arXiv research

Improved mistake bound for group linear separable cases in online multiclass linear classification.

New conditions ensure MMDs separate and converge to target distributions.

Study on self-similar sets on Riemannian manifolds with new separation conditions.

We study the problem of efficient online multiclass linear classification with bandit feedback, where all examples belong to one of $K$ classes and lie in the $d$-dimensional Euclidean space. Previous works have left open the challenge of designing efficient algorithms with finite mistake bounds when the data is linear…

Self-affine arcs without inner weak separation are parabolic segments.

Reduces connectivity problem for genus-4 Heegaard surface in 3-sphere.

While there has been much recent progress using deep learning techniques to separate speech and music audio signals, these systems typically require large collections of isolated sources during the training process. When extending audio source separation algorithms to more general domains such as environmental monitori…

Reduces weak reducing pairs to spheres in 3-sphere Heegaard surfaces.

One approach to monitoring a dynamic system relies on decomposition of the system into weakly interacting subsystems. An earlier paper introduced a notion of weak interaction called separability, and showed that it leads to exact propagation of marginals for prediction. This paper addresses two questions left open by t…

Nuclear norm minimization (NNM) has recently gained significant attention for its use in rank minimization problems. Similar to compressed sensing, using null space characterizations, recovery thresholds for NNM have been studied in \cite{arxiv,Recht_Xu_Hassibi}. However simulations show that the thresholds are far fro…

We introduce a notion of a weak Poisson structure on a manifold $M$ modeled on a locally convex space. This is done by specifying a Poisson bracket on a subalgebra $\cA \subeq C^\infty(M)$ which has to satisfy a non-degeneracy condition (the differentials of elements of $\cA$ separate tangent vectors) and we postulate …

Deep networks can learn functions approximated by shallow networks, but not all functions.

A new IC-Connection improves disentanglement in conditional GANs.

Introduces weak $(p,k)$-Dirac structures in geometric settings.

Proposes a new estimator for weak instrumental variables in panel data models.

In this note we give sufficient conditions to ensure that the weak Finsler structure of a complete $C^k$ Finsler manifold $M$ is determined by the normed algebra $C_b^k(M)$ of all real-valued, bounded and $C^k$ smooth functions with bounded derivative defined on $M$. As a consequence, we obtain: (i) the Finsler structu…

StrADiff separates sources from mixtures without labels, using structured priors.

Posterior regularization enhances Bayesian hierarchical mixture clustering by improving node separation.

This study addresses an issue of co-adaptation between a feature extractor and a classifier in a neural network. A naive joint optimization of a feature extractor and a classifier often brings situations in which an excessively complex feature distribution adapted to a very specific classifier degrades the test perform…

Backtracking Gradient Descent method converges to critical points in Banach spaces.

The study examines different types of equilibria for stopping problems in one-dimensional diffusion processes.

Paper investigates conditions for independence of weak gradients on metric spaces.

We propose a deep-learning approach based on generative adversarial networks (GANs) to reduce noise in weak lensing mass maps under realistic conditions. We apply image-to-image translation using conditional GANs to the mass map obtained from the first-year data of Subaru Hyper Suprime-Cam (HSC) survey. We train the co…

The study examines conditions for weak nearly cosymplectic manifolds to split into products.

This paper studies properties of weak reducing pairs in critical Heegaard splittings.

Proposes a new ARCH framework for Hilbert space data.

Garside groupoids, as recently introduced by Krammer, generalise Garside groups. A weak Garside group is a group that is equivalent as a category to a Garside groupoid. We show that any periodic loop in a Garside groupoid $\CG$ may be viewed as a Garside element for a certain Garside structure on another Garside groupo…

New conditions ensure points can be uniquely represented by combinations of variety elements.

End-to-end approach for weak supervision improves downstream model performance.

Nonexistence results for semilinear parabolic and hyperbolic inequalities on metric graphs

Studied SGD convergence under weak conditions.

The paper studies symplectic forms on projective limits of Banach bundles and their Darboux Theorem.

New metric structures generalize Sasakian and cosymplectic structures, proving rigidity and finding conditions.

New boundary condition for weak inverse mean curvature flow in bounded domains.

Improved multi-class AdaBoost algorithm with stronger weak learnability condition.

We formalize causal separation in portfolio theory, deriving a closed-form projected Markowitz solution.

Study curvature properties of w.a. S-manifolds with new conditions.

AIHT improves online high-dimensional quantile regression by separating support discovery and refinement.

Log minimality proven for weak K-moduli compactifications of Calabi-Yau varieties.

Study weak $f$-K-contact manifolds, finding Einstein-type metrics and solitons.

We establish the positive energy theorem for weak asymptotically anti-de Sitter initial data sets with distributional curvature under the weak dominant energy condition.

As machine learning models continue to increase in complexity, collecting large hand-labeled training sets has become one of the biggest roadblocks in practice. Instead, weaker forms of supervision that provide noisier but cheaper labels are often used. However, these weak supervision sources have diverse and unknown a…

New formulations for Ricci flows without smoothness.

The study explores new metric structures on manifolds, linking them to Einstein metrics.

Paper proves uniqueness of weak solutions for Plateau flow.

Study explores weak generalized K-contact structures in contact metric spaces.

In the context of large financial markets we formulate the notion of \emph{no asymptotic free lunch with vanishing risk} (NAFLVR), under which we can prove a version of the fundamental theorem of asset pricing (FTAP) in markets with an (even uncountably) infinite number of assets, as it is for instance the case in bond…

Study optimizes fairness in predictive models by balancing utility and separation.