arXiv research

One-Class Boundary Peeling detects outliers efficiently and robustly.

Study peels tensor equations on Schwarzschild spacetime.

New model explains neural collapse and limits on minority classes in imbalanced datasets.

New method for causal discovery using peeling algorithms for various data types.

Study of Dirac fields on Kerr spacetimes using peeling method.

New supervised and unsupervised NFLTs for elliptical distributions.

Faster algorithm for generalized mean densest subgraph problem.

A new algorithm reduces graph complexity for better dense subgraph analysis.

In this paper we study an experimentally-observed connection between two seemingly unrelated processes, one from computational geometry and the other from differential geometry. The first one (which we call "grid peeling") is the convex-layer decomposition of subsets $G\subset \mathbb Z^2$ of the integer grid, previous…

In this paper, we show that the peeling property still holds for Bondi-Sachs metrics with nonzero cosmological constant under the boundary condition given by Sommerfeld's radiation condition together with three nontrivial $Λ$-independent functions $B$, $a$, $b$. This should indicate the new boundary condition is natura…

The paper uncovers symmetries in large language models through layer-peeled optimization.

New method speeds up solving L0-regularized least-squares problems.

Study of Bondi-Sachs formalism for massless scalar field with zero cosmological constant.

Proposes a privacy-preserving sign selection method for distributed systems.

Paper explains neural collapse in neural networks using a new model.

The paper develops a robust algorithm for contextual bandits with heavy-tailed rewards.

This paper investigates graph clustering in the planted cluster model in the presence of {\em small clusters}. Traditional results dictate that for an algorithm to provably correctly recover the clusters, {\em all} clusters must be sufficiently large (in particular, $\tildeΩ(\sqrt{n})$ where $n$ is the number of nodes …

Significant improvements in regret analysis for adaptive online learning problems.

A lamination of a graph embedded on a surface is a collection of pairwise disjoint non-contractible simple closed curves drawn on the graph. In the case when the surface is a sphere with three punctures (a.k.a. a pair of pants), we first identify the lamination space of a graph embedded on that surface as a lattice pol…

The Sample Compression Conjecture of Littlestone & Warmuth has remained unsolved for over two decades. This paper presents a systematic geometric investigation of the compression of finite maximum concept classes. Simple arrangements of hyperplanes in Hyperbolic space, and Piecewise-Linear hyperplane arrangements, are …

Paper introduces efficient top-k selection with differential privacy.

Starting from an arbitrary sequence of polygons whose total perimeter is $2n$, we can build an (oriented) surface by pairing their sides in a uniform fashion. Chmutov and Pittel (arXiv:1503.01816) have shown that, regardless of the configuration of polygons we started with, the degree sequence of the graph obtained thi…

Paper proposes a privacy-preserving method to control false discoveries.

Mixtures of Mallows models are a popular generative model for ranking data coming from a heterogeneous population. They have a variety of applications including social choice, recommendation systems and natural language processing. Here we give the first polynomial time algorithm for provably learning the parameters of…

A new iterative low complexity algorithm has been presented for computing the Walsh-Hadamard transform (WHT) of an $N$ dimensional signal with a $K$-sparse WHT, where $N$ is a power of two and $K = O(N^α)$, scales sub-linearly in $N$ for some $0 < α< 1$. Assuming a random support model for the non-zero transform domain…

The paper analyzes generalization in deep contrastive learning.

New method reduces multi-armed bandit regret to near-optimal levels.

Study explains how noisyGD with DP improves feature learning despite high dimensionality.

We consider the estimation of treatment effects in settings when multiple treatments are assigned over time and treatments can have a causal effect on future outcomes or the state of the treated unit. We propose an extension of the double/debiased machine learning framework to estimate the dynamic effects of treatments…

New method TLC improves transductive learning bounds.

Logarithmic corrections to Price's law near black hole event horizon.

Gradient descent converges to a small neighborhood of the true parameter in logistic regression with Gaussian design.