In today's clinical practice, magnetic resonance imaging (MRI) is routinely accelerated through subsampling of the associated Fourier domain. Currently, the construction of these subsampling strategies - known as experimental design - relies primarily on heuristics. We propose to learn experimental design strategies for accelerated MRI with policy gradient methods. Unexpectedly, our experiments show that a simple greedy approximation of the objective leads to solutions nearly on-par with the more general non-greedy approach. We offer a partial explanation for this phenomenon rooted in greater variance in the non-greedy objective's gradient estimates, and experimentally verify that this variance hampers non-greedy models in adapting their policies to individual MR images.

Our learning guarantees are expressed in terms of a data-dependent measure of sequential complexity and a discrepancy measure that can be estimated from data under some mild assumptions. We use our learning bounds to devise new algorithms for non-stationary time series forecasting for which we report some preliminary experimental results.

A basic question in learning theory is to identify if two distributions are identical when we have access only to examples sampled from the distributions. This basic task is considered, for example, in the context of Generative Adversarial Networks (GANs), where a discriminator is trained to distinguish between a real-life distribution and a synthetic distribution. Classically, we use a hypothesis class H and claim that the two distributions are distinct if for some h\in H the expected value on the two distributions is (significantly) different. Our starting point is the following fundamental problem: "is having the hypothesis dependent on more than a single random example beneficial". To address this challenge we define k -ary based discriminators, which have a family of Boolean k -ary functions \G .

The sample compressibility of concept classes plays an important role in learning theory, as a sufficient condition for PAC learnability, and more recently as an avenue for robust generalisation in adaptive data analysis. Whether compression schemes of size O(d) must necessarily exist for all classes of VC dimension d is unknown, but conjectured to be true by Warmuth. Recently Chalopin, Chepoi, Moran, and Warmuth (2018) gave a beautiful unlabelled sample compression scheme of size VC dimension for all maximum classes: classes that meet the Sauer-Shelah-Perles Lemma with equality. They also offered a counterexample to compression schemes based on a promising approach known as corner peeling. In this paper we simplify and extend their proof technique to deal with so-called extremal classes of VC dimension d which contain maximum classes of VC dimension d-1 .

We study the problem of reducing adversarially robust learning to standard PAC learning, i.e. the complexity of learning adversarially robust predictors using access to only a black-box non-robust learner. We give a reduction that can robustly learn any hypothesis class C using any non-robust learner A for C. The number of calls to A depends logarithmically on the number of allowed adversarial perturbations per example, and we give a lower bound showing this is unavoidable.

We formalize and extend existing definitions of backdoor-based watermarks and adversarial defenses as interactive protocols between two players. The existence of these schemes is inherently tied to the learning tasks for which they are designed. Our main result shows that for almost every discriminative learning task, at least one of the two -- a watermark or an adversarial defense -- exists. The term "almost every" indicates that we also identify a third, counterintuitive but necessary option, i.e., a scheme we call a transferable attack. By transferable attack, we refer to an efficient algorithm computing queries that look indistinguishable from the data distribution and fool all efficient defenders. To this end, we prove the necessity of a transferable attack via a construction that uses a cryptographic tool called homomorphic encryption. Furthermore, we show that any task that satisfies our notion of a transferable attack implies a cryptographic primitive, thus requiring the underlying task to be computationally complex. These two facts imply an "equivalence" between the existence of transferable attacks and cryptography. Finally, we show that the class of tasks of bounded VC-dimension has an adversarial defense, and a subclass of them has a watermark.

Classical results in statistical learning typically consider two extreme data-generating models: i.i.d. instances from an unknown distribution, or fully adversarial instances, often much more challenging statistically. To bridge the gap between these models, recent work introduced the smoothed framework, in which at each iteration an adversary generates instances from a distribution constrained to have density bounded by $\sigma^{-1}$ compared to some fixed base measure $\mu$. This framework interpolates between the i.i.d. and adversarial cases, depending on the value of $\sigma$. For the classical online prediction problem, most prior results in smoothed online learning rely on the arguably strong assumption that the base measure $\mu$ is known to the learner, contrasting with standard settings in the PAC learning or consistency literature. We consider the general agnostic problem in which the base measure is unknown and values are arbitrary. Along this direction, Block et al. showed that empirical risk minimization has sublinear regret under the well-specified assumption. We propose an algorithm R-Cover based on recursive coverings which is the first to guarantee sublinear regret for agnostic smoothed online learning without prior knowledge of $\mu$. For classification, we prove that R-Cover has adaptive regret $\tilde O(\sqrt{dT/\sigma})$ for function classes with VC dimension $d$, which is optimal up to logarithmic factors. For regression, we establish that R-Cover has sublinear oblivious regret for function classes with polynomial fat-shattering dimension growth.

Recently, Montasser at al. (2019) showed that finite VC dimension is not sufficient for proper adversarially robust PAC learning. In light of this hardness, there is a growing effort to study what type of relaxations to the adversarially robust PAC learning setup can enable proper learnability. In this work, we initiate the study of proper learning under relaxations of the worst-case robust loss. We give a family of robust loss relaxations under which VC classes are properly PAC learnable with sample complexity close to what one would require in the standard PAC learning setup. On the other hand, we show that for an existing and natural relaxation of the worst-case robust loss, finite VC dimension is not sufficient for proper learning.

We consider the classic problem of (\epsilon,\delta) -\texttt{PAC} learning a best arm where the goal is to identify with confidence 1-\delta an arm whose mean is an \epsilon -approximation to that of the highest mean arm in a multi-armed bandit setting. This problem is one of the most fundamental problems in statistics and learning theory, yet somewhat surprisingly its worst case sample complexity is not well understood. In this paper we propose a new approach for (\epsilon,\delta) -\texttt{PAC} learning a best arm. This approach leads to an algorithm whose sample complexity converges to \emph{exactly} the optimal sample complexity of (\epsilon,\delta) -learning the mean of n arms separately and we complement this result with a conditional matching lower bound. Elimination algorithms is a broad class of (\epsilon,\delta) -\texttt{PAC} best arm learning algorithms that includes many algorithms in the literature.

Recently, deep reinforcement learning (DRL) frameworks have shown potential for solving NP-hard routing problems such as the traveling salesman problem (TSP) without problem-specific expert knowledge. Although DRL can be used to solve complex problems, DRL frameworks still struggle to compete with state-of-the-art heuristics showing a substantial performance gap. This paper proposes a novel hierarchical problem-solving strategy, termed learning collaborative policies (LCP), which can effectively find the near-optimum solution using two iterative DRL policies: the seeder and reviser. The seeder generates as diversified candidate solutions as possible (seeds) while being dedicated to exploring over the full combinatorial action space (i.e., sequence of assignment action). To this end, we train the seeder's policy using a simple yet effective entropy regularization reward to encourage the seeder to find diverse solutions.