307 citations · 693 across the 70 of their papers we have counts for
8 papers · 1 filter
Improved Deep Neural Network Generalization Using m-Sharpness-Aware Minimization
Kayhan Behdin, Qingquan Song, Aman Gupta +4
Modern deep learning models are over-parameterized, where the optimization setup strongly affects the generalization performance. A key element of reliable optimization for these s…
Multi-Task Learning for Sparsity Pattern Heterogeneity: Statistical and Computational Perspectives
Kayhan Behdin, Gabriel Loewinger, Kenneth T. Kishida +2
We consider a problem in Multi-Task Learning (MTL) where multiple linear models are jointly trained on a collection of datasets ("tasks"). A key novelty of our framework is that it…
A Light-speed Linear Program Solver for Personalized Recommendation with Diversity Constraints
Haoyue Wang, Miao Cheng, Kinjal Basu +3
We study a structured linear program (LP) that emerges in the need of ranking candidates or items in personalized recommender systems. Since the candidate set is only known in real…
Pushing the limits of fairness impossibility: Who's the fairest of them all?
Brian Hsu, Rahul Mazumder, Preetam Nandy +1
The impossibility theorem of fairness is a foundational result in the algorithmic fairness literature. It states that outside of special cases, one cannot exactly and simultaneousl…
Quant-BnB: A Scalable Branch-and-Bound Method for Optimal Decision Trees with Continuous Features
Rahul Mazumder, Xiang Meng, Haoyue Wang
Decision trees are one of the most useful and popular methods in the machine learning toolbox. In this paper, we consider the problem of learning optimal decision trees, a combinat…
ForestPrune: Compact Depth-Controlled Tree Ensembles
Brian Liu, Rahul Mazumder
Tree ensembles are powerful models that achieve excellent predictive performances, but can grow to unwieldy sizes. These ensembles are often post-processed (pruned) to reduce memor…