Simple learning rules to cope with changing environments
Graph Chatbot
Chat with Graph Search
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.
This paper analyzes the trajectories of stochastic gradient descent (SGD) to help understand the algorithm’s convergence properties in non-convex problems. We first show that the sequence of iterates generated by SGD remains bounded and converges with prob ...
Since the birth of Information Theory, researchers have defined and exploited various information measures, as well as endowed them with operational meanings. Some were born as a "solution to a problem", like Shannon's Entropy and Mutual Information. Other ...
Studying the complexity of distributed algorithms typically boils down to evaluating how the number of messages exchanged (resp. communication steps performed or shared memory operations executed) by nodes to reliably achieve some common task, evolves with ...
We present a probabilistic approach to quantify the hazard posed by volcanic ballistic projectiles (VBP) and their potential impact on the built environment. A model named Great Balls of Fire (GBF) is introduced to describe ballistic trajectories of VBPs a ...
Path integrals play a crucial role in describing the dynamics of physical systems subject to classical or quantum noise. In fact, when correctly normalized, they express the probability of transition between two states of the system. In this work, we show ...
The likelihood function is a fundamental component in Bayesian statistics. However, evaluating the likelihood of an observation is computationally intractable in many applications. In this paper, we propose a non-parametric approximation of the likelihood ...
Background Coercion in psychiatry is a controversial issue. Identifying its predictors and their interaction using traditional statistical methods is difficult, given the large number of variables involved. The purpose of this study was to use machine-lear ...
Revenue management (RM) can be considered an application of operations research in the transportation industry. For these service companies, it is a difficult task to adjust supply and demand. In order to maximize revenue, RM systems display demand behavio ...
In this paper we study the speed of infection spread and the survival of the contact process in the random geometric graph G = G (n, r(n), f) of n nodes independently distributed in S = -1/2, 1/2 according to a certain density f(.). In the first part ...
Systems and methods for tracking interacting objects may acquire, with a sensor, and two or more images associated with two or more time instances. A processor may generate image data from the two or more images. The processor may apply an extended Probabi ...
