collaborators

6 papers

cs.DC2026

Large-Scale Regularized Matching on GPU Clusters

Aida Rahmattalabi, Gregory Dexter, Sanjana Garg +5

Production decision systems such as ad allocation or content matching involve millions of users and thousands of items, reducing to large-scale linear programs with sparse block-di…

cs.LG2026

Robust Batch-Level Query Routing for Large Language Models under Cost and Capacity Constraints

Jelena Markovic-Voronov, Kayhan Behdin, Yuanda Xu +3

We study the problem of routing queries to large language models (LLMs) under cost, GPU resources, and concurrency constraints. Prior per-query routing methods often fail to contro…

cs.DC2026

DuaLip-GPU Technical Report

Gregory Dexter, Aida Rahmattalabi, Sanjana Garg +6

Large-scale linear programs (LPs) arise in many decision systems, including ranking, allocation, and matching problems that must be solved repeatedly at massive scale. Prior work s…

cs.IR2025

Scaling Down, Serving Fast: Compressing and Deploying Efficient LLMs for Recommendation Systems

Kayhan Behdin, Ata Fatahibaarzi, Qingquan Song +17

Large language models (LLMs) have demonstrated remarkable performance across a wide range of industrial applications, from search and recommendation systems to generative tasks. Al…

cs.LG2025

End-to-end Feature Selection Approach for Learning Skinny Trees

Shibal Ibrahim, Kayhan Behdin, Rahul Mazumder

We propose a new optimization-based approach for feature selection in tree ensembles, an important problem in statistics and machine learning. Popular tree ensemble toolkits e.g.,…

cs.LG2024

Efficient user history modeling with amortized inference for deep learning recommendation models

Lars Hertel, Neil Daftary, Fedor Borisyuk +2

We study user history modeling via Transformer encoders in deep learning recommendation models (DLRM). Such architectures can significantly improve recommendation quality, but usua…