So far considered as noise in neuroscience, irregular arrhyth-mic field potential activity accounts for the majority of the signal power recorded in EEG or MEG [1, 2]. This brain activity follows a power law spectrum P (f) ∼ 1/f β in the limit of low frequencies, which is a hallmark of scale invariance. Recently, several studies [1, 3–6] have shown that the slope β (or equivalently Hurst exponent H) tends to be modulated by task performance or cognitive state (eg, sleep vs awake). These observations were confirmed in fMRI [7–9] although the short length of fMRI time series makes these findings less reliable. In this paper, to compensate for the slower sampling rate in fMRI, we extend univariate wavelet-based Hurst exponent estimator to a multivariate setting using spatial regular-ization. Next, we demonstrate the relevance of the proposed tools on resting-state fMRI data recorded in three groups of individuals once they were specifically trained to a visual discrimination task during a MEG experiment [10]. In a supervised classification framework, our multivariate approach permits to better predict the type of training the participants received as compared to their univariate counterpart.