Devansh Arpit - RankMe

55 papers A* 9A 1B 2Journal 32Unranked 11

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	TPV: Parameter Perturbations Through the Lens of Test Prediction Variance. CoRR Devansh Arpit
2024	—	`conf`	Causal Layering via Conditional Entropy. CLeaR Itai Feigenbaum, Devansh Arpit, Shelby Heinecke, Juan Carlos Niebles, Weiran Yao, Caiming Xiong, Silvio Savarese, Huan Wang
2024	J	`jnl`	Causal Layering via Conditional Entropy. CoRR Itai Feigenbaum, Devansh Arpit, Huan Wang, Shelby Heinecke, Juan Carlos Niebles, Weiran Yao, Caiming Xiong, Silvio Savarese
2024	J	`jnl`	Editing Arbitrary Propositions in LLMs without Subject Labels. CoRR Itai Feigenbaum, Devansh Arpit, Huan Wang, Shelby Heinecke, Juan Carlos Niebles, Weiran Yao, Caiming Xiong, Silvio Savarese
2024	—	`conf`	On the Unlikelihood of D-Separation. PGM Itai Feigenbaum, Devansh Arpit, Shelby Heinecke, Juan Carlos Niebles, Weiran Yao, Huan Wang, Caiming Xiong, Silvio Savarese
2024	A*	`conf`	Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization. ICLR 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
2023	J	`jnl`	BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agents. CoRR Zhiwei Liu, Weiran Yao, Jianguo Zhang, Le Xue, Shelby Heinecke, Rithesh Murthy, Yihao Feng, Zeyuan Chen, Juan Carlos Niebles, Devansh Arpit, Ran Xu, Phil Mui, Huan Wang, Caiming Xiong, Silvio Savarese
2023	J	`jnl`	Merlion: End-to-End Machine Learning for Time Series. J. Mach. Learn. Res. Aadyot Bhatnagar, Paul Kassianik, Chenghao Liu, Tian Lan, Wenzhuo Yang, Rowan Cassius, Doyen Sahoo, Devansh Arpit, Sri Subramanian, Gerald Woo, Amrita Saha, Arun Kumar Jagota, Gokulakrishnan Gopalakrishnan, Manpreet Singh, K. C. Krithika, Sukumar Maddineni, Dae-ki Cho, Bo Zong, Yingbo Zhou, Caiming Xiong, Silvio Savarese, Steven C. H. Hoi, Huan Wang
2023	J	`jnl`	On the Unlikelihood of D-Separation. CoRR Itai Feigenbaum, Huan Wang, Shelby Heinecke, Juan Carlos Niebles, Weiran Yao, Caiming Xiong, Devansh Arpit
2023	J	`jnl`	REX: Rapid Exploration and eXploitation for AI Agents. CoRR Rithesh Murthy, Shelby Heinecke, Juan Carlos Niebles, Zhiwei Liu, Le Xue, Weiran Yao, Yihao Feng, Zeyuan Chen, Akash Gokul, Devansh Arpit, Ran Xu, Phil Mui, Huan Wang, Caiming Xiong, Silvio Savarese
2023	J	`jnl`	Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization. CoRR Weiran Yao, Shelby Heinecke, Juan Carlos Niebles, Zhiwei Liu, Yihao Feng, Le Xue, Rithesh Murthy, Zeyuan Chen, Jianguo Zhang, Devansh Arpit, Ran Xu, Phil Mui, Huan Wang, Caiming Xiong, Silvio Savarese
2023	J	`jnl`	Salesforce CausalAI Library: A Fast and Scalable Framework for Causal Analysis of Time Series and Tabular Data. CoRR Devansh Arpit, Matthew Fernandez, Chenghao Liu, Weiran Yao, Wenzhuo Yang, Paul Josel, Shelby Heinecke, Eric Hu, Huan Wang, Stephen C. H. Hoi, Caiming Xiong, Kun Zhang, Juan Carlos Niebles
2022	A*	`conf`	Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization. NeurIPS Devansh Arpit, Huan Wang, Yingbo Zhou, Caiming Xiong
2021	A*	`conf`	Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization. ICML Stanislaw Jastrzebski, Devansh Arpit, Oliver Åstrand, Giancarlo Kerg, Huan Wang, Caiming Xiong, Richard Socher, Kyunghyun Cho, Krzysztof J. Geras
2021	J	`jnl`	Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization. CoRR Devansh Arpit, Huan Wang, Yingbo Zhou, Caiming Xiong
2021	J	`jnl`	Learning Rich Nearest Neighbor Representations from Self-supervised Ensembles. CoRR Bram Wallace, Devansh Arpit, Huan Wang, Caiming Xiong
2021	J	`jnl`	Merlion: A Machine Learning Library for Time Series. CoRR Aadyot Bhatnagar, Paul Kassianik, Chenghao Liu, Tian Lan, Wenzhuo Yang, Rowan Cassius, Doyen Sahoo, Devansh Arpit, Sri Subramanian, Gerald Woo, Amrita Saha, Arun Kumar Jagota, Gokulakrishnan Gopalakrishnan, Manpreet Singh, K. C. Krithika, Sukumar Maddineni, Dae-ki Cho, Bo Zong, Yingbo Zhou, Caiming Xiong, Silvio Savarese, Steven C. H. Hoi, Huan Wang
2021	J	`jnl`	Momentum Contrastive Autoencoder: Using Contrastive Learning for Latent Space Distribution Matching in WAE. CoRR Devansh Arpit, Aadyot Bhatnagar, Huan Wang, Caiming Xiong
2020	J	`jnl`	Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization. CoRR Stanislaw Jastrzebski, Devansh Arpit, Oliver Åstrand, Giancarlo Kerg, Huan Wang, Caiming Xiong, Richard Socher, Kyunghyun Cho, Krzysztof J. Geras
2020	J	`jnl`	Neural Bayes: A Generic Parameterization Method for Unsupervised Representation Learning. CoRR Devansh Arpit, Huan Wang, Caiming Xiong, Richard Socher, Yoshua Bengio
2020	A*	`conf`	The Break-Even Point on Optimization Trajectories of Deep Neural Networks. ICLR Stanislaw Jastrzebski, Maciej Szymczak, Stanislav Fort, Devansh Arpit, Jacek Tabor, Kyunghyun Cho, Krzysztof J. Geras
2020	J	`jnl`	The Break-Even Point on Optimization Trajectories of Deep Neural Networks. CoRR Stanislaw Jastrzebski, Maciej Szymczak, Stanislav Fort, Devansh Arpit, Jacek Tabor, Kyunghyun Cho, Krzysztof J. Geras
2019	J	`jnl`	Entropy Penalty: Towards Generalization Beyond the IID Assumption. CoRR Devansh Arpit, Caiming Xiong, Richard Socher
2019	A*	`conf`	How to Initialize your Network? Robust Initialization for WeightNorm & ResNets. NeurIPS Devansh Arpit, Víctor Campos, Yoshua Bengio
2019	J	`jnl`	How to Initialize your Network? Robust Initialization for WeightNorm & ResNets. CoRR Devansh Arpit, Victor Campos, Yoshua Bengio
2019	A*	`conf`	On the Spectral Bias of Neural Networks. ICML Nasim Rahaman, Aristide Baratin, Devansh Arpit, Felix Draxler, Min Lin, Fred A. Hamprecht, Yoshua Bengio, Aaron C. Courville
2019	J	`jnl`	The Benefits of Over-parameterization at Initialization in Deep ReLU Networks. CoRR Devansh Arpit, Yoshua Bengio
2019	—	`conf`	h-detach: Modifying the LSTM Gradient Towards Better Optimization. ICLR (Poster) Bhargav Kanuparthi, Devansh Arpit, Giancarlo Kerg, Nan Rosemary Ke, Ioannis Mitliagkas, Yoshua Bengio
2018	J	`jnl`	A Walk with SGD. CoRR Chen Xing, Devansh Arpit, Christos Tsirigotis, Yoshua Bengio
2018	—	`conf`	Finding Flatter Minima with SGD. ICLR (Workshop) Stanislaw Jastrzebski, Zachary Kenton, Devansh Arpit, Nicolas Ballas, Asja Fischer, Yoshua Bengio, Amos J. Storkey
2018	—	`conf`	Fraternal Dropout. ICLR (Poster) Konrad Zolna, Devansh Arpit, Dendi Suhubdy, Yoshua Bengio
2018	J	`jnl`	On the Spectral Bias of Deep Neural Networks. CoRR Nasim Rahaman, Devansh Arpit, Aristide Baratin, Felix Draxler, Min Lin, Fred A. Hamprecht, Yoshua Bengio, Aaron C. Courville
2018	—	`conf`	Residual Connections Encourage Iterative Inference. ICLR (Poster) Stanislaw Jastrzebski, Devansh Arpit, Nicolas Ballas, Vikas Verma, Tong Che, Yoshua Bengio
2018	—	`conf`	Width of Minima Reached by Stochastic Gradient Descent is Influenced by Learning Rate to Batch Size Ratio. ICANN (3) Stanislaw Jastrzebski, Zachary Kenton, Devansh Arpit, Nicolas Ballas, Asja Fischer, Yoshua Bengio, Amos J. Storkey
2018	J	`jnl`	h-detach: Modifying the LSTM Gradient Towards Better Optimization. CoRR Devansh Arpit, Bhargav Kanuparthi, Giancarlo Kerg, Nan Rosemary Ke, Ioannis Mitliagkas, Yoshua Bengio
2017	A*	`conf`	A Closer Look at Memorization in Deep Networks. ICML 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
2017	J	`jnl`	A Closer Look at Memorization in Deep Networks. CoRR 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
2017	—	`conf`	Deep Nets Don't Learn via Memorization. ICLR (Workshop) David Krueger, Nicolas Ballas, Stanislaw Jastrzebski, Devansh Arpit, Maxinder S. Kanwal, Tegan Maharaj, Emmanuel Bengio, Asja Fischer, Aaron C. Courville
2017	J	`jnl`	Fraternal Dropout. CoRR Konrad Zolna, Devansh Arpit, Dendi Suhubdy, Yoshua Bengio
2017	—	`conf`	Person Re-identification for Improved Multi-person Multi-camera Tracking by Continuous Entity Association. CVPR Workshops Neeti Narayan, Nishant Sankaran, Devansh Arpit, Karthik Dantu, Srirangaraj Setlur, Venu Govindaraju
2017	J	`jnl`	Residual Connections Encourage Iterative Inference. CoRR Stanislaw Jastrzebski, Devansh Arpit, Nicolas Ballas, Vikas Verma, Tong Che, Yoshua Bengio
2017	J	`jnl`	Three Factors Influencing Minima in SGD. CoRR Stanislaw Jastrzebski, Zachary Kenton, Devansh Arpit, Nicolas Ballas, Asja Fischer, Yoshua Bengio, Amos J. Storkey
2017	J	`jnl`	Variational Bi-LSTMs. CoRR Samira Shabanian, Devansh Arpit, Adam Trischler, Yoshua Bengio
2016	A*	`conf`	Normalization Propagation: A Parametric Technique for Removing Internal Covariate Shift in Deep Networks. ICML Devansh Arpit, Yingbo Zhou, Bhargava Urala Kota, Venu Govindaraju
2016	J	`jnl`	Normalization Propagation: A Parametric Technique for Removing Internal Covariate Shift in Deep Networks. CoRR Devansh Arpit, Yingbo Zhou, Bhargava Urala Kota, Venu Govindaraju
2016	—	`conf`	Subspace learning via low rank projections for dimensionality reduction. BTAS Devansh Arpit, Chetan Ramaiah, Venu Govindaraju
2016	J	`jnl`	Towards Optimality Conditions for Non-Linear Networks. CoRR Devansh Arpit, Hung Q. Ngo, Yingbo Zhou, Nils Napp, Venu Govindaraju
2016	A*	`conf`	Why Regularized Auto-Encoders learn Sparse Representation? ICML Devansh Arpit, Yingbo Zhou, Hung Q. Ngo, Venu Govindaraju
2015	J	`jnl`	Why Regularized Auto-Encoders learn Sparse Representation? CoRR Devansh Arpit, Yingbo Zhou, Hung Q. Ngo, Venu Govindaraju
2014	—	`conf`	Dimensionality Reduction with Subspace Structure Preservation. NIPS Devansh Arpit, Ifeoma Nwogu, Venu Govindaraju
2014	J	`jnl`	Dimensionality Reduction with Subspace Structure Preservation. CoRR Devansh Arpit, Ifeoma Nwogu, Venu Govindaraju
2014	J	`jnl`	Randomized Subspace Learning Algorithms with Subspace Structure Preservation Guarantees. CoRR Devansh Arpit, Gaurav Srivastava, Venu Govindaraju
2013	A	`conf`	Ridge Regression based classifiers for large scale class imbalanced datasets. WACV Devansh Arpit, Shuang Wu, Pradeep Natarajan, Rohit Prasad, Premkumar Natarajan
2012	B	`conf`	Locality-constrained Low Rank Coding for face recognition. ICPR Devansh Arpit, Gaurav Srivastava, Yun Fu
2011	B	`conf`	Fingerprint feature extraction from gray scale images by ridge tracing. IJCB Devansh Arpit, Anoop M. Namboodiri