We propose a recursive algorithm for estimating time-varying signals from a few linear measurements. The signals are assumed sparse, with unknown support, and are described by a dynamical model. In each iteration, the algorithm solves an l1-l1 minimization problem and estimates the number of measurements that it has to take at the next iteration. These estimates are computed based on recent the...

Quantum machine learning (QML) models based on parameterized quantum circuits are often highlighted as candidates for computing's near-term “killer application''. However, the understanding of empirical and generalization performance these is still in its infancy. In this paper we study how to balance between training accuracy (also called structural risk minimization...

We propose a recursive algorithm for estimating time-varying signals from a few linear measurements. The signals are assumed sparse, with unknown support, and are described by a dynamical model. In each iteration, the algorithm solves an l1-l1 minimization problem and estimates the number of measurements that it has to take at the next iteration. These estimates are computed based on recent the...

We study the general problem of an agent wishing to minimize the risk of a position at a fixed date. The agent trades in a market with a risky asset, with incomplete information, proportional transaction costs, and possibly constraints on strategies. In particular, this framework includes the problems of hedging contingent claims and maximizing utility from wealth. We obtain a minimization prob...

Large deep neural networks are powerful, but exhibit undesirable behaviors such as memorization and sensitivity to adversarial examples. In this work, we propose mixup, a simple learning principle to alleviate these issues. In essence, mixup trains a neural network on convex combinations of pairs of examples and their labels. By doing so, mixup regularizes the neural network to favor simple lin...