1,720,970 research outputs found
Statistical Mechanics Approach to Inverse Problems on Networks
Full text linkStatistical Mechanics has gained a central role in modern Inference and Computer Science. Many optimization and inference problems can be cast in a Statistical Mechanics framework, and various concepts and methods developed in this area of Physics can be very helpful not only in the theoretical analysis, but also constitute valuable tools for solving single instance cases of hard inference and computational tasks. In this work, I address various inverse problems on networks, from models of epidemic spreading to learning in neural networks, and apply a variety of methods which have been developed in the context of Disordered Systems, namely Replica and Cavity methods from the theoretical side, and their algorithmic incarnation, Belief Propagation, to solve hard inverse problems which can be formulated in a Bayesian framewor
Neural networks trained with SGD learn distributions of increasing complexity
Full text linkThe ability of deep neural networks to generalise well even when they
interpolate their training data has been explained using various "simplicity
biases". These theories postulate that neural networks avoid overfitting by
first learning simple functions, say a linear classifier, before learning more
complex, non-linear functions. Meanwhile, data structure is also recognised as
a key ingredient for good generalisation, yet its role in simplicity biases is
not yet understood. Here, we show that neural networks trained using stochastic
gradient descent initially classify their inputs using lower-order input
statistics, like mean and covariance, and exploit higher-order statistics only
later during training. We first demonstrate this distributional simplicity bias
(DSB) in a solvable model of a neural network trained on synthetic data. We
empirically demonstrate DSB in a range of deep convolutional networks and
visual transformers trained on CIFAR10, and show that it even holds in networks
pre-trained on ImageNet. We discuss the relation of DSB to other simplicity
biases and consider its implications for the principle of Gaussian universality
in learning.Comment: Source code available at https://github.com/sgoldt/dist_inc_com
Subdominant Dense Clusters Allow for Simple Learning and High Computational Performance in Neural Networks with Discrete Synapses
Full text linkWe show that discrete synaptic weights can be efficiently used for learning in large scale neural systems, and lead to unanticipated computational performance. We focus on the representative case of learning random patterns with binary synapses in single layer networks. The standard statistical analysis shows that this problem is exponentially dominated by isolated solutions that are extremely hard to find algorithmically. Here, we introduce a novel method that allows us to find analytical evidence for the existence of subdominant and extremely dense regions of solutions. Numerical experiments confirm these findings. We also show that the dense regions are surprisingly accessible by simple learning protocols, and that these synaptic configurations are robust to perturbations and generalize better than typical solutions. These outcomes extend to synapses with multiple states and to deeper neural architectures. The large deviation measure also suggests how to design novel algorithmic schemes for optimization based on local entropy maximization
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Dispelling the Myths Behind First-author Citation Counts
Full text linkWe conducted a full-scale evaluative citation analysis study of scholars in the XML research field to explore just how different from each other author rankings resulting from different citation counting methods actually are, and to demonstrate the capability of emerging data and tools on the Web in supporting more realistic citation counting methods. Our results contest some common arguments for the continued
use of first-author citation counts in the evaluation of scholars, such as high correlations between author rankings by first-author citation counts and other citation
counting methods, and high costs of using more realistic citation counting methods that are not well-supported by the ISI databases. It is argued that increasingly available digital full text research papers make it possible for citation analysis studies to go beyond what the ISI databases have directly supported and to employ more
sophisticated methods
- …
