1 code implementation • NeurIPS 2023 • Chanakya Ekbote, Ajinkya Pankaj Deshpande, Arun Iyer, Ramakrishna Bairi, Sundararajan Sellamanickam
This paper presents a simple filter-based augmentation method to capture different parts of the eigen-spectrum.
no code implementations • 1 Nov 2022 • Chanakya Ekbote, Moksh Jain, Payel Das, Yoshua Bengio
We hypothesize that this can lead to incompatibility between the inductive optimization biases in training $R$ and in training the GFlowNet, potentially leading to worse samples and slow adaptation to changes in the distribution.
1 code implementation • 2 Mar 2022 • Moksh Jain, Emmanuel Bengio, Alex-Hernandez Garcia, Jarrid Rector-Brooks, Bonaventure F. P. Dossou, Chanakya Ekbote, Jie Fu, Tianyu Zhang, Micheal Kilgour, Dinghuai Zhang, Lena Simine, Payel Das, Yoshua Bengio
In this work, we propose an active learning algorithm leveraging epistemic uncertainty estimation and the recently proposed GFlowNets as a generator of diverse candidate solutions, with the objective to obtain a diverse batch of useful (as defined by some utility function, for example, the predicted anti-microbial activity of a peptide) and informative candidates after each round.
1 code implementation • 7 Dec 2021 • Vijay Lingam, Chanakya Ekbote, Manan Sharma, Rahul Ragesh, Arun Iyer, Sundararajan Sellamanickam
We study various aspects of our proposed model including, dependency on the number of eigencomponents utilized, latent polynomial filters learned, and performance of the individual polynomials on the node classification task.