arXiv research

Unified Bayesian framework for PTA data analysis tackles hierarchical model issues.

Paper proves MDS NP-hard and provides a PTAS.

This paper formalizes Uniswap v3 using PTA and FST for rigorous analysis.

Paper predicts international trade flows using machine learning and factorization models.

A new algorithm finds optimal centers for sets in metric spaces.

Decoupled GCN is shown to be equivalent to label propagation.

First proper learning algorithm for Gaussian halfspaces with matching sample and computational complexity.

New algorithm learns random neural networks efficiently.

Designs efficient algorithms to maximize the expectation of Gaussian random variables.

DiD-BCF model improves causal inference in panel data with robust non-parametric methods.

In Bipartite Correlation Clustering (BCC) we are given a complete bipartite graph $G$ with `+' and `-' edges, and we seek a vertex clustering that maximizes the number of agreements: the number of all `+' edges within clusters plus all `-' edges cut across clusters. BCC is known to be NP-hard. We present a novel approx…

In this paper, we study the stochastic combinatorial multi-armed bandit (CMAB) framework that allows a general nonlinear reward function, whose expected value may not depend only on the means of the input random variables but possibly on the entire distributions of these variables. Our framework enables a much larger c…

In this paper, we study the combinatorial multi-armed bandit problem (CMAB) with probabilistically triggered arms (PTAs). Under the assumption that the arm triggering probabilities (ATPs) are positive for all arms, we prove that a class of upper confidence bound (UCB) policies, named Combinatorial UCB with exploration …

Background: Fluctuating hearing loss is characteristic of Meniere's Disease (MD) during acute episodes. However, no reliable audiometric hallmarks are available for counselling the hearing recovery possibility. Aims/Objectives: To find parameters for predicting MD hearing outcomes. Material and Methods: We applied mach…

Novel LSTM network predicts pulsar timing residuals with few-shot data.

We give the first dimension-efficient algorithms for learning Rectified Linear Units (ReLUs), which are functions of the form $\mathbf{x} \mapsto \max(0, \mathbf{w} \cdot \mathbf{x})$ with $\mathbf{w} \in \mathbb{S}^{n-1}$. Our algorithm works in the challenging Reliable Agnostic learning model of Kalai, Kanade, and Ma…

This paper defends SVMs against poisoning attacks using DBSCAN and hardness proofs.

A new framework improves fairness in clustering and Wasserstein Barycenter problems.

New formula refutes random CSPs with fewer constraints.

Gravitational wave memory increases faster than Brownian motion in early universe and astrophysical sources.

We develop an efficient algorithm for low-rank approximation with improved approximation guarantees.