Search

Despite the increasing importance of multiple priors in various domains of economics and the significant theoretical advances concerning them, choice-based incentive-compatible multiple-prior elicitation largely remains an open problem. This paper develops a solution, comprising a preference-based identification of a subject’s probability interval for an event, and two procedures for eliciting it. The method does not rely on specific assumptions about subjects’ ambiguity attitudes or probabilistic sophistication. To demonstrate its feasibility, we implement it in two incentivized experiments to elicit the multiple-prior equivalent of subjects’ cumulative distribution functions over continuous-valued sources of uncertainty. We find a predominance of non-degenerate probability intervals among subjects for all explored sources, with intervals being wider for less familiar sources. Finally, we use our method to undertake the first elicitation of the mixture coefficient in the Hurwicz α-maxmin EU model that fully controls for beliefs.

International audience; Estimating the maximum number of concurrent speakers from single-channel mixtures is a challenging problem and an essential first step to address various audio-based tasks such as blind source separation, speaker diarization, and audio surveillance. We propose a unifying probabilistic paradigm, where deep neural network architectures are used to infer output posterior distributions. These probabilities are in turn processed to yield discrete point estimates. Designing such architectures often involves two important and complementary aspects that we investigate and discuss. First, we study how recent advances in deep architectures may be exploited for the task of speaker count estimation. In particular, we show that convolutional recurrent neural networks outperform recurrent networks used in a previous study when adequate input features are used. Even for short segments of speech mixtures, we can estimate up to five speakers, with a significantly lower error than other methods. Second, through comprehensive evaluation, we compare the best-performing method to several baselines, as well as the influence of gain variations, different data sets, and reverberation. The output of our proposed method is compared to human performance. Finally, we give insights into the strategy used by our proposed method.

Agents make predictions based on similar past cases, while also learning the relative importance of various attributes in judging similarity. We ask whether the resulting "empirical similarity" is unique, and how easy it is to find it. We show that with many observations and few relevant variables, uniqueness holds. By contrast, when there are many variables relative to observations, non-uniqueness is the rule, and finding the best similarity function is computationally hard. The results are interpreted as providing conditions under which rational agents who have access to the same observations are likely to converge on the same predictions, and conditions under which they may entertain different probabilistic beliefs.