We study a variant of the simple hypothesis testing problem where observed samples do not necessarily come from either of the specified distributions, but rather from a close variant of them. In this setting, we require a test that is robust to misspecification and identifies which distribution is closer in Hellinger distance. If the underlying distribution is nearly equidistant from both hypotheses, the problem becomes intractable. Our main result is a lower bound on the slack factor, which quantifies how much closer the underlying distribution must be to one hypothesis relative to the other for any test to remain robust. We also demonstrate the implications of this result for testing with respect to symmetric chi-squared distance. Finally, we study an alternative way to specify robustness, where each hypothesis is a Hellinger ball around a fixed distribution. We provide and analyze a test for this composite hypothesis testing problem.

We study the Chernoff-Stein exponent of the following binary hypothesis testing problem: Associated with each hypothesis is a set of channels. A transmitter, without knowledge of the hypothesis, chooses the vector of inputs to the channel. Given the hypothesis, from the set associated with the hypothesis, an adversary chooses channels, one for each element of the input vector. Based on the channel outputs, a detector attempts to distinguish between the hypotheses. We study the Chernoff-Stein exponent for the cases where the transmitter (i) is deterministic, (ii) may privately randomize, and (iii) shares randomness with the detector that is unavailable to the adversary. It turns out that while a memoryless transmission strategy is optimal under shared randomness, it may be strictly suboptimal when the transmitter only has private randomness.

We study the adversarial binary hypothesis testing problem [1] in the sequential setting. Associated with each hypothesis is a closed, convex set of distributions. Given the hypothesis, each observation is generated according to a distribution chosen (from the set associated with the hypothesis) by an adversary who has access to past observations. In the sequential setting, the number of observations the detector uses to arrive at a decision is variable; however there is a constraint on the expected number of observations used. We characterize the closure of the set of achievable pairs of error exponents.

We study the Chernoff-Stein exponent of the following binary hypothesis testing problem: Associated with each hypothesis is a set of channels. A transmitter, without knowledge of the hypothesis, chooses the vector of inputs to the channel. Given the hypothesis, from the set associated with the hypothesis, an adversary chooses channels, one for each element of the input vector. Based on the channel outputs, a detector attempts to distinguish between the hypotheses. We study the Chernoff-Stein exponent for the cases where the transmitter (i) is deterministic, (ii) may privately randomize, and (iii) shares randomness with the detector that is unavailable to the adversary. It turns out that while a memoryless transmission strategy is optimal under shared randomness, it may be strictly suboptimal when the transmitter only has private randomness.

Generalization error captures the degree to which the output of a learning algorithm overfits the training data. We obtain a family of bounds which generalize the bounds developed by Xu & Raginsky (2017) and Bu, Zou and Veeravalli (2019), under certain assumptions. Our bounds are based on the Rényi analogue of the Donsker-Varadhan representation of Kullback-Leibler divergence. We also obtain bounds on the probability of generalization error which recover the bounds of Esposito, Gastpar and Issa (2020). We also give a multiplicative lower bound on the expected true loss for a 0-1 loss function.