1,721,326 research outputs found
A Time-Dependent-Coefficient Reduced-Order Model for Unsteady Aerodynamics of Proprotors
No full textL-GreCo: Layerwise-adaptive gradient compression for efficient data-parallel deep learning
No full textData-parallel distributed training of deep neural networks (DNN) has gained very widespread adoption, but can still experience communication bottlenecks. To address this issue, entire families of compression mechanisms have been developed, including quantization, sparsification, and low-rank approximation, some of which are seeing significant practical adoption. Despite this progress, almost all known compression schemes apply compression uniformly across DNN layers, although layers are heterogeneous in terms of parameter count and their impact on model accuracy.In this work, we provide a general framework for adapting the degree of compression across the model's layers dynamically during training, improving the overall compression, while leading to substantial speedups, without sacrificing accuracy. Our framework, called L-GreCo, is based on an adaptive algorithm, which automatically picks the optimal compression parameters for model layers guaranteeing the best compression ratio while satisfying an error constraint. Extensive experiments over image classification and language modeling tasks shows that L-GreCo is effective across all existing families of compression methods, and achieves up to 2.5
×
training speedup and up to 5
×
compression improvement over efficient implementations of existing approaches, while recovering full accuracy. Moreover, L-GreCo is complementary to existing adaptive algorithms, improving their compression ratio by 50\% and practical throughput by 66\%. An anonymized implementation is available at https://github.com/LGrCo/L-GreCo
L-GreCo: Layerwise-adaptive gradient compression for efficient data-parallel deep learning
No full textData-parallel distributed training of deep neural networks (DNN) has gained very widespread adoption, but can still experience communication bottlenecks. To address this issue, entire families of compression mechanisms have been developed, including quantization, sparsification, and low-rank approximation, some of which are seeing significant practical adoption. Despite this progress, almost all known compression schemes apply compression uniformly across DNN layers, although layers are heterogeneous in terms of parameter count and their impact on model accuracy.In this work, we provide a general framework for adapting the degree of compression across the model's layers dynamically during training, improving the overall compression, while leading to substantial speedups, without sacrificing accuracy. Our framework, called L-GreCo, is based on an adaptive algorithm, which automatically picks the optimal compression parameters for model layers guaranteeing the best compression ratio while satisfying an error constraint. Extensive experiments over image classification and language modeling tasks shows that L-GreCo is effective across all existing families of compression methods, and achieves up to 2.5
×
training speedup and up to 5
×
compression improvement over efficient implementations of existing approaches, while recovering full accuracy. Moreover, L-GreCo is complementary to existing adaptive algorithms, improving their compression ratio by 50\% and practical throughput by 66\%. An anonymized implementation is available at https://github.com/LGrCo/L-GreCo
L'identité dans l'interaction: pratiques de catégorisation et accountability en milieu homoparental
No full textDrawing on a corpus of audio-recorded interactions in a French association of present and future gay and lesbian parents, we analyze the processes whereby participants construct their identity of homo parents. The recorded interactions take place during focus group meetings in which participants share and discuss their experience. The discussion often focuses on the problems children will have to face in their relationship with parents and with other children living in a more traditional family. In discussing these problems, participants often produce hypothetical narratives with made-up scenes in which their children either call them or refer to them.
Two different processes of constructing homoparental categories have attracted our attention: those activated to choose the kinship terms participants consider most appropriate to name parents in a gay or lesbian couple, and those used to evoke participants’ collective identity as focus-group members. In the first case, identity categories of gay and lesbian parents are the topic of the conversations, and the choice of kinship terms with the semantic traits they bring is constantly negotiated and reformulated in the interaction. In the second case, the focus - group collective identity, even if not thematized, emerges in humourous episodes in which participants propose paradoxical made-up scenes that evidently oversimplify the parental experience they are discussing about. Participants laugh at those scenes and, in so doing, re-establish the problematic perspective upon the homoparental experience they share. Those humoristic episodes are thus functional to the evocation of the collective focus - group identity
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
L-GreCo: Layerwise-Adaptive Gradient Compression for Efficient and Accurate Deep Learning
Full text linkData-parallel distributed training of deep neural networks (DNN) has gained
very widespread adoption, but can still experience communication bottlenecks.
To address this issue, entire families of compression mechanisms have been
developed, including quantization, sparsification, and low-rank approximation,
some of which are seeing significant practical adoption. Despite this progress,
almost all known compression schemes apply compression uniformly across DNN
layers, although layers are heterogeneous in terms of parameter count and their
impact on model accuracy. In this work, we provide a general framework for
adapting the degree of compression across the model's layers dynamically during
training, improving the overall compression, while leading to substantial
speedups, without sacrificing accuracy. Our framework, called L-GreCo, is based
on an adaptive algorithm, which automatically picks the optimal compression
parameters for model layers guaranteeing the best compression ratio while
satisfying an error constraint. Extensive experiments over image classification
and language modeling tasks shows that L-GreCo is effective across all existing
families of compression methods, and achieves up to 2.5 training
speedup and up to 5 compression improvement over efficient
implementations of existing approaches, while recovering full accuracy.
Moreover, L-GreCo is complementary to existing adaptive algorithms, improving
their compression ratio by 50% and practical throughput by 66%
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
- …
