Shashank Rajput

33 papers A* 13A 1Journal 17Unranked 2

Year	Rank	Type	Title / Venue / Authors
2024	—	`conf`	Inference-Friendly Models With MixAttention. ENLSP Shashank Rajput, Ying Sheng, Sean Owen, Vitaliy Chiley
2024	J	`jnl`	Inference-Friendly Models With MixAttention. CoRR Shashank Rajput, Ying Sheng, Sean Owen, Vitaliy Chiley
2024	A*	`conf`	Maestro: Uncovering Low-Rank Structures via Trainable Decomposition. ICML Samuel Horváth, Stefanos Laskaridis, Shashank Rajput, Hongyi Wang
2023	A*	`conf`	Looped Transformers as Programmable Computers. ICML Angeliki Giannou, Shashank Rajput, Jy-yong Sohn, Kangwook Lee, Jason D. Lee, Dimitris Papailiopoulos
2023	J	`jnl`	Looped Transformers as Programmable Computers. CoRR Angeliki Giannou, Shashank Rajput, Jy-yong Sohn, Kangwook Lee, Jason D. Lee, Dimitris S. Papailiopoulos
2023	J	`jnl`	Maestro: Uncovering Low-Rank Structures via Trainable Decomposition. CoRR Samuel Horváth, Stefanos Laskaridis, Shashank Rajput, Hongyi Wang
2023	A*	`conf`	Recommender Systems with Generative Retrieval. NeurIPS Shashank Rajput, Nikhil Mehta, Anima Singh, Raghunandan Hulikal Keshavan, Trung Vu, Lukasz Heldt, Lichan Hong, Yi Tay, Vinh Q. Tran, Jonah Samost, Maciej Kula, Ed H. Chi, Mahesh Sathiamoorthy
2023	J	`jnl`	Recommender Systems with Generative Retrieval. CoRR Shashank Rajput, Nikhil Mehta, Anima Singh, Raghunandan H. Keshavan, Trung Vu, Lukasz Heldt, Lichan Hong, Yi Tay, Vinh Q. Tran, Jonah Samost, Maciej Kula, Ed H. Chi, Maheswaran Sathiamoorthy
2023	J	`jnl`	The Expressive Power of Tuning Only the Norm Layers. CoRR Angeliki Giannou, Shashank Rajput, Dimitris S. Papailiopoulos
2023	A*	`conf`	The Expressive Power of Tuning Only the Normalization Layers. COLT Angeliki Giannou, Shashank Rajput, Dimitris Papailiopoulos
2022	A	`conf`	Finding Nearly Everything within Random Binary Networks. AISTATS Kartik Sreenivasan, Shashank Rajput, Jy-yong Sohn, Dimitris S. Papailiopoulos
2022	J	`jnl`	LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks. CoRR Tuan Dinh, Yuchen Zeng, Ruisu Zhang, Ziqian Lin, Michael Gira, Shashank Rajput, Jy-yong Sohn, Dimitris S. Papailiopoulos, Kangwook Lee
2022	A*	`conf`	LIFT: Language-Interfaced Fine-Tuning for Non-language Machine Learning Tasks. NeurIPS Tuan Dinh, Yuchen Zeng, Ruisu Zhang, Ziqian Lin, Michael Gira, Shashank Rajput, Jy-yong Sohn, Dimitris S. Papailiopoulos, Kangwook Lee
2022	A*	`conf`	Minibatch vs Local SGD with Shuffling: Tight Convergence Bounds and Beyond. ICLR Chulhee Yun, Shashank Rajput, Suvrit Sra
2022	A*	`conf`	Permutation-Based SGD: Is Random Optimal? ICLR Shashank Rajput, Kangwook Lee, Dimitris S. Papailiopoulos
2022	—	`conf`	Utilizing Language-Image Pretraining for Efficient and Robust Bilingual Word Alignment. EMNLP (Findings) Tuan Dinh, Jy-yong Sohn, Shashank Rajput, Timothy Ossowski, Yifei Ming, Junjie Hu, Dimitris S. Papailiopoulos, Kangwook Lee
2022	J	`jnl`	Utilizing Language-Image Pretraining for Efficient and Robust Bilingual Word Alignment. CoRR Tuan Dinh, Jy-yong Sohn, Shashank Rajput, Timothy Ossowski, Yifei Ming, Junjie Hu, Dimitris S. Papailiopoulos, Kangwook Lee
2021	A*	`conf`	An Exponential Improvement on the Memorization Capacity of Deep Threshold Networks. NeurIPS Shashank Rajput, Kartik Sreenivasan, Dimitris S. Papailiopoulos, Amin Karbasi
2021	J	`jnl`	An Exponential Improvement on the Memorization Capacity of Deep Threshold Networks. CoRR Shashank Rajput, Kartik Sreenivasan, Dimitris S. Papailiopoulos, Amin Karbasi
2021	J	`jnl`	Finding Everything within Random Binary Networks. CoRR Kartik Sreenivasan, Shashank Rajput, Jy-yong Sohn, Dimitris S. Papailiopoulos
2021	J	`jnl`	Minibatch vs Local SGD with Shuffling: Tight Convergence Bounds and Beyond. CoRR Chulhee Yun, Shashank Rajput, Suvrit Sra
2021	J	`jnl`	Permutation-Based SGD: Is Random Optimal? CoRR Shashank Rajput, Kangwook Lee, Dimitris S. Papailiopoulos
2020	A*	`conf`	Attack of the Tails: Yes, You Really Can Backdoor Federated Learning. NeurIPS Hongyi Wang, Kartik Sreenivasan, Shashank Rajput, Harit Vishwakarma, Saurabh Agarwal, Jy-yong Sohn, Kangwook Lee, Dimitris S. Papailiopoulos
2020	J	`jnl`	Attack of the Tails: Yes, You Really Can Backdoor Federated Learning. CoRR Hongyi Wang, Kartik Sreenivasan, Shashank Rajput, Harit Vishwakarma, Saurabh Agarwal, Jy-yong Sohn, Kangwook Lee, Dimitris S. Papailiopoulos
2020	A*	`conf`	Closing the convergence gap of SGD without replacement. ICML Shashank Rajput, Anant Gupta, Dimitris S. Papailiopoulos
2020	J	`jnl`	Closing the convergence gap of SGD without replacement. CoRR Shashank Rajput, Anant Gupta, Dimitris S. Papailiopoulos
2020	A*	`conf`	Optimal Lottery Tickets via Subset Sum: Logarithmic Over-Parameterization is Sufficient. NeurIPS Ankit Pensia, Shashank Rajput, Alliot Nagle, Harit Vishwakarma, Dimitris S. Papailiopoulos
2020	J	`jnl`	Optimal Lottery Tickets via SubsetSum: Logarithmic Over-Parameterization is Sufficient. CoRR Ankit Pensia, Shashank Rajput, Alliot Nagle, Harit Vishwakarma, Dimitris S. Papailiopoulos
2019	J	`jnl`	Convergence and Margin of Adversarial Training on Separable Data. CoRR Zachary Charles, Shashank Rajput, Stephen J. Wright, Dimitris S. Papailiopoulos
2019	A*	`conf`	DETOX: A Redundancy-based Framework for Faster and More Robust Gradient Aggregation. NeurIPS Shashank Rajput, Hongyi Wang, Zachary Charles, Dimitris S. Papailiopoulos
2019	J	`jnl`	DETOX: A Redundancy-based Framework for Faster and More Robust Gradient Aggregation. CoRR Shashank Rajput, Hongyi Wang, Zachary Charles, Dimitris S. Papailiopoulos
2019	A*	`conf`	Does Data Augmentation Lead to Positive Margin? ICML Shashank Rajput, Zhili Feng, Zachary Charles, Po-Ling Loh, Dimitris S. Papailiopoulos
2019	J	`jnl`	Does Data Augmentation Lead to Positive Margin? CoRR Shashank Rajput, Zhili Feng, Zachary Charles, Po-Ling Loh, Dimitris S. Papailiopoulos