Observing a linear superposition principle, a family of new minimal hypersurfaces in Euclidean space is found, as well as that linear combinations of generalized helicoids induce new algebraic minimal cones of arbitrarily high degree.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
169,181 papers · 148 categories
Trend · papers per month
48 results for “linear minimization”
Characterizes kernel of linearization for minimal surfaces problem
problem Characterizing kernel of linearization for minimal surfaces problem
method Show kernel consists of potential fields and TT fields
result In whole-space Euclidean decomposition, kernel consists of potential fields and TT fields
New minimal surfaces created from existing ones.
problem Non-linearity of minimal surface equations.
method General methods to generate new minimal surfaces from known ones.
result Existence of general methods for minimal surfaces.
New cones in 4D space found with minimal mass.
problem Finding mass-minimizing piecewise linear cones in 4D space.
method Mass minimization via Lipschitz maps, classification of candidates.
result No additional mass-minimizing cones found outside five known cases.
Noise in linear networks minimizes sharpness and leads to shrinkage-thresholding.
problem Minimizing sharpness in diagonal linear networks.
method Stochastic sharpness-aware minimization (SAM) with isotropic noise.
result Noise forces shrinkage-thresholding of true parameters.
Minimal surfaces in third-order ODEs identified for linear second-order ODEs.
problem Characterizing minimal surfaces in third-order ODEs.
method Analyzing submanifolds of third-order ODEs as Riemannian manifolds.
result Linear second-order ODEs with are the only minimal surfaces and totally geodesic.
Minimal graph theorem proven for convex domains.
problem Characterizing minimal graphs over convex domains.
method Analyzing minimal surface equation solutions on convex domains.
result Minimal graphs over convex domains are linear.
The paper analyzes the performance of empirical risk minimization for -norm linear regression.
problem Empirical risk minimization on -norm linear regression.
method Analyzes performance under various conditions and moment assumptions.
result High probability excess risk bounds for empirical risk minimizer, matching asymptotic rates.
Stochastic heavy ball method achieves linear convergence for general loss minimization.
problem Minimizing generalization error in machine learning models.
method SGD steps with heavy ball momentum, focusing on expected loss, not finite-sum minimization.
result Established the first linear convergence result for the stochastic heavy ball method.
Diagonal linear networks converge to lasso regularization path during training.
problem Understanding the regularization behavior of diagonal linear networks.
method Analyzing the training trajectory of diagonal linear networks and comparing it to the lasso regularization path.
result The training trajectory of diagonal linear networks is closely related to the lasso regularization path.
Invariant minimal surfaces in the real special linear group of degree 2 with canonical Riemannian and Lorentzian metrics are studied. Constant mean curvature surfaces with vertically harmonic Gauß map are classified.
Paper analyzes agnostic learning of mixed linear regression without generative models.
problem Learning mixed linear regression without assuming stochastic generation.
method Expectation Maximization (EM) and Alternating Minimization (AM) algorithms.
result AM and EM algorithms converge to population loss minimizers under standard conditions.
We consider the problem of solving mixed random linear equations with components. This is the noiseless setting of mixed linear regression. The goal is to estimate multiple linear models from mixed samples in the case where the labels (which sample corresponds to which model) are not observed. We give a tractable a…
Algorithm minimizes regret in adaptive control of unknown linear systems.
problem Adaptive control of unknown linear systems with quadratic costs.
method Provably polynomial time algorithm using recent developments in system estimation and robust controller synthesis.
result First algorithm with high probability guarantees of sub-linear regret.
Develops Frank-Wolfe Augmented Lagrangian for convex optimization.
problem Minimizing functions over intersections of convex sets.
method Frank-Wolfe Augmented Lagrangian (FW-AL) method.
result Sublinear convergence rate for general convex compact sets, linear for polytopes.
If a knot has the Alexander polynomial not equal to 1, then it is linear -colorable. By means of such a coloring, such a knot is given an upper bound for the minimal quandle order, i.e., the minimal order of a quandle with which the knot is quandle colorable. For twist knots, we study the minimal quandle orders in d…
We study surfaces in Euclidean space that are minimal for a log-linear density , where are real numbers not all zero. We prove that if a surface is -minimal foliated by circles in parallel planes, then these planes are orthogonal to the vector and the surface must…
Study finds best linear model in high dimensions using PGD.
problem Finding the best linear model in high-dimensional data.
method Projected gradient descent (PGD) algorithm for estimating the population minimizer.
result PGD achieves linear convergence and data-dependent error bounds.
Paper proves flatness of anisotropic minimal graphs in half-spaces.
problem Anisotropic minimal graphs with free boundaries in half-spaces.
method Proves flatness using linear growth conditions.
result Anisotropic minimal graphs in half-spaces are flat if they have at most one-sided linear growth.
Extended Linear Regression: A Kalman Filter Approach for Minimizing Loss via Area Under the Curvecs.LG
Enhances linear regression with Kalman filter for loss minimization.
problem Minimizing loss in linear regression models.
method Integrates Kalman filter and SGD for optimal weight updates.
result Develops optimal linear regression equation with minimum area under curve.
Optimal Liouville theorem for minimal disks in any codimension.
problem Characterizing harmonic functions on minimal disks in high-dimensional spaces.
method Analyzing harmonic functions and using Liouville's theorem.
result Optimal Liouville theorem for minimal disks in any codimension.
New method solves constrained self-concordant minimization problems efficiently.
problem Constrained self-concordant minimization problems.
method Newton Frank-Wolfe method using linear minimization oracles.
result The method uses nearly the same number of linear minimization calls as the Frank-Wolfe method.
We consider the following problem: for which classes of finite groups, and in particular finite simple groups, does the minimal dimension of a faithful, smooth action on a homology sphere coincide with the minimal dimension of a faithful, linear action on a sphere? We prove that the two minimal dimensions coincide for …
New nonconvex methods improve SysID efficiency and accuracy.
problem Efficiently identify low-order linear systems from limited data.
method Proposes two nonconvex reformulations of Hankel-rank minimization for SysID.
result Nonconvex methods achieve lower statistical error rates and sample complexities.
Study shows TAP free energy minimization provides better posterior inference in high-dimensional linear models.
problem Deviation from true posterior mean and underestimation of posterior uncertainty in variational inference.
method Minimization of TAP free energy in a high-dimensional asymptotic framework, showing geometric and statistical properties.
result Local minimizer of TAP free energy provides consistent estimate of posterior marginals and correctly calibrated posterior inference.
The -groupoid of symmetries is minimal under specific conditions.
problem Conditions for the minimality of the -groupoid of symmetries of a projective structure.
method Analyzing the -groupoid and its sub-groupoids, and relating it to the non-integrability of certain equations.
result The minimality of the -groupoid is equivalent to the non-integrability of specific equations.
Minimal equators and homological systoles found in Berger projective spaces.
problem Tackles the minimality of real projective subspaces under Berger deformations.
method Uses the skew-adjoint endomorphism to classify minimal subspaces and compute homological systoles.
result Equatorial hypersurfaces remain minimal, but not all real subspaces are minimal under Berger deformations.
The paper improves SVR with linear constraints for better model properties.
problem Improving Support Vector Regression with linear constraints.
method Generalized SMO algorithm for solving optimization with linear constraints.
result The proposed method shows better practical performance on various datasets.
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.
IRMAE learns compact latent spaces by minimizing rank.
problem Learning compact latent representations in autoencoders.
method Implicitly minimizes the rank of the covariance matrix through gradient descent in multi-layer linear networks.
result Demonstrates validity on image generation and representation learning tasks.
Two new Frank-Wolfe algorithms use subsampling to speed up convergence.
problem Efficiently solving large-scale optimization problems with linear minimization over subsets.
method Randomized variants of Frank-Wolfe algorithms with subsampling.
result Achieves sublinear or linear convergence rates with reduced computational cost.
Algorithm reduces regret in partially observable systems by learning dynamics and using optimistic control.
problem Minimizing regret in partially observable linear quadratic control systems with unknown dynamics.
method ExpCommit algorithm that learns model parameters and uses optimism in uncertainty.
result End-to-end sublinear regret upper bound of for ExpCommit.
Optimal bounds for exp-concave stochastic minimization in terms of effective dimension.
problem Finding optimal statistical and computational complexity for exp-concave stochastic minimization.
method Derives optimal bounds using effective dimension and sketching techniques.
result Reveals connections between algorithmic stability and ridge leverage scores.
Paper proposes a new robust LDA method using L1,2-norm ratio minimization.
problem Outliers sensitivity in traditional LDA methods.
method L1,2-norm ratio minimization, novel efficient algorithm.
result The proposed method is effective and converges fast.
A triangulated piecewise-linear minimal surface in Euclidean 3-space defined using a variational characterization is critical for area amongst all continuous piecewise-linear variations with compact support that preserve the simplicial structure. We explicitly construct examples of such surfaces that are embedded and a…
Deep linear networks minimize sharpness, avoiding large eigenvalues.
problem Understanding optimization dynamics in deep linear networks for regression.
method Analyzing sharpness (largest eigenvalue of Hessian) of minimizers and gradient flow solutions.
result Gradient flow implicitly regularizes towards flat minima, with sharpness bounded by a constant.
Significant attention has been given to minimizing a penalized least squares criterion for estimating sparse solutions to large linear systems of equations. The penalty is responsible for inducing sparsity and the natural choice is the so-called norm. In this paper we develop a Momentumized Iterative Shrinkage Th…
New algorithm minimizes cumulative loss in dynamic linear bandits without prior knowledge of comparator switches.
problem Minimizing cumulative loss in dynamic linear bandits with unknown number of switches.
method Combining several bandit algorithms to adapt to unknown number of switches without prior knowledge.
result First algorithm achieving optimal regret guarantee of up to poly-logarithmic terms.
MILDA uses unlabelled data to compute LDA projections.
problem Training LDA models with unlabelled data.
method Minimal prior information to compute LDA projection vector.
result MILDA closely matches supervised LDA performance and adapts to non-stationary data.
New insights into optimization and generalization for linear models.
problem Understanding the implicit regularization of optimization methods for linear models.
method Investigating the norms minimized by interpolating solutions and using projections to move between solutions.
result Proving that for over-parameterized linear classification, projections onto the data-span enable the use of under-parameterized techniques.
ReLU networks implicitly favor low-rank solutions, but not as strongly as linear networks.
problem Understanding implicit regularization in ReLU networks for rank minimization.
method Analysis of gradient flow on ReLU networks, empirical testing.
result Gradient flow on ReLU networks does not necessarily minimize ranks, unlike in linear networks.
Study bounds index of minimal hypersurfaces in curved spaces.
problem Bounding the index of minimal hypersurfaces.
method Proved linear index bound using first Betti number and curvature.
result Index is bounded below by a linear function of first Betti number.
Hybrid RL algorithms improve offline and online RL in linear MDPs.
problem Improving RL performance without single-policy concentrability.
method Developed computationally efficient algorithms for PAC and regret-minimizing RL in linear MDPs.
result Achieved sharper error or regret bounds for linear MDPs.
An embedding of a graph into is said to be linear, if any edge of the graph is sent to be a line segment. And we say that an embedding of a graph into is free, if is a free group. It was known that for any complete graph its linear embedding is always free.…
ERM performs well in feature learning with minimal feature maps.
problem Empirical risk minimization in feature learning with square loss.
method Asymptotic and non-asymptotic analysis of ERM performance.
result Excess risk quantiles of ERM match those of oracle procedure under certain conditions.
Maximal surfaces in correspond to timelike minimal surfaces.
problem Establishing a correspondence between maximal and timelike minimal surfaces in .
method Linear transformation between maximal surfaces and timelike minimal surfaces, preserving singularities and Gauss map.
result One-one correspondence and preservation of properties between maximal and timelike minimal surfaces.
Local LMO optimizes constrained problems using local linear minimization.
problem Constrained optimization problems with complex feasible sets.
method Designs a new projection-free gradient method using local linear minimization.
result Transfers convergence rates of Projected Gradient Descent to the projection-free world.
New algorithm minimizes Bayesian regret in offline linear bandits.
problem Minimizing Bayesian regret in offline linear bandits.
method Proposes a new algorithm that directly minimizes upper bounds on Bayesian regret using conic optimization.
result Upper bounds are tight and guarantee superior performance compared to LCB.