arXiv research

New method optimizes lossy compression models more effectively.

We solve the vector embedding problem by minimizing total distortion under constraints.

Study optimal reinsurance contracts to prevent moral hazard under non-concave premium principles.

Method determines asset prices in incomplete markets to optimize portfolios.

The paper analyzes extreme risk measures with limited distributional information.

The paper studies robust risk measures with linear penalties under uncertain distributions.

The Madry Lab recently hosted a competition designed to test the robustness of their adversarially trained MNIST model. Attacks were constrained to perturb each pixel of the input image by a scaled maximal $L_\infty$ distortion $ε$ = 0.3. This discourages the use of attacks which are not optimized on the $L_\infty$ dis…

New bounds for optimal transport using Gaussian processes and rate-distortion functions.

The paper calculates bounds for risk metrics and entropies under partial information constraints.

Optimizes riskmetrics with uncertainty, making complex problems simpler.

Develops a power-calibrated framework for LLM watermarking, optimizing tradeoffs between detectability and distortion.

Proposes ITISC for clustering with minimized worst-case expected distortions.

Optimal risk sharing found for heterogeneous risk attitudes using distortion risk measures.

Registration, which aims to find an optimal 1-1 correspondence between shapes, is an important process in different research areas. Conformal mappings have been widely used to obtain a diffeomorphism between shapes that minimizes angular distortion. Conformal registrations are beneficial since it preserves the local ge…

This paper addresses the challenges in classifying textual data obtained from open online platforms, which are vulnerable to distortion. Most existing classification methods minimize the overall classification error and may yield an undesirably large type I error (relevant textual messages are classified as irrelevant)…

New approach connects robust learning to privacy issues.

Paper proposes robust risk measures for non-negative risks with partial information.

New insights into image compression trade-offs with private randomness.

This paper studies the problem of optimal investment with CRRA (constant, relative risk aversion) preferences, subject to dynamic risk constraints on trading strategies. The market model considered is continuous in time and incomplete. the prices of financial assets are modeled by Itô processes. The dynamic risk constr…

Study bounds on curvature for special Finsler metrics.

This study analyzes communication constraints in MoE architectures using information theory.

HAMD optimizes cubic portfolios without quadratization, achieving better results.

A robust method for decomposing spectral peaks robust to distortion and interference.

Lower bounds on Bayes risk for realizable models derived using information theory.

Method flattens complex surfaces with consistent density and shape.

A method for camera calibration using heatmap regression for fisheye images.

The paper uses thermodynamics to improve machine learning representation quality.

Comonotonic allocations are restored under certain constraints, improving risk-sharing.

Develops a unified framework for computing n-dimensional quasi-conformal mappings.

Vertex distortion detects if a knot is unknot.

There is a consensus that human and non-human subjects experience temporal distortions in many stages of their perceptual and decision-making systems. Similarly, intertemporal choice research has shown that decision-makers undervalue future outcomes relative to immediate ones. Here we combine techniques from informatio…

Extends likelihood ratio exponential families to analyze various optimization methods.

Algorithm finds optimal affine transformation to minimize overall distortion.

FedCONST adapts update magnitudes to enhance feature generalization in FL.

We propose a partially linear additive Gaussian graphical model (PLA-GGM) for the estimation of associations between random variables distorted by observed confounders. Model parameters are estimated using an $L_1$-regularized maximal pseudo-profile likelihood estimator (MaPPLE) for which we prove $\sqrt{n}$-sparsisten…

Vertex distortion measures how far lattice knots deviate from straight lines.

MLDL preserves manifold geometry in vector transformations.

We consider the problem of distortion minimal morphing of $n$-dimensional compact connected oriented smooth manifolds without boundary embedded in $\R^{n+1}$. Distortion involves bending and stretching. In this paper, minimal distortion (with respect to stretching) is defined as the infinitesimal relative change in vol…

This paper shows how to calculate risk measures for sums of two counter-monotonic risks.

Most distortion correction methods focus on simple forms of distortion, such as radial or linear distortions. These works undistort images either based on measurements in the presence of a calibration grid, or use multiple views to find point correspondences and predict distortion parameters. When possible distortions …

Study distortion risk measures for step-weighted distributions.

The distortion of a curve measures the maximum arc/chord length ratio. Gromov showed any closed curve has distortion at least pi/2 and asked about the distortion of knots. Here, we prove that any nontrivial tame knot has distortion at least 5pi/3; examples show that distortion under 7.16 suffices to build a trefoil kno…

Computed distortion coefficients for the α-Grushin plane.

Study on risk measures using distorted Choquet integrals with random distortions.

Donald Trump was lagging behind in nearly all opinion polls leading up to the 2016 US presidential election, but he surprisingly won the election. This raises the following important questions: 1) why most opinion polls were not accurate in 2016? and 2) how to improve the accuracies of opinion polls? In this paper, we …

We study a generalized family of stochastic orders, semiparametrized by a distortion function H, namely H-distorted stochastic dominance, which may determine a continuum of dominance relations from the first- to the second-order stochastic dominance (and beyond). Such a family is especially suitable for representing a …

Risk-averse model uncertainty framework for safe reinforcement learning.

We show that an entire branched cover of finite distortion cannot have a compact branch set if its distortion satisfies a certain asymptotic growth condition. We furthermore show that this bound is strict by constructing an entire, continuous, open and discrete mapping of finite distortion which is piecewise smooth, ha…