100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models: [Experiments & Analysis]

Yeounoh Chung, Rushabh Desai, Jian He, Yu Xiao, Thibaud Hottelier, Yves-Laurent Kom Samo, Pushkar Khadilkar, Xianshun Chen, Sam Idicula, Fatma Özcan 0001, Alon Y. Halevy, Yannis Papakonstantinou. 100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models: [Experiments & Analysis]. Proc. ACM Manag. Data, 4(3), 2026. [doi]

Authors

Yeounoh Chung

This author has not been identified. Look up 'Yeounoh Chung' in Google

Rushabh Desai

This author has not been identified. Look up 'Rushabh Desai' in Google

Jian He

This author has not been identified. Look up 'Jian He' in Google

Yu Xiao

This author has not been identified. Look up 'Yu Xiao' in Google

Thibaud Hottelier

This author has not been identified. Look up 'Thibaud Hottelier' in Google

Yves-Laurent Kom Samo

This author has not been identified. Look up 'Yves-Laurent Kom Samo' in Google

Pushkar Khadilkar

This author has not been identified. Look up 'Pushkar Khadilkar' in Google

Xianshun Chen

This author has not been identified. Look up 'Xianshun Chen' in Google

Sam Idicula

This author has not been identified. Look up 'Sam Idicula' in Google

Fatma Özcan 0001

This author has not been identified. Look up 'Fatma Özcan 0001' in Google

Alon Y. Halevy

This author has not been identified. Look up 'Alon Y. Halevy' in Google

Yannis Papakonstantinou

This author has not been identified. Look up 'Yannis Papakonstantinou' in Google