Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Ekbote, Chanakya"'
Autor:
Makkuva, Ashok Vardhan, Bondaschi, Marco, Ekbote, Chanakya, Girish, Adway, Nagle, Alliot, Kim, Hyeji, Gastpar, Michael
In recent years, transformer-based models have revolutionized deep learning, particularly in sequence modeling. To better understand this phenomenon, there is a growing interest in using Markov input processes to study transformers. However, our curr
Externí odkaz:
http://arxiv.org/abs/2406.03072
Autor:
Ekbote, Chanakya, Deshpande, Ajinkya Pankaj, Iyer, Arun, Bairi, Ramakrishna, Sellamanickam, Sundararajan
Unsupervised node representations learnt using contrastive learning-based methods have shown good performance on downstream tasks. However, these methods rely on augmentations that mimic low-pass filters, limiting their performance on tasks requiring
Externí odkaz:
http://arxiv.org/abs/2310.01892
Generative Flow Networks (GFlowNets) have demonstrated significant performance improvements for generating diverse discrete objects $x$ given a reward function $R(x)$, indicating the utility of the object and trained independently from the GFlowNet b
Externí odkaz:
http://arxiv.org/abs/2211.00568
Autor:
Jain, Moksh, Bengio, Emmanuel, Garcia, Alex-Hernandez, Rector-Brooks, Jarrid, Dossou, Bonaventure F. P., Ekbote, Chanakya, Fu, Jie, Zhang, Tianyu, Kilgour, Micheal, Zhang, Dinghuai, Simine, Lena, Das, Payel, Bengio, Yoshua
Design of de novo biological sequences with desired properties, like protein and DNA sequences, often involves an active loop with several rounds of molecule ideation and expensive wet-lab evaluations. These experiments can consist of multiple stages
Externí odkaz:
http://arxiv.org/abs/2203.04115
Autor:
Lingam, Vijay, Ekbote, Chanakya, Sharma, Manan, Ragesh, Rahul, Iyer, Arun, Sellamanickam, Sundararajan
Graph Neural Networks (GNNs) exploit signals from node features and the input graph topology to improve node classification task performance. However, these models tend to perform poorly on heterophilic graphs, where connected nodes have different la
Externí odkaz:
http://arxiv.org/abs/2112.03499
Autor:
Nayak, Shravan, Ekbote, Chanakya Ajit, Chauhan, Annanya Pratap Singh, Diddigi, Raghuram Bharadwaj, Ray, Prishita, Sikdar, Abhinava, Danda, Sai Koti Reddy, Bhatnagar, Shalabh
We consider the problem of energy management in microgrid networks. A microgrid is capable of generating a limited amount of energy from a renewable resource and is responsible for handling the demands of its dedicated customers. Owing to the variabl
Externí odkaz:
http://arxiv.org/abs/2002.02084