minimal length with rate O(N−1/2). This paper develops a new nonlocal approximation method for minimal surfaces, proving robust estimates and separation properties.
problem Constructing minimal surfaces in 3-manifolds and understanding their stability and separation.
method Nonlocal approximation of minimal surfaces, focusing on stability and separation properties.
result Robust curvature and separation estimates for stable nonlocal minimal surfaces, proving hyperplanes are the only stable hypersurfaces in R^4.
New fairness concept extends minimax fairness to lexicographic fairness.
problem Fairness in supervised learning, especially lexicographic fairness.
method Introduced approximate lexifairness, derived algorithms for finding solutions, and proved generalization bounds.
result Proved that approximate lexifairness on training data implies approximate lexifairness on true distribution.
SGD approximates diffusion processes in nonconvex optimization.
problem Nonconvex optimization problems in machine learning.
method Diffusion approximation of SGD using master equation.
result SGD dynamics can escape local minima and saddle points.
We prove a version of the classical Runge and Mergelyan uniform approximation theorems for non-orientable minimal surfaces in Euclidean 3-space R3. Then, we obtain some geometric applications. Among them, we emphasize the following ones: 1. A Gunning-Narasimhan type theorem for non-orientable conformal surfaces. 2. An …
Minimal width din+1 allows ReLU nets to approximate any continuous function of din variables.
problem Approximating continuous functions using ReLU nets with minimal width.
method Analyzing the expressive power of depth in neural nets with ReLU activations.
result Minimal width din+1 is necessary and sufficient for ReLU nets to approximate any continuous function of din variables. New algorithms minimize non-zero entries in low-rank approximations.
problem Minimizing non-zero entries in low-rank approximations of matrices.
method Approximation algorithms for minimizing ℓ0-norm of rank-k matrices. result First provable guarantees for ℓ0-Low Rank Approximation for k>1. Efficiently completes low-rank matrices with nearly linear time complexity.
problem Completing low-rank matrices from a few observed entries.
method Robust alternating minimization framework with approximate updates.
result Achieves nearly linear time complexity in matrix completion.
We study randomized sketching methods for approximately solving least-squares problem with a general convex constraint. The quality of a least-squares approximation can be assessed in different ways: either in terms of the value of the quadratic objective function (cost approximation), or in terms of some distance meas…
Efficiently approximates population risk in large-scale generalized linear problems.
problem Computational intractability of minimizing empirical risk in large-scale settings.
method Designing an efficient algorithm that approximates the population risk minimizer in generalized linear problems.
result Achieves the same accuracy as empirical risk minimizer through cheaper iterations with cubic convergence rate.
Empirical study of IRMv1, an invariant risk minimization framework.
problem Learning predictors invariant to spurious correlations across different training environments.
method Extending ColoredMNIST experiment to various settings.
result IRMv1 performs better as spurious correlation varies more widely.
Infinite width ReLU networks can approximate functions with bounded Euclidean norm.
problem Functions that can be approximated by ReLU networks with bounded Euclidean norm.
method Analyzing the minimal network norm required to approximate a given function.
result The minimal network norm for representing a function \( f \) is \( \max(\int |f''(x)| dx, |f'(-\infty) + f'(+\infty)|) \).
A new variational inference method using optimal transport.
problem Approximating complex posterior distributions with flexible particle-based methods.
method Introducing a new particle-based variational inference method based on semi-discrete optimal transport.
result The method provides a particle approximation and optimal transportation densities.
There are hyperbolic 3-manifolds that fiber over the circle but that do not admit fibrations by minimal surfaces. Furthermore these manifolds do not admit fibrations by surfaces that are even approximately minimal.
Matrix rank minimization problem is in general NP-hard. The nuclear norm is used to substitute the rank function in many recent studies. Nevertheless, the nuclear norm approximation adds all singular values together and the approximation error may depend heavily on the magnitudes of singular values. This might restrict…
In a series of papers, including the present one, we give a new, shorter proof of Almgren's partial regularity theorem for area minimizing currents in a Riemannian manifold, with a slight improvement on the regularity assumption for the latter. This note establishes a new a priori estimate on the excess measure of an a…
This paper presents quantum and classical algorithms for approximate submodular function minimization.
problem Approximate minimization of submodular functions.
method Classical and quantum algorithms for submodular minimization, with a new quantum sampling method.
result Quantum algorithm for approximate submodular minimization with improved time complexity.
Graph-based active learning improves with a new algorithm that balances exploration and exploitation.
problem Graph-based active learning algorithms based on expected error minimization (EEM) often use approximations due to computational hardness, leading to suboptimal performance.
method Proposes TSA (Two-Step Approximation) algorithm that efficiently balances exploration and exploitation with similar computational complexity.
result Empirically shows that balancing exploration and exploitation improves performance in both toy and real-world datasets.
We extend natural-gradient methods to mixtures of exponential-family distributions, improving inference speed.
problem Complex, multimodal posterior distributions are difficult to approximate with simple exponential-family distributions.
method We use minimal conditional-EF representations and derive simple natural-gradient updates.
result Our natural-gradient method converges faster than black-box methods with reparameterization gradients.
Develops consistent approximations for composite optimization problems.
problem Significant errors in solutions due to approximations in optimization problems.
method Specifies conditions for well-behaved approximations in minimizers, stationary points, and level-sets for a broad class of composite problems.
result Framework of consistent approximations for composite problems, including stochastic, neural-network, and multi-objective optimization.
The paper studies harmonic graphs in the Heisenberg group and their properties.
problem No analogous theorem exists for H-minimal surfaces in the Heisenberg group. method Introduced intrinsic Dirichlet energy and studied its critical points (contact harmonic graphs).
result Calibration condition and construction of energy-minimizing graphs with various singularities.
A new method minimizes experimental design regret for various optimality criteria.
problem Optimizing experimental design points for statistical efficiency.
method Regret minimization framework for polynomial-time approximation.
result Achieves (1+ε) approximation with O(p/ε2) design points. Efficient algorithm approximates discrete random variables with minimal Kolmogorov distance.
problem Estimating the probability of missing deadlines in series-parallel schedules.
method An efficient algorithm that computes a random variable with minimal Kolmogorov distance to a given discrete random variable.
result The algorithm efficiently approximates the probability of missing deadlines with minimal Kolmogorov distance.
Corrected Monti's blow-up analysis for H-minimizing sets in Heisenberg group.
problem Blow-up analysis of H-minimizing sets in Heisenberg group with corrected partial differential equation.
method Revised Monti's results on blow-ups of H-perimeter minimizing sets in Hn and corrected the partial differential equation for the limit function. result Corrected the partial differential equation for the limit function of blow-ups in Heisenberg group.
Proposes CLUB for reliable MI minimization in high dimensions.
problem Estimating and minimizing mutual information in high-dimensional spaces.
method Contrastive Log-ratio Upper Bound (CLUB) for MI minimization.
result CLUB provides reliable estimation of mutual information.
We address the problem of minimizing a convex function over the space of large matrices with low rank. While this optimization problem is hard in general, we propose an efficient greedy algorithm and derive its formal approximation guarantees. Each iteration of the algorithm involves (approximately) finding the left an…
We consider an appoximation of a catenoid constructed from "odd" truncated cones that maintains minimality in a certain sense. Thorough this procedure, we obtain a discrete curve approximating a catenary by exploiting the fact that it is the function that generates a catenoid. In this investigation, the theory of the G…
Novel Newton method for large-scale kernel methods using random features.
problem Efficiently solving large-scale finite-sum minimization problems in RKHS.
method Randomized feature-based Newton method for empirical risk minimization.
result Local superlinear and global linear convergence of the method.
Approximate dynamic programming is a popular method for solving large Markov decision processes. This paper describes a new class of approximate dynamic programming (ADP) methods- distributionally robust ADP-that address the curse of dimensionality by minimizing a pessimistic bound on the policy loss. This approach tur…
New algorithms minimize regret in SSP with optimal sparse updates.
problem Minimizing regret in Stochastic Shortest Path models.
method Implicit finite-horizon approximation for analysis, model-free and model-based algorithms developed.
result Minimax optimal regret for both model-free and model-based algorithms.
Deviation inequalities for stochastic approximation methods.
problem Establishing bounds on the deviation of stochastic approximation methods.
method Martingale approximation method for separately Lipschitz functions.
result Established various deviation inequalities for stochastic approximation by averaging and minimization.
We develop a family of accelerated stochastic algorithms that minimize sums of convex functions. Our algorithms improve upon the fastest running time for empirical risk minimization (ERM), and in particular linear least-squares regression, across a wide range of problem settings. To achieve this, we establish a framewo…