output
20072026
most citedOn Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima

571 citations

29 papers

cs.HC2026

Designing for Interconnected Islamic Learning: A Qualitative Study of Muslim Women's Experiences with Qur'an, Hadith, and Seerah Apps

Ishrat Jahan Easha, Nabil Mosharraf Hossain, Araf Mohammad Mahbub +4

Islamic learning often depends on reading the Qur'an, Hadith, and Seerah together, yet digital tools typically separate these sources across apps, screens, and search pathways. We…

cs.SI2023★ 17 cited

Creative beyond TikToks: Investigating Adolescents' Social Privacy Management on TikTok

Nico Ebert, Tim Geppert, Joanna Strycharz +3

TikTok has been criticized for its low privacy standards, but little is known about how its adolescent users protect their privacy. Based on interviews with 54 adolescents in Switz…

math.OC2021★ 26 cited

A Near-Optimal Algorithm for Stochastic Bilevel Optimization via Double-Momentum

Prashant Khanduri, Siliang Zeng, Mingyi Hong +3

This paper proposes a new algorithm -- the \underline{S}ingle-timescale Do\underline{u}ble-momentum \underline{St}ochastic \underline{A}pprox\underline{i}matio\underline{n} (SUSTAI…

cs.LG2020★ 1 cited

A predictive model for kidney transplant graft survival using machine learning

Eric S. Pahl, W. Nick Street, Hans J. Johnson +1

Kidney transplantation is the best treatment for end-stage renal failure patients. The predominant method used for kidney quality assessment is the Cox regression-based, kidney don…

cs.LG2020

End-to-End Learning and Intervention in Games

Jiayang Li, Jing Yu, Yu Marco Nie +1

In a social system, the self-interest of agents can be detrimental to the collective good, sometimes leading to social dilemmas. To resolve such a conflict, a central designer may…

math.OC2020★ 16 cited

Mixed-Projection Conic Optimization: A New Paradigm for Modeling Rank Constraints

Dimitris Bertsimas, Ryan Cory-Wright, Jean Pauphilet

We propose a framework for modeling and solving low-rank optimization problems to certifiable optimality. We introduce symmetric projection matrices that satisfy , the matri…