Nous utilisons des témoins pour analyser le trafic et l’utilisation de notre site web, afin de personnaliser votre expérience. Vous pouvez désactiver ces technologies à tout moment, mais cela peut restreindre certaines fonctionnalités du site. Consultez notre Politique de protection de la vie privée pour en savoir plus.
Paramètre des cookies
Vous pouvez activer et désactiver les types de cookies que vous souhaitez accepter. Cependant certains choix que vous ferez pourraient affecter les services proposés sur nos sites (ex : suggestions, annonces personnalisées, etc.).
Cookies essentiels
Ces cookies sont nécessaires au fonctionnement du site et ne peuvent être désactivés. (Toujours actif)
Cookies analyse
Acceptez-vous l'utilisation de cookies pour mesurer l'audience de nos sites ?
Multimedia Player
Acceptez-vous l'utilisation de cookies pour afficher et vous permettre de regarder les contenus vidéo hébergés par nos partenaires (YouTube, etc.) ?
Publications
The effects of nature-based vs. indoor settings on the adaptability, performance and affect of calisthenics exercisers. A registered report.
The « jingle-jangle fallacy » of empathy: Delineating affective, cognitive and motor components of empathy from behavioral synchrony using a virtual agent
Efficiently solving a vehicle routing problem (VRP) in a practical runtime is a critical challenge for delivery management companies. This p… (voir plus)aper explores both a theoretical and experimental connection between the Capacitated Vehicle Routing Problem (CVRP) and the Constrained Centroid-Based Clustering (CCBC). Reducing a CVRP to a CCBC is a synonym for a transition from an exponential to a polynomial complexity using commonly known algorithms for clustering, i.e K-means. At the beginning, we conduct an exploratory analysis to highlight the existence of such a relationship between the two problems through illustrative small-size examples and simultaneously deduce some mathematically-related formulations and properties. On a second level, the paper proposes a CCBC based approach endowed with some enhancements. The proposed framework consists of three stages. At the first step, a constrained centroid-based clustering algorithm generates feasible clusters of customers. This methodology incorporates three enhancement tools to achieve near-optimal clusters, namely: a multi-start procedure for initial centroids, a customer assignment metric, and a self-adjustment mechanism for choosing the number of clusters. At the second step, a traveling salesman problem (T SP) solver is used to optimize the order of customers within each cluster. Finally, we introduce a process relying on routes cutting and relinking procedure, which calls upon solving a linear and integer programming model to further improve the obtained routes. This step is inspired by the ruin&recreate algorithm. This approach is an extension of the classical cluster-first, route-second method and provides near-optimal solutions on well-known benchmark instances in terms of solution quality and computational runtime, offering a milestone in solving VRP.
Vertebrate species worldwide are currently facing significant declines in many populations. Although we have gained substantial knowledge ab… (voir plus)out the direct threats that affect individual species, these threats only represent a fraction of the broader vertebrate threat profile, which is also shaped by species interactions. For example, threats faced by prey species can jeopardize the survival of their predators due to food resource scarcity. Yet, indirect threats arising from species interactions have received limited investigation thus far. In this study, we investigate the indirect consequences of anthropogenic threats on biodiversity in the context of European vertebrate food webs. We integrated data on trophic interactions among over 800 terrestrial vertebrates, along with their associated human‐induced threats. We quantified and mapped the vulnerability of various components of the food web, including species, interactions, and trophic groups to six major threats: pollution, agricultural intensification, climate change, direct exploitation, urbanization, and invasive alien species and diseases. Direct exploitation and agricultural intensification were two major threats for terrestrial vertebrate food webs: affecting 34% and 31% of species, respectively, they threaten 85% and 69% of interactions in Europe. By integrating network ecology with threat impact assessments, our study contributes to a better understanding of the magnitude of anthropogenic impacts on biodiversity.
Assessing the quality of summarizers poses significant challenges. In response, we propose a novel task-oriented evaluation approach that as… (voir plus)sesses summarizers based on their capacity to produce summaries that are useful for downstream tasks, while preserving task outcomes. We theoretically establish a direct relationship between the resulting error probability of these tasks and the mutual information between source texts and generated summaries. We introduce
In order to improve the efficiency of the last-mile delivery system when customers are possibly absent for deliveries, we propose the idea o… (voir plus)f employing the crowd to work as keepers and to provide storage services for their neighbors. Crowd keepers have extra flexibility, more availability, and lower costs than fixed storage options such as automated lockers, and this leads to a more efficient and a more profitable system for last-mile deliveries. We present a bilevel program that jointly determines the assignment, routing, and pricing decisions while considering customer preferences, keeper behaviors, and platform operations. We develop an equivalent single-level program, a mixed-integer linear program with subtour elimination constraints, that can be solved to optimality using a row generation algorithm. To improve the efficiency of the solution procedure, we further derive exact best response sets for both customers and keepers, and approximate optimal travel times using linear regression. We present a numerical study using a real-world data set from Amazon. The fixed-storage and no-storage systems are used as benchmarks to assess the performance of the crowdkeeping system. The results show that the crowdkeeping delivery system has the potential to generate higher profits because of its ability to consolidate deliveries and to eliminate failed deliveries. Funding: Funding provided by the Natural Sciences and Engineering Research Council of Canada [Grants 2022-04979 and 2022-05261], the Canada Research Chair program [Grant CRC-2018-00105], and the China Scholarship Council [Grant 202006190051] is gratefully acknowledged. Supplemental Material: The online appendix is available at https://doi.org/10.1287/trsc.2022.0323 .
Underpinning the past decades of work on the design, initialization, and optimization of neural networks is a seemingly innocuous assumption… (voir plus): that the network is trained on a \textit{stationary} data distribution. In settings where this assumption is violated, e.g.\ deep reinforcement learning, learning algorithms become unstable and brittle with respect to hyperparameters and even random seeds. One factor driving this instability is the loss of plasticity, meaning that updating the network's predictions in response to new information becomes more difficult as training progresses. While many recent works provide analyses and partial solutions to this phenomenon, a fundamental question remains unanswered: to what extent do known mechanisms of plasticity loss overlap, and how can mitigation strategies be combined to best maintain the trainability of a network? This paper addresses these questions, showing that loss of plasticity can be decomposed into multiple independent mechanisms and that, while intervening on any single mechanism is insufficient to avoid the loss of plasticity in all cases, intervening on multiple mechanisms in conjunction results in highly robust learning algorithms. We show that a combination of layer normalization and weight decay is highly effective at maintaining plasticity in a variety of synthetic nonstationary learning tasks, and further demonstrate its effectiveness on naturally arising nonstationarities, including reinforcement learning in the Arcade Learning Environment.
Underpinning the past decades of work on the design, initialization, and optimization of neural networks is a seemingly innocuous assumption… (voir plus): that the network is trained on a \textit{stationary} data distribution. In settings where this assumption is violated, e.g.\ deep reinforcement learning, learning algorithms become unstable and brittle with respect to hyperparameters and even random seeds. One factor driving this instability is the loss of plasticity, meaning that updating the network's predictions in response to new information becomes more difficult as training progresses. While many recent works provide analyses and partial solutions to this phenomenon, a fundamental question remains unanswered: to what extent do known mechanisms of plasticity loss overlap, and how can mitigation strategies be combined to best maintain the trainability of a network? This paper addresses these questions, showing that loss of plasticity can be decomposed into multiple independent mechanisms and that, while intervening on any single mechanism is insufficient to avoid the loss of plasticity in all cases, intervening on multiple mechanisms in conjunction results in highly robust learning algorithms. We show that a combination of layer normalization and weight decay is highly effective at maintaining plasticity in a variety of synthetic nonstationary learning tasks, and further demonstrate its effectiveness on naturally arising nonstationarities, including reinforcement learning in the Arcade Learning Environment.
Recurrent neural networks (RNNs) have fast inference and scale efficiently on long sequences, but they are difficult to train and hard to sc… (voir plus)ale. We propose Hawk, an RNN with gated linear recurrences, and Griffin, a hybrid model that mixes gated linear recurrences with local attention. Hawk exceeds the reported performance of Mamba on downstream tasks, while Griffin matches the performance of Llama-2 despite being trained on over 6 times fewer tokens. We also show that Griffin can extrapolate on sequences significantly longer than those seen during training. Our models match the hardware efficiency of Transformers during training, and during inference they have lower latency and significantly higher throughput. We scale Griffin up to 14B parameters, and explain how to shard our models for efficient distributed training.
