Performance guarantees for online learning algorithms typically take the form of regret bounds, which express that the cumulative loss overhead compared to the best expert in hindsight is small. In the common case of large but structured expert sets we typically wish to keep the regret especially small compared to simple experts, at the cost of modest additional overhead compared to more complex others. We study which such regret trade-offs can be achieved, and how. We analyse regret w.r.t. each individual expert as a multi-objective criterion in the simple but fundamental case of absolute loss. We characterise the achievable and Pareto optimal trade-offs, and the corresponding optimal strategies for each sample size both exactly for each finite horizon and asymptotically.

We study exploration in Multi-Armed Bandits (MAB) in a setting where~$k$ players collaborate in order to identify an $\epsilon$-optimal arm. Our motivation comes from recent employment of MAB algorithms in computationally intensive, large-scale applications. Our results demonstrate a non-trivial tradeoff between the number of arm pulls required by each of the players, and the amount of communication between them. In particular, our main result shows that by allowing the $k$ players to communicate \emph{only once}, they are able to learn $\sqrt{k}$ times faster than a single player. That is, distributing learning to $k$ players gives rise to a factor~$\sqrt{k}$ parallel speed-up. We complement this result with a lower bound showing this is in general the best possible. On the other extreme, we present an algorithm that achieves the ideal factor $k$ speed-up in learning performance, with communication only logarithmic in~$1/\epsilon$.

We study low rank matrix and tensor completion and propose novel algorithms that employ adaptive sampling schemes to obtain strong performance guarantees for these problems. Our algorithms exploit adaptivity to identify entries that are highly informative for identifying the column space of the matrix (tensor) and consequently, our results hold even when the row space is highly coherent, in contrast with previous analysis of matrix completion. In the absence of noise, we show that one can exactly recover a $n \times n$ matrix of rank $r$ using $O(r^2 n \log(r))$ observations, which is better than the best known bound under random sampling. We also show that one can recover an order $T$ tensor using $O(r^{2(T-1)}T^2 n \log(r))$. For noisy recovery, we show that one can consistently estimate a low rank matrix corrupted with noise using $O(nr \textrm{polylog}(n))$ observations. We complement our study with simulations that verify our theoretical guarantees and demonstrate the scalability of our algorithms.

Finite-State Transducers (FST) are a standard tool for modeling paired input-output sequences and are used in numerous applications, ranging from computational biology to natural language processing. Recently Balle et al. presented a spectral algorithm for learning FST from samples of aligned input-output sequences. In this paper we address the more realistic, yet challenging setting where the alignments are unknown to the learning algorithm. We frame FST learning as finding a low rank Hankel matrix satisfying constraints derived from observable statistics. Under this formulation, we provide identifiability results for FST distributions. Then, following previous work on rank minimization, we propose a regularized convex relaxation of this objective which is based on minimizing a nuclear norm penalty subject to linear constraints and can be solved efficiently.

We consider the stochastic approximation problem where a convex function has to be minimized, given only the knowledge of unbiased estimates of its gradients at certain points, a framework which includes machine learning methods based on the minimization of the empirical risk. We focus on problems without strong convexity, for which all previously known algorithms achieve a convergence rate for function values of $O(1/\sqrt{n})$. We consider and analyze two algorithms that achieve a rate of $O(1/n)$ for classical supervised learning problems. For least-squares regression, we show that averaged stochastic gradient descent with constant step-size achieves the desired rate. For logistic regression, this is achieved by a simple novel stochastic gradient algorithm that (a) constructs successive local quadratic approximations of the loss functions, while (b) preserving the same running time complexity as stochastic gradient descent. For these algorithms, we provide a non-asymptotic analysis of the generalization error (in expectation, and also in high probability for least-squares), and run extensive experiments showing that they often outperform existing approaches.

We consider the online Principal Component Analysis (PCA) where contaminated samples (containing outliers) are revealed sequentially to the Principal Components (PCs)estimator. Due to their sensitiveness to outliers, previous online PCA algorithms fail in this case and their results can be arbitrarily skewed by the outliers. Herewe propose the online robust PCA algorithm, which is able to improve the PCs estimation upon an initial one steadily, even when faced with a constant fraction of outliers. We show that the final result of the proposed online RPCA has an acceptable degradation from the optimum. Actually, under mild conditions, online RPCA achieves the maximal robustness with a 50% breakdown point. Moreover, online RPCA is shown to be efficient for both storage and computation, sinceit need not re-explore the previous samples as in traditional robust PCA algorithms.

We propose a family of maximum mean discrepancy (MMD) kernel two-sample tests that have low sample complexity and are consistent. The test has a hyperparameter that allows one to control the tradeoff between sample complexity and computational time. Our family of tests, which we denote as B-tests, is both computationally and statistically efficient, combining favorable properties of previously proposed MMD two-sample tests. It does so by better leveraging samples to produce low variance estimates in the finite sample case, while avoiding a quadratic number of kernel evaluations and complex null-hypothesis approximation as would be required by tests relying on one sample U-statistics. The B-test uses a smaller than quadratic number of kernel evaluations and avoids completely the computational burden of complex null-hypothesis approximation while maintaining consistency and probabilistically conservative thresholds on Type I error. Finally, recent results of combining multiple kernels transfer seamlessly to our hypothesis test, allowing a further increase in discriminative power and decrease in sample complexity.

Multi-armed bandit problems are receiving a great deal of attention because they adequately formalize the exploration-exploitation trade-offs arising in several industrially relevant applications, such as online advertisement and, more generally, recommendation systems. In many cases, however, these applications have a strong social component, whose integration in the bandit algorithm could lead to a dramatic performance increase. For instance, we may want to serve content to a group of users by taking advantage of an underlying network of social relationships among them. In this paper, we introduce novel algorithmic approaches to the solution of such networked bandit problems. More specifically, we design and analyze a global strategy which allocates a bandit algorithm to each network node (user) and allows it to “share” signals (contexts and payoffs) with the neghboring nodes. We then derive two more scalable variants of this strategy based on different ways of clustering the graph nodes. We experimentally compare the algorithm and its variants to state-of-the-art methods for contextual bandits that do not use the relational information. Our experiments, carried out on synthetic and real-world datasets, show a marked increase in prediction performance obtained by exploiting the network structure.

Motivated by various applications in machine learning, the problem of minimizing a convex smooth loss function with trace norm regularization has received much attention lately. Currently, a popular method for solving such problem is the proximal gradient method (PGM), which is known to have a sublinear rate of convergence. In this paper, we show that for a large class of loss functions, the convergence rate of the PGM is in fact linear. Our result is established without any strong convexity assumption on the loss function. A key ingredient in our proof is a new Lipschitzian error bound for the aforementioned trace norm-regularized problem, which may be of independent interest.

An important challenge in Markov decision processes is to ensure robustness with respect to unexpected or adversarial system behavior while taking advantage of well-behaving parts of the system. We consider a problem setting where some unknown parts of the state space can have arbitrary transitions while other parts are purely stochastic. We devise an algorithm that is adaptive to potentially adversarial behavior and show that it achieves similar regret bounds as the purely stochastic case.