Timezone: »

Improving Online Algorithms via ML Predictions
Manish Purohit · Zoya Svitkina · Ravi Kumar

Wed Dec 05 07:45 AM -- 09:45 AM (PST) @ Room 210 #79

In this work we study the problem of using machine-learned predictions to improve performance of online algorithms. We consider two classical problems, ski rental and non-clairvoyant job scheduling, and obtain new online algorithms that use predictions to make their decisions. These algorithms are oblivious to the performance of the predictor, improve with better predictions, but do not degrade much if the predictions are poor.

Author Information

Manish Purohit (Google)
Zoya Svitkina (Google)
Ravi Kumar (Google)

More from the Same Authors