Revisiting fair-PAC learning and the axioms of cardinal welfare
C Cousins - International Conference on Artificial …, 2023 - proceedings.mlr.press
Cardinal objectives serve as intuitive targets in fair machine learning by summarizing utility
(welfare) or disutility (malfare) $ u $ over $ g $ groups. Under standard axioms, all welfare …
(welfare) or disutility (malfare) $ u $ over $ g $ groups. Under standard axioms, all welfare …
Bavarian: Betweenness Centrality Approximation with Variance-aware Rademacher Averages
C Cousins, C Wohlgemuth, M Riondato - ACM Transactions on …, 2023 - dl.acm.org
“[A] llain Gersten, Hopfen, und Wasser”—1516 Reinheitsgebot We present Bavarian, a
collection of sampling-based algorithms for approximating the Betweenness Centrality (BC) …
collection of sampling-based algorithms for approximating the Betweenness Centrality (BC) …
Fast doubly-adaptive MCMC to estimate the gibbs partition function with weak mixing time bounds
S Haddadan, Y Zhuang, C Cousins… - Advances in Neural …, 2021 - proceedings.neurips.cc
We present a novel method for reducing the computational complexity of rigorously
estimating the partition functions of Gibbs (or Boltzmann) distributions, which arise …
estimating the partition functions of Gibbs (or Boltzmann) distributions, which arise …
DeMEtRIS: Counting (near)-Cliques by Crawling
We study the problem of approximately counting cliques and near cliques in a graph, where
the access to the graph is only available through crawling its vertices; thus typically seeing …
the access to the graph is only available through crawling its vertices; thus typically seeing …
[PDF][PDF] Fast Doubly-Adaptive MCMC to Estimate the Gibbs Partition Function with Weak Mixing Time Bounds (Supplementary material)
S Haddadan rO, Y Zhuang rO, C Cousins rO, E Upfal - proceedings.neurips.cc
We present a novel method for reducing the computational complexity of rigorously
estimating the partition functions (normalizing constants) of Gibbs (Boltzmann) distributions …
estimating the partition functions (normalizing constants) of Gibbs (Boltzmann) distributions …
[PDF][PDF] Rigorous Statistical Methods for Trustworthy Guarantees in Fair Machine Learning and Beyond
C Cousins - 2021 - cs.brown.edu
Introduction My research has always been broadly interdisciplinary, with a focus on
introducing rigorous modern statistical techniques and finite-sample concentration-of …
introducing rigorous modern statistical techniques and finite-sample concentration-of …
[PDF][PDF] Uniform Convergence, Fair Machine Learning, and Dependent Statistical Estimation
C Cousins - 2021 - cs.brown.edu
Here I present a loosely technical overview of the most significant mathematical ideas in my
work, as summarized by three simple inequalities, alongside their broad implications and …
work, as summarized by three simple inequalities, alongside their broad implications and …