arXiv research

New method optimizes policies without assuming known link functions between preferences and rewards.

We consider the group of unrestricted virtual braids, describe its structure and explore its relations with fused links. Also, we define the groups of flat virtual braids and virtual Gauss braids and study some of their properties, in particular their linearity.

R. Kashaev and N. Reshetikhin introduced the notion of holonomy braiding extending V. Turaev's homotopy braiding to describe the behavior of cyclic representations of the unrestricted quantum group $U_qsl_2$ at root of unity. In this paper, using quandles and biquandles we develop a general theory for Reshetikhin-Turae…

We study learning problems involving arbitrary classes of functions $F$, distributions $X$ and targets $Y$. Because proper learning procedures, i.e., procedures that are only allowed to select functions in $F$, tend to perform poorly unless the problem satisfies some additional structural property (e.g., that $F$ is co…

New tests for VaR and ES forecast encompassing using flexible link functions.

This paper considers the optimal dividend payment problem in piecewise-deterministic compound Poisson risk models. The objective is to maximize the expected discounted dividend payout up to the time of ruin. We provide a comparative study in this general framework of both restricted and unrestricted payment schemes, wh…

MoMA improves model-based RL by using unrestricted policy classes.

Neural networks are vulnerable to adversarially-constructed perturbations of their inputs. Most research so far has considered perturbations of a fixed magnitude under some $l_p$ norm. Although studying these attacks is valuable, there has been increasing interest in the construction of (and robustness to) unrestricted…

New algorithms ensure fair selection in combinatorial semi-bandit with unrestricted delays.

Study compares adaptive vs fixed query learning methods.

Adversarial examples are typically constructed by perturbing an existing data point within a small matrix norm, and current defense methods are focused on guarding against this type of attack. In this paper, we propose unrestricted adversarial examples, a new threat model where the attackers are not restricted to small…

Study of unrestricted virtual braid groups and their properties.

We propose a novel approach for generating unrestricted adversarial examples by manipulating fine-grained aspects of image generation. Unlike existing unrestricted attacks that typically hand-craft geometric transformations, we learn stylistic and stochastic modifications leveraging state-of-the-art generative models. …

The rebmix package provides R functions for random univariate and multivariate finite mixture model generation, estimation, clustering and classification. The paper is focused on multivariate normal mixture models with unrestricted variance-covariance matrices. The objective is to show how to generate datasets for a kn…

Generative models create indistinguishable adversarial objects for object detection.

New methods reduce extrapolation errors in feature importance.

The study extends classical results on harmonic functions to Riemannian manifolds with non-tangential boundary limits.

Recently, it is proven that generalized Robertson-Walker space-times in all orthogonal subspaces of Gray's decomposition but one(unrestricted) are perfect fluid space-times. GRW space-times in the unrestricted subspace are identified by having constant scalar curvature. Generalized quasi-Einstein GRW space-times have a…

We consider an insurance entity endowed with an initial capital and a surplus process modelled as a Brownian motion with drift. It is assumed that the company seeks to maximise the cumulated value of expected discounted dividends, which are declared or paid in a foreign currency. The currency fluctuation is modelled as…

Motivated by the resurgence of neural networks in being able to solve complex learning tasks we undertake a study of high depth networks using ReLU gates which implement the function $x \mapsto \max\{0,x\}$. We try to understand the role of depth in such neural networks by showing size lowerbounds against such network …

This paper tackles the computational complexity of finding approximate stationary points in non-convex optimization.

A stochastic model helps maintain insufficiently funded pension funds.

Thanks to recent advances in deep neural networks (DNNs), face recognition systems have become highly accurate in classifying a large number of face images. However, recent studies have found that DNNs could be vulnerable to adversarial examples, raising concerns about the robustness of such systems. Adversarial exampl…

Study improves cryptocurrency price prediction using deep learning with trading and social media indicators.

Study on framed surfaces with bounds on Morse index.

We provide a new approach to training neural models to exhibit transparency in a well-defined, functional manner. Our approach naturally operates over structured data and tailors the predictor, functionally, towards a chosen family of (local) witnesses. The estimation problem is setup as a co-operative game between an …

ScoreAG generates unrestricted adversarial images maintaining semantic integrity.

Least Squares Estimators are suboptimal for 5D convex functions.

The article has been withdrawn by the author. Wolfgang Lueck and Peter Linnell pointed out that the proof of Lemma 3.8 does not apply to the unrestricted case of wreath product. It is not clear at this stage how to complete the proof of Theorem 3.1 using the present version of Lemma 3.8. The valid results originating f…

New method estimates sparse covariance matrices in logit mixtures.

Defines a new 2+1-G-HQFT using graded skein modules.

Polynomial-time DP algorithm for learning Gaussians with matching sample complexity.

This paper proposes BAT to balance accuracy and robustness in adversarial training.

PGNs dynamically infer and use graph structures to improve model generalization.

Paper introduces methods for more reliable probabilistic predictions with confidence intervals.

Algorithm tackles large-scale portfolio optimization with higher moments, improving computational efficiency.

Study on the Euler-Plateau energy with elastic modulus, focusing on minimizers and critical surfaces.

A new way to describe correlation matrices makes modeling easier.

For links with vanishing pairwise linking numbers, the link components bound pairwise disjoint surfaces in $B^{4}$. In this paper, we describe the set of genera of such surfaces in terms of the $h$-function, which is a link invariant from Heegaard Floer homology. In particular, we use the $h$-function to give lower bou…

Deep NLP models benefit from underlying structures in the data---e.g., parse trees---typically extracted using off-the-shelf parsers. Recent attempts to jointly learn the latent structure encounter a tradeoff: either make factorization assumptions that limit expressiveness, or sacrifice end-to-end differentiability. Us…

ZSPO optimizes RL from unknown link functions using human feedback.

New link invariants from diagram colorings match link widths.

100 years ago exactly, in 1906, Hartogs published a celebrated extension phenomenon (birth of Several Complex Variables), whose global counterpart was stated in full generality later by Osgood (1929): holomorphic functions in a connected neighborhood V(bD) of a connected boundary bD contained in C^n (n >= 2) do extend …

Formula for arborescent link tails using theta functions.

We study Heegaard Floer homology and various related invariants (such as the $h$-function) for two-component L-space links with linking number zero. For such links, we explicitly describe the relationship between the $h$-function, the Sato-Levine invariant and the Casson invariant. We give a formula for the Heegaard Fl…

Paper computes link determinants using Fourier-Hadamard transforms.

The paper explores fibered and quasi-positive links, introducing new families and invariants.

We give a necessary condition for a meromorphic function in several variables to give rise to a Milnor fibration of the local link (respectively of the link at infinity). In the case of two variables we give some necessary and sufficient conditions for the local link (respectively the link at infinity) to be fibred.