79 citations · 541 across the 84 of their papers we have counts for
96 papers
Exact power indices for plurality-voting ensembles
Ilie Sarpe, Theofanis Georgakopoulos, Aristides Gionis
Plurality-voting ensembles aggregate the predictions of multiple base classifiers and output the most voted class, with ties typically broken at random. Despite the simple aggregat…
Does Muon Need Fine-Grained Spectral Shaping?
Meher Chaitanya, Tianyi Zhou, Aristides Gionis
Muon combines current and past gradients into matrix momentum. For , the idealized polar update gives every singular direction the same weight. We refer to…
CAST: Canonical Approximate Schur Tree for Approximate Cholesky on Graphs
Meher Chaitanya, Cameron Musco, Aristides Gionis
Graph-data workloads such as diffusion estimation, ranking, semi-supervised learning, and network optimization often solve many Laplacian or symmetric diagonally dominant M-matrix…
Unsupervised Multi-Scale Gromov-Wasserstein Hypergraph Alignment
Lutz Oettershagen, Honglian Wang, Aristides Gionis
We study unsupervised hypergraph alignment, where the goal is to infer node correspondences between two hypergraphs using only structural information, without node features, labels…
Integrating Local and Global Entropy for Uncertainty Quantification in LLMs
Johanne Medina, Tianyi Zhou, Keivin Isufaj +2
Large language models hallucinate confidently, making uncertainty quantification (UQ) essential for reliable deployment. Existing methods rely predominantly on token-level signals,…
Efficient Banzhaf-Based Data Valuation for -Nearest Neighbors Classification
Guangyi Zhang, Lutz Oettershagen, Lixu Wang +1
Data valuation, the task of quantifying the contribution of individual data points to model performance, has emerged as a fundamental challenge in machine learning. Game-theoretic…