Aggregated predictors are obtained by making a set of basic predictors vote according to
some weights, that is, to some probability distribution. Randomized predictors are obtained …

Summary We move beyond Is Machine Learning Useful for Macroeconomic Forecasting? by
adding the how. The current forecasting literature has focused on matching specific …

We present data-dependent learning bounds for the general scenario of non-stationary non-
mixing stochastic processes. Our learning guarantees are expressed in terms of a data …

This paper presents the first generalization bounds for time series prediction with a non-
stationary mixing stochastic process. We prove Rademacher complexity learning bounds for …

PAC-Bayesian learning bounds are of the utmost interest to the learning community. Their
role is to connect the generalization ability of an aggregation distribution ρ ρ to its empirical …

We introduce a new recursive aggregation procedure called Bernstein Online Aggregation
(BOA). Its exponential weights include a second order refinement. The procedure is optimal …

We present a series of theoretical and algorithmic results combining the benefits of the
statistical learning approach to time series prediction with that of on-line learning. We prove …

In this work, we establish risk bounds for Empirical Risk Minimization (ERM) with both
dependent and heavy-tailed data-generating processes. We do so by extending the seminal …

We present data-dependent learning bounds for the general scenario of non-stationary non-
mixing stochastic processes. Our learning guarantees are expressed in terms of a data …

In this paper, we derive a PAC-Bayes bound on the generalisation gap, in a supervised time-
series setting for a special class of discrete-time non-linear dynamical systems. This class …