Timezone: »

 
Oral
Multi-Fidelity Black-Box Optimization with Hierarchical Partitions
Rajat Sen · kirthevasan kandasamy · Sanjay Shakkottai

Fri Jul 13 01:00 AM -- 01:10 AM (PDT) @ A5
in Online Learning 4 »

Motivated by settings such as hyper-parameter tuning and physical simulations, we consider the problem of black-box optimization of a function. Multi-fidelity techniques have become popular for applications where exact function evaluations are expensive, but coarse (biased) approximations are available at much lower cost. A canonical example is that of hyper-parameter selection in a learning algorithm. The learning algorithm can be trained for fewer iterations -- this results in a lower cost, but its validation error is only coarsely indicative of the same if the algorithm had been trained till completion. We incorporate the multi-fidelity setup into the powerful framework of black-box optimization through hierarchical partitioning. We develop tree-search based multi-fidelity algorithms with theoretical guarantees on simple regret. We finally demonstrate the performance gains of our algorithms on both real and synthetic datasets.

[ PDF]  [ Video] 

Author Information

Rajat Sen (University of Texas at Austin)

I am a 4th year PhD. student in WNCG, UT Austin. I am advised by [Dr. Sanjay Shakkottai](http://users.ece.utexas.edu/~shakkott/Sanjay_Shakkottai/Contact.html). I received my Bachelors degree in ECE, IIT Kharagpur in 2013. I have spent most of my childhood in Durgapur and Kolkata, West Bengal, India. My research interests include online learning (especially Multi-Armed Bandit problems), causality, learning in queueing systems, recommendation systems and social networks. I like to work on real-world problems that allow rigorous theoretical analysis.

kirthevasan kandasamy (CMU)
Sanjay Shakkottai (University of Texas at Austin)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors