3 accepted papers
A streaming algorithm is said to be adversarially robust if its accuracy guarantees are maintained even when the data stream is chosen maliciously, by an adaptive adversary. We establish a connection between adversarial robustness of streaming algorithms and the notion of differential privacy. This…
Optimization of machine learning models is commonly performed through stochastic gradient updates on randomly ordered training examples. This practice means that each fraction of an epoch comprises an independent random sample of the training data that may not preserve informative structure present…
We study the problem of controlling linear time-invariant systems with known noisy dynamics and adversarially chosen quadratic losses. We present the first efficient online learning algorithms in this setting that guarantee $O(\sqrt{T})$ regret under mild assumptions, where $T$ is the time horizon.…