Study compares 5 nonlinear kernels, finding min-max outperforms RBF on some datasets.
problem Comparing performance of nonlinear kernels on various datasets.
method 5 different nonlinear kernels (min-max, RBF, fRBF, acos, acos-χ2) were compared on multiple datasets. result min-max kernel outperforms RBF on some datasets, suggesting its potential for linearization.
The min-max kernel is a generalization of the popular resemblance kernel (which is designed for binary data). In this paper, we demonstrate, through an extensive classification study using kernel machines, that the min-max kernel often provides an effective measure of similarity for nonnegative data. As the min-max ker…
Proposes a method for kernel learning using feature maps.
problem Improving SVM margin through iterative refinement.
method Fourier-analytic characterization and iterative feature maps.
result Optimal and generalization guarantees for SVM margin improvement.
Proposes new kernels for better classification performance.
problem Improving classification performance in computer vision.
method Developed GInt and NGMM kernels, and validated their effectiveness empirically.
result GInt kernel performs well in classification tasks, NGMM kernel outperforms GInt.
Proposes a new feature preprocessing method using kernel density integral transformation.
problem Feature preprocessing for tabular data in machine learning and statistics.
method Kernel density integral transformation as a drop-in replacement or improved alternative to min-max scaling and quantile transformation.
result Frequently outperforms min-max scaling and quantile transformation with hyperparameter tuning.
The paper proposes a novel MKL approach for OCC using ℓp-norm constraints.
problem Addressing the MKL problem for one-class classification.
method A min-max saddle point Lagrangian optimisation problem is formulated and solved efficiently.
result The proposed method outperforms baselines and other algorithms on various data sets.
A robust method for multiple kernel learning against adversarial inputs.
problem Certifiably robust learning against adversarial perturbations.
method Distributionally robust optimization with min-max formulation and debiasing techniques.
result The method achieves theoretical guarantees and generalization bounds.
Improved kernel methods enhance data similarity estimation.
problem Efficiently estimating the RBF kernel's similarity.
method Normalized Random Fourier Features (NRFF) and Generalized Min-Max (GMM) kernel.
result GCWS typically requires fewer samples than NRFF for comparable accuracy.
Nystrom method approximates GMM kernel for large datasets.
problem Efficiently computing GMM kernel for large-scale datasets.
method Apply Nystrom method to approximate GMM kernel.
result GMM-NYS approximates GMM kernel with comparable accuracy using fewer samples.
New method for training GANs with reduced complexity and robustness.
problem Non-robustness and high computational complexity in GAN training.
method Kernel-based approach with stochastic gradient algorithm.
result Training algorithm with reduced complexity and increased robustness.
Adaptive kernels from neural networks improve model performance.
problem Improving neural network performance through adaptive kernels.
method Deriving adaptive kernels from infinite-width neural networks using feature learning and gradient flow training.
result Adaptive kernels achieve lower test loss compared to traditional kernels.
Equity-Transformer solves NP-hard min-max routing problems efficiently.
problem Min-max routing problems with multiple agents and large-scale applications.
method Sequential planning approach with Transformer and equitable workload distribution inductive biases.
result Significant runtime and cost reductions in min-max mTSP and min-max mPDP tasks.
Study shows strong min-max principle for phase transitions.
problem Understanding nodal sets near minimal hypersurfaces.
method Analogous to White's principle, applies to Allen-Cahn energy.
result Strong min-max principle for phase transitions.
Upper bound for Morse index of min-max varifolds.
problem Bounding Morse index of varifolds.
method Proving upper bound for Morse index of min-max stationary integral varifolds.
result Upper bound for Morse index of min-max stationary integral varifolds.
Localized min-max method proves minimal hypersurface existence.
problem Existence of minimal hypersurfaces in complete manifolds.
method Localized min-max approach to prove existence.
result Existence of complete embedded minimal hypersurface with index at most one.
The paper solves min-max widths on a 3-sphere and strengthens multiplicity theorems.
problem Which min-max widths of the unit 3-sphere lie between 2π2 and 8π? method Homological min-max theory and stronger versions of multiplicity one theorems.
result Proves the 10th to 13th min-max widths of the unit 3-sphere lie between 2π2 and 8π. Proves multiplicity one for min-max minimal hypersurfaces in specific manifolds.
problem Proving multiplicity one for min-max minimal hypersurfaces in specific manifolds.
method Using min-max theory for hypersurfaces with prescribed mean curvature and approximating min-max values.
result Confirms a conjecture by Marques-Neves for min-max minimal hypersurfaces in bumpy metrics.
Characterizes Zoll metrics via min-max values.
problem Characterizing Zoll Riemannian metrics.
method Uses min-max values in a loop space.
result Two min-max values coincide for Zoll metrics.
We propose a novel adversarial training method in feature space that improves model robustness and computational efficiency.
problem Improving model robustness against adversarial input perturbations with computational efficiency.
method Shift from input to feature-space perturbations, reformulating the adversarial training problem in reproducing kernel Hilbert spaces, enabling exact solution of inner maximization and efficient optimization.
result The feature-perturbed formulation is a relaxation of the original problem and provides a regularized estimator that adapts to noise and function smoothness.
Paper develops min-max theory for CMC hypersurfaces.
problem Constructing constant mean curvature hypersurfaces.
method Min-max theory applied to arbitrary closed manifolds.
result Existence of nontrivial, smooth, closed, almost embedded CMC hypersurfaces.
Study introduces statistical mechanics for min-max problems.
problem Understanding the properties of min-max problems in high dimensions.
method Statistical mechanical formalism for analyzing min-max problems.
result Derives the relationship between training data and generalization error.
Adaptive momentum method solves non-convex min-max problems.
problem Non-convex min-max optimization problems in training generative adversarial networks.
method Proposes an adaptive momentum algorithm for non-convex min-max optimization.
result Establishes non-asymptotic convergence rates for the proposed algorithm.
Paper proves finiteness and Morse index estimates for equivariant min-max hypersurfaces.
problem Existence and finiteness of G-invariant minimal hypersurfaces. method Equivariant min-max theory, compactness theorem, bumpy metrics theorem.
result Generalization of Morse index estimates to equivariant setting.
The study bounds Morse indices of Willmore spheres in relation to min-max sweep-outs.
problem Estimating Morse indices of Willmore spheres.
method Analyzing the sum of Morse indices of Willmore spheres in min-max sweep-outs.
result At most one Willmore sphere can have index 1 among those realising min-max sphere eversion.
New proof of Smale conjecture for RP^3 and lens spaces using min-max theory.
problem Proving the Smale conjecture for specific spaces.
method Minimal surfaces and min-max theory.
result New proof of Smale conjecture for RP3 and lens spaces. Paper improves Morse index bound for hypersurfaces.
problem Improving Morse index bound for hypersurfaces.
method Construction of hierarchical deformations and restrictive min-max theory.
result Generalizes a result by X. Zhou for 3≤n+1≤7. New methods solve min-max problems on manifolds using Riemannian Hamiltonians.
problem Min-max optimization on Riemannian manifolds.
method Riemannian Hamiltonian methods (RHM) to minimize the Hamiltonian function.
result RHM leads to correct search directions and global optimality in min-max problems.
Bound on equivariant index for min-max surfaces.
problem Bounding the index of equivariant min-max surfaces.
method Equivariant min-max procedure with group action.
result Equivariant index bound by number of parameters.
Survey of advances in non-convex min-max optimization for applications.
problem Finding optimal solutions in non-convex, non-concave min-max problems.
method Selective review of theoretical and algorithmic advances.
result Exciting recent advances in solving non-convex min-max problems.
Tunable GMM kernels improve on original GMM in various classification tasks.
problem Improving the efficiency and performance of GMM kernels.
method Developed three tunable GMM kernels: eGMM, pGMM, and epGMM.
result Tunable GMM kernels typically improve over the original GMM kernel on 60 datasets.
Proposes tunable GMM kernels for classification tasks.
problem Lack of competitive performance of GMM kernels compared to tree methods on deep learning datasets.
method Introduces tunable GMM kernels with added parameters and combines basic kernels for improved performance.
result Tunable GMM kernels can produce good results for various classification tasks.
We reformulate LIPs as min-max problems for easier solution.
problem Recovering signals from few linear measurements.
method Proposed a min-max reformulation of LIPs.
result Saddle points characterize solutions to LIPs.
Epoch-GDA achieves optimal convergence rate for SCSC min-max problems.
problem Solving stochastic min-max problems with strong convexity and strong concavity.
method Epoch-wise stochastic gradient descent ascent method (Epoch-GDA) without additional assumptions.
result Achieves the optimal rate of O(1/T) for the duality gap of general SCSC min-max problems. The paper bounds the min-max width of embedded circles on spheres and manifolds.
problem Bounding the min-max width of embedded circles on spheres and manifolds.
method Inducing a sweepout by pairs of points in embedded circles from a given sweepout of the sphere by closed curves.
result Lower bounds for the Birkhoff min-max invariant of a Riemannian sphere in terms of the min-max width of its embedded circles.
Study confirms a 2-sphere metric with three geodesics of minimal length.
problem Understanding the systolic, width, and Gromov-Guth metrics on a 2-sphere.
method Classical min-max and hyperbolic geometry tools.
result Figure-eight geodesics achieve the systolic, width, and Gromov-Guth metrics on a 2-sphere.
Develops equivariant min-max theory for minimal surfaces in S^3.
problem Finding minimal surfaces in S^3 with specific symmetries.
method Equivariant min-max theory as proposed by Pitts-Rubinstein.
result Produces new and known minimal surfaces in S^3.
Generic min-max theory proves existence of hypersurfaces with specific mean curvature.
problem Proving existence of hypersurfaces with prescribed mean curvature for generic functions.
method Generic min-max theory applied to smooth prescription functions.
result Existence of nontrivial, smooth, closed hypersurfaces with specific mean curvature.
Bayesian optimization methods improved for min max optimization problems.
problem Min-max optimization for unknown functions.
method Extended Bayesian optimization to min-max problems with new acquisition functions.
result Improved acquisition functions lead to better solutions.
In this paper, we study the shape of the min-max minimal hypersurface produced by Almgren-Pitts-Schoen-Simon \cite{AF62, AF65, P81, SS81} in a Riemannian manifold (Mn+1,g) of positive Ricci curvature for all dimensions. The min-max hypersurface has a singular set of Hausdorff codimension 7. We characterize the …
This research proves that two min-max theories for hypersurfaces are equivalent.
problem Comparing two min-max theories for hypersurfaces.
method Developed and proved the equivalence of Almgren-Pitts and Allen-Cahn min-max theories.
result The Almgren-Pitts widths and Allen-Cahn widths are equivalent.
The study proves a generic multiplicity one theorem for G-invariant minimal hypersurfaces.
problem Proving a generic multiplicity one theorem for G-invariant minimal hypersurfaces. method Equivariant min-max theory and analysis of G-homology classes. result Shows a generic multiplicity one theorem for G-invariant minimal hypersurfaces. Constructs cmc doublings of minimal surfaces via min-max theory.
problem Construct cmc doublings of minimal surfaces.
method Uses min-max theory and catenoid estimate.
result Constructs ε-cmc doublings of Σ for small ε > 0.
This study reveals a Min-Max property in LeNet's convolutional layers, enhancing adversarial robustness.
problem Uncertainty in the connection weights of convolutional layers in neural networks.
method Demonstrates the Min-Max property through back propagation-based training and a simplified convolution formulation.
result The Min-Max property improves adversarial robustness, indicating a stronger uncertainty in the model parameters.
New insights into gradient descent and ascent dynamics in min-max optimization.
problem Understanding the convergence and limit points of gradient descent and ascent methods in min-max optimization problems.
method Characterization of limit points using dynamical systems perspective for GDA and OGDA.
result Both GDA and OGDA dynamics avoid unstable critical points and have a superset of local min-max solutions.
New Gaussian min-max theorem extends classical results to non-i.i.d. Gaussian matrices.
problem Extending classical Gaussian min-max theorems to non-i.i.d. Gaussian matrices.
method Identifying a new pair of Gaussian processes that satisfy comparison inequalities.
result New Gaussian min-max and convex Gaussian min-max theorems with applications in multi-source Gaussian regression and binary classification.
New algorithm solves non-convex, non-differentiable min-max games.
problem Limited theoretical understanding of non-smooth min-max games.
method Proximal gradient descent-ascent algorithm for convex-strongly convex games.
result Algorithm converges to ε-Nash equilibrium with polynomial gradient evaluations.
Proves min-max theory for constant geodesic curvature curves on closed surfaces.
problem Prescribing mean curvature on surfaces with constant geodesic curvature.
method Min-max theory applied to classify blowups and ensure almost embedded solutions.
result Produces a solution with constant geodesic curvature c on closed surfaces. Generic density of equivariant min-max hypersurfaces in Riemannian manifolds.
problem Finding generic density of equivariant min-max hypersurfaces in Riemannian manifolds.
method Weyl asymptotic law for G-equivariant volume spectrum, generic density result. result Generic density of equivariant min-max hypersurfaces in Riemannian manifolds.