Devansh Arpit
Publication record assembled from the DBLP archive of ranked conferences.
Papers indexed
16
Venues
6
Active years
2012–2024
Best venue rank
A*
Where they publish
Papers
16 indexed papers, newest first.
| Year | Venue | Title | Authors |
|---|---|---|---|
| 2024 | ICLR | Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization. | Weiran Yao, Shelby Heinecke, Juan Carlos Niebles, Zhiwei Liu, Yihao Feng, Le Xue, Rithesh R. N., Zeyuan Chen, Jianguo Zhang, Devansh Arpit, Ran Xu, Phil Mui, Huan Wang, Caiming Xiong, Silvio Savarese |
| 2021 | ICML | Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization. | Stanislaw Jastrzebski, Devansh Arpit, Oliver strand, Giancarlo Kerg, Huan Wang, Caiming Xiong, Richard Socher, Kyunghyun Cho, Krzysztof J. Geras |
| 2020 | ICLR | The Break-Even Point on Optimization Trajectories of Deep Neural Networks. | Stanislaw Jastrzebski, Maciej Szymczak, Stanislav Fort, Devansh Arpit, Jacek Tabor, Kyunghyun Cho, Krzysztof J. Geras |
| 2019 | ICLR | h-detach: Modifying the LSTM Gradient Towards Better Optimization. | Bhargav Kanuparthi, Devansh Arpit, Giancarlo Kerg, Nan Rosemary Ke, Ioannis Mitliagkas, Yoshua Bengio |
| 2019 | ICML | On the Spectral Bias of Neural Networks. | Nasim Rahaman, Aristide Baratin, Devansh Arpit, Felix Draxler, Min Lin, Fred A. Hamprecht, Yoshua Bengio, Aaron C. Courville |
| 2018 | ICANN | Width of Minima Reached by Stochastic Gradient Descent is Influenced by Learning Rate to Batch Size Ratio. | Stanislaw Jastrzebski, Zachary Kenton, Devansh Arpit, Nicolas Ballas, Asja Fischer, Yoshua Bengio, Amos J. Storkey |
| 2018 | ICLR | Residual Connections Encourage Iterative Inference. | Stanislaw Jastrzebski, Devansh Arpit, Nicolas Ballas, Vikas Verma, Tong Che, Yoshua Bengio |
| 2018 | ICLR | Finding Flatter Minima with SGD. | Stanislaw Jastrzebski, Zachary Kenton, Devansh Arpit, Nicolas Ballas, Asja Fischer, Yoshua Bengio, Amos J. Storkey |
| 2018 | ICLR | Fraternal Dropout. | Konrad Zolna, Devansh Arpit, Dendi Suhubdy, Yoshua Bengio |
| 2017 | CVPR | Person Re-identification for Improved Multi-person Multi-camera Tracking by Continuous Entity Association. | Neeti Narayan, Nishant Sankaran, Devansh Arpit, Karthik Dantu, Srirangaraj Setlur, Venu Govindaraju |
| 2017 | ICLR | Deep Nets Don't Learn via Memorization. | David Krueger, Nicolas Ballas, Stanislaw Jastrzebski, Devansh Arpit, Maxinder S. Kanwal, Tegan Maharaj, Emmanuel Bengio, Asja Fischer, Aaron C. Courville |
| 2017 | ICML | A Closer Look at Memorization in Deep Networks. | Devansh Arpit, Stanislaw Jastrzebski, Nicolas Ballas, David Krueger, Emmanuel Bengio, Maxinder S. Kanwal, Tegan Maharaj, Asja Fischer, Aaron C. Courville, Yoshua Bengio, Simon Lacoste-Julien |
| 2016 | ICML | Normalization Propagation: A Parametric Technique for Removing Internal Covariate Shift in Deep Networks. | Devansh Arpit, Yingbo Zhou, Bhargava Urala Kota, Venu Govindaraju |
| 2016 | ICML | Why Regularized Auto-Encoders learn Sparse Representation? | Devansh Arpit, Yingbo Zhou, Hung Q. Ngo, Venu Govindaraju |
| 2013 | WACV | Ridge Regression based classifiers for large scale class imbalanced datasets. | Devansh Arpit, Shuang Wu, Pradeep Natarajan, Rohit Prasad, Premkumar Natarajan |
| 2012 | ICPR | Locality-constrained Low Rank Coding for face recognition. | Devansh Arpit, Gaurav Srivastava, Yun Fu |