arXiv research

Paper studies fundamental limits of communication in distributed learning.

Aggregation distorts causal discovery results but recovery is possible with partial linearity or prior.

New aggregation method improves GNN robustness to structural perturbations.

Improved defense against data poisoning attacks by aggregating smaller subsets.

New bounds on generalization error for distributed learning using rate-distortion theory.

Study optimal risk sharing in decentralized peer-to-peer markets with robust risk measures.

Study on costs of manipulating AMM-based price oracles.

Distortion risk measures are extensively used in finance and insurance applications because of their appealing properties. We present three methods to construct new class of distortion functions and measures. The approach involves the composting methods, the mixing methods and the approach that based on the theory of c…

Algorithm for online decision making with unknown dynamics and aggregate feedback.

Paper provides new bounds for risk aggregation and sharing.

Deep Partition Aggregation defends against poisoning attacks with provable certificates.

UVeQFed tackles FL model compression over limited channels.

Study shows how high-budget agents can manipulate prediction markets.

The paper analyzes risk measures and optimal reserve allocation strategies.

We extend the recently introduced theory of Lovasz-Bregman (LB) divergences (Iyer & Bilmes 2012) in several ways. We show that they represent a distortion between a "score" and an "ordering", thus providing a new view of rank aggregation and order based clustering with interesting connections to web ranking. We show ho…

We extend the recently introduced theory of Lovasz-Bregman (LB) divergences (Iyer & Bilmes, 2012) in several ways. We show that they represent a distortion between a 'score' and an 'ordering', thus providing a new view of rank aggregation and order based clustering with interesting connections to web ranking. We show h…

The paper studies risk-sharing allocations for risk-seeking agents using a common distortion risk measure.

We consider the problem of learning a neural network classifier. Under the information bottleneck (IB) principle, we associate with this classification problem a representation learning problem, which we call "IB learning". We show that IB learning is, in fact, equivalent to a special class of the quantization problem.…

Federated learning promises to make machine learning feasible on distributed, private datasets by implementing gradient descent using secure aggregation methods. The idea is to compute a global weight update without revealing the contributions of individual users. Current practical protocols for secure aggregation work…

CDP reduces point cloud dimensions by preserving detour-induced local non-convexity.

FedCONST adapts update magnitudes to enhance feature generalization in FL.

Vertex distortion detects if a knot is unknot.

A new method reduces preference distortion in LLM alignment.

Algorithm finds optimal affine transformation to minimize overall distortion.

We decompose the squared price-of-risk premium into three components: intervention-stable premium, confounding wedge, and information loss.

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

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…

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

Computed distortion coefficients for the α-Grushin plane.

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

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 …

ReGEN-TAD detects anomalies in financial time series with interpretable models.

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…

We propose a generic model for multiple choice situations in the presence of herding and compare it with recent empirical results from a Web-based music market experiment. The model predicts a phase transition between a weak imitation phase and a strong imitation, `fashion' phase, where choices are driven by peer press…

The distortion of a curve is the supremum, taken over distinct pairs of points of the curve, of the ratio of arclength to spatial distance between the points. Gromov asked in 1981 whether a curve in every knot type can be constructed with distortion less than a universal constant C. Answering Gromov's question seems to…

The study shows exponential distortion in virtually special groups containing free subgroups.

Estimates rate-distortion function for large datasets using neural networks.

We construct 2-dimensional CAT(-1) groups which contain free subgroups with arbitrary iterated exponential distortion, and with distortion higher than any iterated exponential.

New coding theorem shows achievable rate matches theoretical limit.

Paper proposes a new black-box attack approach to minimize visual distortion.

Sharp bounds for distortion risk metrics under uncertain distributions.

Study dynamic risk measures and performance indices using distortion functions.

New bounds on knot distortion and Seifert surface properties.

Efficiently simulates risk budgeting portfolios using novel algorithms.