@inproceedings{Hu:2015,
author = {Hu, X and Prashanth, LA and Gyorgy, A and Szepesvari, C},
title = {(Bandit) Convex Optimization with Biased Noisy Gradient Oracles},
url = {http://opt-ml.org/oldopt/opt15/papers.html},
year = {2015}
}

Download

TY  - CPAPER
AB  - For bandit convex optimization we propose a model, where a gradient estimation oracle acts as anintermediary between a noisy function evaluation oracle and the algorithms. The algorithms cancontrol the bias-variance tradeoff in the gradient estimates. We prove lower and upper bounds forthe minimax error of algorithms that interact with the objective function by controlling this oracle.The upper bounds replicate many existing results (capturing the essence of existing proofs) while thelower bounds put a limit on the achievable performance in this setup. In particular, our results implythat no algorithm can achieve the optimal minimax error rate in stochastic bandit smooth convexoptimization.
AU  - Hu,X
AU  - Prashanth,LA
AU  - Gyorgy,A
AU  - Szepesvari,C
PY  - 2015///
TI  - (Bandit) Convex Optimization with Biased Noisy Gradient Oracles
UR  - http://opt-ml.org/oldopt/opt15/papers.html
UR  - http://hdl.handle.net/10044/1/40576
ER  - 

Download