Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.
DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.
We present a general method for maintaining estimates of the distribution of parameters in arbitrary models. This is then applied to the estimation of probability distribution over actions in value-based reinforcement learning. While this approach is simil ...
[1] In this paper we extend previous mathematical results on the probabilistic modeling of base flows driven by spatial and temporal fluctuations of soil moisture and affected by intermittent rainfall forcings and by heterogeneous transport, soil, and vege ...
Most discriminative techniques for detecting instances from object categories in still images consist of looping over a partition of a pose space with dedicated binary classifiers. The efficiency of this strategy for a complex pose, i.e., for fine-grained ...
In this paper we provide the complete solution to the existence and characterization problem of optimal capital and risk allocations for not necessarily monotone, law-invariant convex risk measures on the model space Lp, for any p ε [1;∞]. Our main result ...
The differential model MIAGE (see "Mechanistic Interpretation of Alpine Glacierized Environments: Part 1. Model formulation and related dynamical properties" by Perona and Burlando, this issue) is analyzed in this work with the purpose of: (i) showing the ...
This paper aims at a first theoretical step toward the probabilistic modeling of nutrient contents in catchment-scale soil states. To this end, we wish to characterize probabilistically the slow, leaching-prone component of the hydrologic response, which c ...
High spatio-temporal resolution monitoring has only been progressively developed in the Rhine–Meuse basins over the last few decades. As a consequence, basic hydrological information can be very scarce in some areas. In regions which are homogeneous from a ...
It is well known and surprising that the uncoded transmission of an independent and identically distributed Gaussian source across an additive white Gaussian noise channel is optimal: No amount of sophistication in the coding strategy can ever perform bett ...
[1] We derive a new allometric scaling law for loopless networks, which we confirm with studies on rivers, exact network results and computer simulations. We provide evidence suggesting that ensemble averaging of the allometric property (where individual r ...