Search Results for author: Cyrus Cousins

Found 7 papers, 1 papers with code

To Pool or Not To Pool: Analyzing the Regularizing Effects of Group-Fair Training on Shared Models

no code implementations29 Feb 2024 Cyrus Cousins, I. Elizabeth Kumar, Suresh Venkatasubramanian

In fair machine learning, one source of performance disparities between groups is over-fitting to groups with relatively few training samples.

Dividing Good and Better Items Among Agents with Bivalued Submodular Valuations

no code implementations6 Feb 2023 Cyrus Cousins, Vignesh Viswanathan, Yair Zick

This is surprising since for the simpler classes of bivalued additive valuations and binary submodular valuations, MNW allocations are known to be envy free up to any good (EFX).

Fast Doubly-Adaptive MCMC to Estimate the Gibbs Partition Function with Weak Mixing Time Bounds

no code implementations NeurIPS 2021 Shahrzad Haddadan, Yue Zhuang, Cyrus Cousins, Eli Upfal

While the cooling schedule in these algorithms is adaptive, the mean estimation computations use MCMC as a black-box to draw approximate samples.

An Axiomatic Theory of Provably-Fair Welfare-Centric Machine Learning

no code implementations NeurIPS 2021 Cyrus Cousins

Unfortunately, many machine-learning problems are more naturally cast as loss minimization tasks, rather than utility maximization, which complicates direct application of welfare-centric methods to fair machine learning.

BIG-bench Machine Learning Computational Efficiency

Sharp uniform convergence bounds through empirical centralization

no code implementations NeurIPS 2020 Cyrus Cousins, Matteo Riondato

We introduce the use of empirical centralization to derive novel practical, probabilistic, sample-dependent bounds to the Supremum Deviation (SD) of empirical means of functions in a family from their expectations.

MCRapper: Monte-Carlo Rademacher Averages for Poset Families and Approximate Pattern Mining

1 code implementation16 Jun 2020 Leonardo Pellegrina, Cyrus Cousins, Fabio Vandin, Matteo Riondato

To show the practical use of MCRapper, we employ it to develop an algorithm TFP-R for the task of True Frequent Pattern (TFP) mining.

Uniform Convergence Bounds for Codec Selection

no code implementations18 Dec 2018 Clayton Sanford, Cyrus Cousins, Eli Upfal

We frame the problem of selecting an optimal audio encoding scheme as a supervised learning task.

Selection bias

Cannot find the paper you are looking for? You can Submit a new open access paper.