activity
20192026
most citedEmpirical Study of the Benefits of Overparameterization in Learning Latent Variable Models

6 citations · 8 across the 10 of their papers we have counts for

collaborators
Showing cs.DSShow all

6 papers · 1 filter

cs.DS2026

A Better-than-2 Approximation for k-Median Part I: The Power of General Bids

Rares-Darius Buhai, Vincent Cohen-Addad, Henry Fleischmann +6

The Greedy algorithm of Jain, Mahdian, Markakis, Saberi, and Vazirani was the best Lagrangian-multiplier-preserving (LMP) approximation algorithm for facility location, and thus th…

cs.DS2026

A Better-than- Approximation for -Median Part II: Stable Instances

Rares-Darius Buhai, Vincent Cohen-Addad, Henry Fleischmann +6

We consider the -median problem on general metric spaces, subject to the condition that the instances are -stable (i.e., the optimal solution using centers has a cost a…

cs.DS2025

Finding Colorings in One-Sided Expanders

Rares-Darius Buhai, Yiding Hua, David Steurer +1

We establish new algorithmic guarantees with matching hardness results for coloring and independent set problems in one-sided expanders and related classes of graphs. For example,…

cs.DS2024

Dimension Reduction via Sum-of-Squares and Improved Clustering Algorithms for Non-Spherical Mixtures

Prashanti Anderson, Mitali Bafna, Rares-Darius Buhai +2

We develop a new approach for clustering non-spherical (i.e., arbitrary component covariances) Gaussian mixture models via a subroutine, based on the sum-of-squares method, that fi…

cs.DS2024★ 1 cited

Semirandom Planted Clique and the Restricted Isometry Property

Jarosław Błasiok, Rares-Darius Buhai, Pravesh K. Kothari +1

We give a simple, greedy -time algorithm to list-decode planted cliques in a semirandom model introduced in [CSV17] (following [FK01]) that succeeds when…

cs.DS2022

Algorithms approaching the threshold for semi-random planted clique

Rares-Darius Buhai, Pravesh K. Kothari, David Steurer

We design new polynomial-time algorithms for recovering planted cliques in the semi-random graph model introduced by Feige and Kilian 2001. The previous best algorithms for this mo…