Classifies ancient convex curves in convex domains.
problem Ancient convex curve shortening flows on convex domains.
method Classification of convex ancient solutions.
result Ancient convex curves in convex domains classified.
Classifies geodetically convex sets and functions on Heisenberg group.
problem Characterizing geodetically convex sets and functions in the Heisenberg group.
method Classification through mathematical analysis.
result Geodetically convex sets and functions defined on Heisenberg group Hn classified. Classifies ancient flows in a disc with boundary.
problem Ancient convex flows in a disc with boundary.
method Classifies flows using curve shortening.
result Ancient convex flows in a disc are classified.
Unhinged loss minimization fails to improve classifier accuracy for simple data.
problem Accuracy of classifiers minimizing the unhinged loss.
method Minimizing the unhinged loss function.
result Minimizing the unhinged loss yields classifiers with accuracy no better than random guessing for simple data.
Proposes a non-convex optimization method for a parsimonious weighted naive Bayes classifier.
problem Improving naïve Bayes classifier performance with a large number of input variables.
method Sparse regularization of model log-likelihood for direct estimation of variable weights.
result Optimization-based weighted naïve Bayes classifiers achieve equivalent performance to averaging-based classifiers.
Efficient poisoning attack converges to any target classifier with provable convergence.
problem Inducing a corrupted model that misbehaves in favor of an adversary.
method Online convex optimization to find poisoning points incrementally.
result Provably converges to any attainable target classifier.
Paper proposes a new classifier for hyperbolic spaces using horospherical boundaries.
problem Optimization of large margin classifiers in hyperbolic spaces.
method Horospherical decision boundaries for geodesically convex optimization.
result Geodesically convex optimization leads to globally optimal solutions.
The study classifies flows of finite curvature in 3D space.
problem Classifying flows of finite curvature in 3D space.
method Partial classification of eternal mean convex flows.
result Topologically nonplanar flows must exit a catenoid.
Adversarial consistency depends on the uniqueness of adversarial Bayes classifiers.
problem Consistency of adversarial surrogate losses is not guaranteed.
method Connected consistency of adversarial surrogate losses to the uniqueness of adversarial Bayes classifiers.
result A convex surrogate loss is statistically consistent for adversarial learning if and only if the adversarial Bayes classifier is unique.
We give an explicit classification of translation-invariant, Lorentz-invariant continuous valuations on convex sets. We also classify the Lorentz-invariant even generalized valuations.
In this paper we consider convex improper affine maps of the 3-dimensional affine space and classify their singularities. The main tool developed is a generating family with properties that closely resembles the area function for non-convex improper affine maps.
In this study, a novel sparsity-driven weighted ensemble classifier (SDWEC) that improves classification accuracy and minimizes the number of classifiers is proposed. Using pre-trained classifiers, an ensemble in which base classifiers votes according to assigned weights is formed. These assigned weights directly affec…
Classifies tight contact structures on specific Seifert fibered manifolds.
problem Classifying tight contact structures on Seifert fibered manifolds.
method Constructed contact structures using Legendrian surgery and used convex surface theory for the upper bound.
result Found the lower and upper bounds for tight contact structures.
The paper classifies nilmanifolds with specific SL(3,C) structures.
problem Classifying nilmanifolds with invariant mean convex or tamed SL(3,C) structures.
method Invariants and classification of structures on nilmanifolds.
result Classification of nilmanifolds with invariant mean convex closed SL(3,C) structures.
Researchers classify and decompose valuations on convex functions.
problem Classifying valuations on convex functions.
method Geometric decomposition of valuations, using properties of special subspaces and Monge-Ampère-type operators.
result Valuations decompose into subspaces defined by vanishing properties.
This work shows neural networks can solve non-convex constraints problems.
problem Training neural networks under non-convex constraints.
method Project stochastic gradient descent with no-regret analysis of online learning.
result Overparameterized neural networks achieve near-optimal and near-feasible solutions.
In this paper we classify convex compact ancient solutions to the affine curve shortening flow: namely, any convex compact ancient solution to the affine curve shortening flow must be a shrinking ellipse. The method combines a rescaling argument inspired by \cite{Wang}, affine invariance of the equation and monotonicit…
Study contact structures on lens spaces, classifying rational knots.
problem Classify rational knots in lens spaces.
method One-parametric convex surface theory to classify Legendrian and transverse rational unknots.
result Determine the contact mapping class group of lens spaces.
Motivated by problems of anomaly detection, this paper implements the Neyman-Pearson paradigm to deal with asymmetric errors in binary classification with a convex loss. Given a finite collection of classifiers, we combine them and obtain a new classifier that satisfies simultaneously the two following properties with …
For a Euclidean building X of type A2, we classify the 0-dimensional subbuildings A of ∂TX that occur as the asymptotic boundary of closed convex subsets. In particular, we show that triviality of the holonomy of a triple (of points of A) is (essentially) sufficient. To prove this, we construct n…
Classifies ancient solutions to curvature flows, finding two main types.
problem Classifying ancient solutions to fully nonlinear curvature flows.
method Natural conditions on speed, convexity, noncollapsing, uniform two-convexity.
result Exactly two possibilities: self-similarly shrinking cylinder or rotationally symmetric translating soliton.
Consider a classification problem where we have both labeled and unlabeled data available. We show that for linear classifiers defined by convex margin-based surrogate losses that are decreasing, it is impossible to construct any semi-supervised approach that is able to guarantee an improvement over the supervised clas…
Convex-cocompact groups in infinite hyperbolic space are deformable.
problem Understanding deformability of convex-cocompact groups in infinite hyperbolic spaces.
method Proving convex-cocompact representations form an open set and using bending to deform them.
result Deformable convex-cocompact representations of surface groups not conjugate to exotic PSL(2,R) representations.
Study compares chi-squared divergence and KL-divergence posteriors for PAC-Bayesian bounds.
problem Investigates optimal posteriors for PAC-Bayesian bounds using chi-squared divergence.
method Analyzes bounds for three distance functions, derives FP equations for computation.
result Chi-squared divergence based posteriors have weaker bounds and worse test errors.
Classifies regularity for Lagrangian mean curvature type equations.
problem Classifying regularity for Lagrangian mean curvature type equations.
method Generalized constant rank theorem for Legendre transform, constructed convex solutions, and showed regularity conditions.
result Optimal regularity conditions for Lagrangian mean curvature type equations.
We classify the self-similar solutions to a class of Weingarten curvature flow of connected compact convex hypersurfaces, isometrically immersed into space forms with non-positive curvature, and obtain a new characterization of a sphere in a Euclidean space Rn+1.
New regularizers tighten convex relaxation bounds for neural networks.
problem Large gap between certifiable and empirical robustness in neural networks.
method Two regularizers to train neural networks yielding tighter convex relaxation bounds.
result Higher certified accuracy with proposed regularizers.
Classifies convex disks with Legendrian boundary in overtwisted contact 3-manifolds.
problem Classifying convex disks with Legendrian boundary in overtwisted contact 3-manifolds.
method Contact isotopy classification, h-principle, fundamental groups, contact mapping class group.
result Establishes an h-principle for convex disks with Legendrian boundary in overtwisted contact 3-manifolds.
The paper classifies flows of ancient curves in 2D space.
problem Classifying closed convex flows by curvature powers.
method Sub-affine-critical powers of curvature for flow classification.
result Ancient flows converge exponentially to smooth shrinkers.
Optimal posterior distributions improve SVM classifiers and parameter selection.
problem Improving SVM classifiers and selecting optimal regularization parameters.
method PAC-Bayesian approach with optimal posterior identification for stochastic classifiers.
result Optimal posteriors yield tight risk bounds and improved SVM performance.
Study of convex hypersurfaces with specific curvature properties.
problem Characterizing convex hypersurfaces with vanishing Weyl curvature and semi-parallel cubic form.
method Analyzing locally strongly convex affine hypersurfaces with vanishing Weyl curvature tensor and semi-parallel cubic form relative to the Levi-Civita connection of affine metric.
result Classification of such hypersurfaces, excluding flat affine metric cases.
We consider a discriminative learning (regression) problem, whereby the regression function is a convex combination of k linear classifiers. Existing approaches are based on the EM algorithm, or similar techniques, without provable guarantees. We develop a simple method based on spectral techniques and a `mirroring' tr…
We classify positive tight contact structures, up to isotopy fixing the boundary, on the manifolds N=M(D2;r1,r2) with minimal convex boundary of slope s and Giroux torsion 0 along ∂N, where r1,r2∈(0,1)∩Q, in the following cases: (1) s∈(−∞,0)∪[2,+∞); (2) $s\in[0…
In this paper, we establish a general inequality for locally strongly convex centroaffine hypersurfaces in Rn+1 involving the norm of the covariant derivatives of both the difference tensor K and the Tchebychev vector field T. Our result is optimal in that, applying our recent classification for local…
Classifies horocycle flow closures in hyperbolic 3-manifolds.
problem Classifying horocycle flow closures in hyperbolic 3-manifolds.
method Classifies orbit closures of the 1-dimensional horocycle flow on the frame bundle of M.
result The closure of a horocycle in M is a properly immersed submanifold.
This paper introduces Jensen, an easily extensible and scalable toolkit for production-level machine learning and convex optimization. Jensen implements a framework of convex (or loss) functions, convex optimization algorithms (including Gradient Descent, L-BFGS, Stochastic Gradient Descent, Conjugate Gradient, etc.), …
We consider the evolution of hypersurfaces on the unit sphere Sn+1 by their mean curvature. We prove a differential Harnack inequality for any weakly convex solution to the mean curvature flow. As an application, by applying an Aleksandrov reflection argument, we classify convex, ancient solutions of the …
We prove that any complete immersed two-sided mean convex translating soliton Σ⊂R3 for the mean curvature flow is convex. As a corollary it follows that an entire mean convex graphical translating soliton in R3 is the axisymmetric "bowl soliton". We also show that if the mean curvature of…
Nested Cavity Classifier (NCC) is a classification rule that pursues partitioning the feature space, in parallel coordinates, into convex hulls to build decision regions. It is claimed in some literatures that this geometric-based classifier is superior to many others, particularly in higher dimensions. First, we give …
Paper introduces r-DEP classifier for binary classification tasks.
problem No natural ordering for feature patterns in practical situations.
method Introduces reduced dilation-erosion (r-DEP) classifier using multi-valued mathematical morphology.
result r-DEP classifiers outperform traditional SVCs in balanced accuracy.
New ancient solutions found for curvature flow in 2D.
problem Ancient solutions for curvature flow in 2D.
method Constructing and classifying convex ancient solutions.
result All convex ancient solutions classified for α∈(32,1). Study shows how classifiers can approach Bayes error in high-dimensional settings.
problem Generalization error in high-dimensional perceptrons.
method Proved a formula for generalization error using convex optimization and observed that logistic and hinge regression can approach Bayes error closely.
result Logistic and hinge regression can approach Bayes-optimal generalization error closely in high-dimensional settings.
The paper classifies vertices in planar polygons formed by convex domains.
problem Classifying vertices in planar polygons formed by convex domains.
method Analyzing polygons formed by homothets and translates of a convex domain.
result The number of singular boundary points in a C-polygon is between n and 2(n−1)+m for a strictly convex domain with m singular boundary points. Fairness-aware classification is receiving increasing attention in the machine learning fields. Recently research proposes to formulate the fairness-aware classification as constrained optimization problems. However, several limitations exist in previous works due to the lack of a theoretical framework for guiding the …
We apply the network Lasso to classify partially labeled data points which are characterized by high-dimensional feature vectors. In order to learn an accurate classifier from limited amounts of labeled data, we borrow statistical strength, via an intrinsic network structure, across the dataset. The resulting logistic …
Study minimax rates for binary classifier estimation with margin conditions.
problem Estimating binary classifiers with geometric margin conditions.
method Derive lower bounds for worst-case learning rates over various function classes.
result Identify optimal rates close to O(n−1) for different function classes. New methods classify convex lattice polygons for affine dimers.
problem Not all convex lattice polygons are characteristic polygons of affine dimers.
method General constructions and algorithm for finding affine dimers with prescribed polygons.
result All lattice triangles, generalised parallelograms, and polygons of genus at most two admit an affine dimer.
Optimal domain adaptation model using Fisher's Linear Discriminant.
problem Improving classification accuracy across different domains.
method Convex combination of source and target hypotheses, derived under 0-1 loss.
result Effective classifier can be computed without direct source task information.