Srinadh Bhojanapalli

78 papers A* 22Misc 1Journal 47Unranked 8

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Autoregressive Ranking: Bridging the Gap Between Dual and Cross Encoders. CoRR Benjamin Rozonoyer, Chong You, Michael Boratko, Himanshu Jain, Nilesh Gupta, Srinadh Bhojanapalli, Andrew McCallum, Felix Yu
2025	A*	`conf`	Arithmetic Transformers Can Length-Generalize in Both Operand Length and Count. ICLR Hanseul Cho, Jaeyoung Cha, Srinadh Bhojanapalli, Chulhee Yun
2025	J	`jnl`	Scalable In-context Ranking with Generative Models. CoRR Nilesh Gupta, Chong You, Srinadh Bhojanapalli, Sanjiv Kumar, Inderjit S. Dhillon, Felix X. Yu
2025	J	`jnl`	Spark Transformer: Reactivating Sparsity in FFN and Attention. CoRR Chong You, Kan Wu, Zhipeng Jia, Lin Chen, Srinadh Bhojanapalli, Jiaxian Guo, Utku Evci, Jan Wassenberg, Praneeth Netrapalli, Jeremiah J. Willcock, Suvinay Subramanian, Felix Chern, Alek Andreev, Shreya Pathak, Felix X. Yu, Prateek Jain, David E. Culler, Henry M. Levy, Sanjiv Kumar
2024	J	`jnl`	Arithmetic Transformers Can Length-Generalize in Both Operand Length and Count. CoRR Hanseul Cho, Jaeyoung Cha, Srinadh Bhojanapalli, Chulhee Yun
2024	A*	`conf`	Dual-Encoders for Extreme Multi-label Classification. ICLR Nilesh Gupta, Devvrit, Ankit Singh Rawat, Srinadh Bhojanapalli, Prateek Jain, Inderjit S. Dhillon
2024	J	`jnl`	Efficient Language Model Architectures for Differentially Private Federated Learning. CoRR Jae Hun Ro, Srinadh Bhojanapalli, Zheng Xu, Yanxiang Zhang, Ananda Theertha Suresh
2024	A*	`conf`	Functional Interpolation for Relative Positions improves Long Context Transformers. ICLR Shanda Li, Chong You, Guru Guruganesh, Joshua Ainslie, Santiago Ontañón, Manzil Zaheer, Sumit Sanghai, Yiming Yang, Sanjiv Kumar, Srinadh Bhojanapalli
2024	J	`jnl`	HiRE: High Recall Approximate Top-k Estimation for Efficient LLM Inference. CoRR Yashas Samaga, Varun Yerram, Chong You, Srinadh Bhojanapalli, Sanjiv Kumar, Prateek Jain, Praneeth Netrapalli
2024	J	`jnl`	Mimetic Initialization Helps State Space Models Learn to Recall. CoRR Asher Trockman, Hrayr Harutyunyan, J. Zico Kolter, Sanjiv Kumar, Srinadh Bhojanapalli
2024	A*	`conf`	Position Coupling: Improving Length Generalization of Arithmetic Transformers Using Task Structure. NeurIPS Hanseul Cho, Jaeyoung Cha, Pranjal Awasthi, Srinadh Bhojanapalli, Anupam Gupta, Chulhee Yun
2024	J	`jnl`	Position Coupling: Leveraging Task Structure for Improved Length Generalization of Transformers. CoRR Hanseul Cho, Jaeyoung Cha, Pranjal Awasthi, Srinadh Bhojanapalli, Anupam Gupta, Chulhee Yun
2023	J	`jnl`	Depth Dependence of μP Learning Rates in ReLU MLPs. CoRR Samy Jelassi, Boris Hanin, Ziwei Ji, Sashank J. Reddi, Srinadh Bhojanapalli, Sanjiv Kumar
2023	J	`jnl`	Efficacy of Dual-Encoders for Extreme Multi-Label Classification. CoRR Nilesh Gupta, Devvrit Khatri, Ankit Singh Rawat, Srinadh Bhojanapalli, Prateek Jain, Inderjit S. Dhillon
2023	J	`jnl`	Functional Interpolation for Relative Positions Improves Long Context Transformers. CoRR Shanda Li, Chong You, Guru Guruganesh, Joshua Ainslie, Santiago Ontañón, Manzil Zaheer, Sumit Sanghai, Yiming Yang, Sanjiv Kumar, Srinadh Bhojanapalli
2023	A*	`conf`	On student-teacher deviations in distillation: does it pay to disobey? NeurIPS Vaishnavh Nagarajan, Aditya Krishna Menon, Srinadh Bhojanapalli, Hossein Mobahi, Sanjiv Kumar
2023	J	`jnl`	On student-teacher deviations in distillation: does it pay to disobey? CoRR Vaishnavh Nagarajan, Aditya Krishna Menon, Srinadh Bhojanapalli, Hossein Mobahi, Sanjiv Kumar
2023	A*	`conf`	The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers. ICLR Zonglin Li, Chong You, Srinadh Bhojanapalli, Daliang Li, Ankit Singh Rawat, Sashank J. Reddi, Ke Ye, Felix Chern, Felix X. Yu, Ruiqi Guo, Sanjiv Kumar
2023	A*	`conf`	Treeformer: Dense Gradient Trees for Efficient Attention Computation. ICLR Lovish Madaan, Srinadh Bhojanapalli, Himanshu Jain, Prateek Jain
2022	J	`jnl`	Large Models are Parsimonious Learners: Activation Sparsity in Trained Transformers. CoRR Zonglin Li, Chong You, Srinadh Bhojanapalli, Daliang Li, Ankit Singh Rawat, Sashank J. Reddi, Ke Ye, Felix Chern, Felix X. Yu, Ruiqi Guo, Sanjiv Kumar
2022	A*	`conf`	On the Adversarial Robustness of Mixture of Experts. NeurIPS Joan Puigcerver, Rodolphe Jenatton, Carlos Riquelme, Pranjal Awasthi, Srinadh Bhojanapalli
2022	J	`jnl`	On the Adversarial Robustness of Mixture of Experts. CoRR Joan Puigcerver, Rodolphe Jenatton, Carlos Riquelme, Pranjal Awasthi, Srinadh Bhojanapalli
2022	A*	`conf`	Robust Training of Neural Networks Using Scale Invariant Architectures. ICML Zhiyuan Li, Srinadh Bhojanapalli, Manzil Zaheer, Sashank J. Reddi, Sanjiv Kumar
2022	J	`jnl`	Robust Training of Neural Networks using Scale Invariant Architectures. CoRR Zhiyuan Li, Srinadh Bhojanapalli, Manzil Zaheer, Sashank J. Reddi, Sanjiv Kumar
2022	J	`jnl`	Teacher's pet: understanding and mitigating biases in distillation. Trans. Mach. Learn. Res. Michal Lukasik, Srinadh Bhojanapalli, Aditya Krishna Menon, Sanjiv Kumar
2022	J	`jnl`	Treeformer: Dense Gradient Trees for Efficient Attention Computation. CoRR Lovish Madaan, Srinadh Bhojanapalli, Himanshu Jain, Prateek Jain
2021	—	`conf`	A Simple and Effective Positional Encoding for Transformers. EMNLP (1) Pu-Chin Chen, Henry Tsai, Srinadh Bhojanapalli, Hyung Won Chung, Yin-Wen Chang, Chun-Sung Ferng
2021	A*	`conf`	Coping with Label Shift via Distributionally Robust Optimisation. ICLR Jingzhao Zhang, Aditya Krishna Menon, Andreas Veit, Srinadh Bhojanapalli, Sanjiv Kumar, Suvrit Sra
2021	J	`jnl`	Demystifying the Better Performance of Position Encoding Variants for Transformer. CoRR Pu-Chin Chen, Henry Tsai, Srinadh Bhojanapalli, Hyung Won Chung, Yin-Wen Chang, Chun-Sung Ferng
2021	J	`jnl`	Eigen Analysis of Self-Attention and its Reconstruction from Partial Computation. CoRR Srinadh Bhojanapalli, Ayan Chakrabarti, Himanshu Jain, Sanjiv Kumar, Michal Lukasik, Andreas Veit
2021	J	`jnl`	Leveraging redundancy in attention with Reuse Transformers. CoRR Srinadh Bhojanapalli, Ayan Chakrabarti, Andreas Veit, Michal Lukasik, Himanshu Jain, Frederick Liu, Yin-Wen Chang, Sanjiv Kumar
2021	J	`jnl`	On the Reproducibility of Neural Network Predictions. CoRR Srinadh Bhojanapalli, Kimberly Wilber, Andreas Veit, Ankit Singh Rawat, Seungyeon Kim, Aditya Krishna Menon, Sanjiv Kumar
2021	J	`jnl`	Teacher's pet: understanding and mitigating biases in distillation. CoRR Michal Lukasik, Srinadh Bhojanapalli, Aditya Krishna Menon, Sanjiv Kumar
2021	A*	`conf`	Understanding Robustness of Transformers for Image Classification. ICCV Srinadh Bhojanapalli, Ayan Chakrabarti, Daniel Glasner, Daliang Li, Thomas Unterthiner, Andreas Veit
2021	J	`jnl`	Understanding Robustness of Transformers for Image Classification. CoRR Srinadh Bhojanapalli, Ayan Chakrabarti, Daniel Glasner, Daliang Li, Thomas Unterthiner, Andreas Veit
2020	J	`jnl`	$O(n)$ Connections are Expressive Enough: Universal Approximability of Sparse Transformers. CoRR Chulhee Yun, Yin-Wen Chang, Srinadh Bhojanapalli, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar
2020	A*	`conf`	An efficient nonconvex reformulation of stagewise convex optimization problems. NeurIPS Rudy Bunel, Oliver Hinder, Srinadh Bhojanapalli, Krishnamurthy Dvijotham
2020	J	`jnl`	An efficient nonconvex reformulation of stagewise convex optimization problems. CoRR Rudy Bunel, Oliver Hinder, Srinadh Bhojanapalli, Krishnamurthy Dvijotham
2020	A*	`conf`	Are Transformers universal approximators of sequence-to-sequence functions? ICLR Chulhee Yun, Srinadh Bhojanapalli, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar
2020	J	`jnl`	Coping with Label Shift via Distributionally Robust Optimisation. CoRR Jingzhao Zhang, Aditya Krishna Menon, Andreas Veit, Srinadh Bhojanapalli, Sanjiv Kumar, Suvrit Sra
2020	A*	`conf`	Does label smoothing mitigate label noise? ICML Michal Lukasik, Srinadh Bhojanapalli, Aditya Krishna Menon, Sanjiv Kumar
2020	J	`jnl`	Does label smoothing mitigate label noise? CoRR Michal Lukasik, Srinadh Bhojanapalli, Aditya Krishna Menon, Sanjiv Kumar
2020	A*	`conf`	Large Batch Optimization for Deep Learning: Training BERT in 76 minutes. ICLR Yang You, Jing Li, Sashank J. Reddi, Jonathan Hseu, Sanjiv Kumar, Srinadh Bhojanapalli, Xiaodan Song, James Demmel, Kurt Keutzer, Cho-Jui Hsieh
2020	A*	`conf`	Low-Rank Bottleneck in Multi-head Attention Models. ICML Srinadh Bhojanapalli, Chulhee Yun, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar
2020	J	`jnl`	Low-Rank Bottleneck in Multi-head Attention Models. CoRR Srinadh Bhojanapalli, Chulhee Yun, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar
2020	J	`jnl`	Modifying Memories in Transformer Models. CoRR Chen Zhu, Ankit Singh Rawat, Manzil Zaheer, Srinadh Bhojanapalli, Daliang Li, Felix X. Yu, Sanjiv Kumar
2020	A*	`conf`	O(n) Connections are Expressive Enough: Universal Approximability of Sparse Transformers. NeurIPS Chulhee Yun, Yin-Wen Chang, Srinadh Bhojanapalli, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar
2020	—	`conf`	Semantic Label Smoothing for Sequence to Sequence Problems. EMNLP (1) Michal Lukasik, Himanshu Jain, Aditya Krishna Menon, Seungyeon Kim, Srinadh Bhojanapalli, Felix X. Yu, Sanjiv Kumar
2020	J	`jnl`	Semantic Label Smoothing for Sequence to Sequence Problems. CoRR Michal Lukasik, Himanshu Jain, Aditya Krishna Menon, Seungyeon Kim, Srinadh Bhojanapalli, Felix X. Yu, Sanjiv Kumar
2019	J	`jnl`	Are Transformers universal approximators of sequence-to-sequence functions? CoRR Chulhee Yun, Srinadh Bhojanapalli, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar
2019	—	`conf`	The role of over-parametrization in generalization of neural networks. ICLR (Poster) Behnam Neyshabur, Zhiyuan Li, Srinadh Bhojanapalli, Yann LeCun, Nathan Srebro
2018	—	`conf`	A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks. ICLR (Poster) Behnam Neyshabur, Srinadh Bhojanapalli, Nathan Srebro
2018	Misc	`conf`	Implicit Regularization in Matrix Factorization. ITA Suriya Gunasekar, Blake E. Woodworth, Srinadh Bhojanapalli, Behnam Neyshabur, Nathan Srebro
2018	A*	`conf`	Smoothed analysis for low-rank solutions to semidefinite programs in quadratic penalty form. COLT Srinadh Bhojanapalli, Nicolas Boumal, Prateek Jain, Praneeth Netrapalli
2018	J	`jnl`	Smoothed analysis for low-rank solutions to semidefinite programs in quadratic penalty form. CoRR Srinadh Bhojanapalli, Nicolas Boumal, Prateek Jain, Praneeth Netrapalli
2018	J	`jnl`	Towards Understanding the Role of Over-Parametrization in Generalization of Neural Networks. CoRR Behnam Neyshabur, Zhiyuan Li, Srinadh Bhojanapalli, Yann LeCun, Nathan Srebro
2017	J	`jnl`	A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks. CoRR Behnam Neyshabur, Srinadh Bhojanapalli, David McAllester, Nathan Srebro
2017	—	`conf`	Exploring Generalization in Deep Learning. NIPS Behnam Neyshabur, Srinadh Bhojanapalli, David McAllester, Nati Srebro
2017	J	`jnl`	Exploring Generalization in Deep Learning. CoRR Behnam Neyshabur, Srinadh Bhojanapalli, David McAllester, Nathan Srebro
2017	—	`conf`	Implicit Regularization in Matrix Factorization. NIPS Suriya Gunasekar, Blake E. Woodworth, Srinadh Bhojanapalli, Behnam Neyshabur, Nati Srebro
2017	J	`jnl`	Implicit Regularization in Matrix Factorization. CoRR Suriya Gunasekar, Blake E. Woodworth, Srinadh Bhojanapalli, Behnam Neyshabur, Nathan Srebro
2017	J	`jnl`	Provable quantum state tomography via non-convex methods. CoRR Anastasios Kyrillidis, Amir Kalev, Dohyung Park, Srinadh Bhojanapalli, Constantine Caramanis, Sujay Sanghavi
2017	J	`jnl`	Stabilizing GAN Training with Multiple Random Projections. CoRR Behnam Neyshabur, Srinadh Bhojanapalli, Ayan Chakrabarti
2016	A*	`conf`	Dropping Convexity for Faster Semi-definite Optimization. COLT Srinadh Bhojanapalli, Anastasios Kyrillidis, Sujay Sanghavi
2016	—	`conf`	Global Optimality of Local Search for Low Rank Matrix Recovery. NIPS Srinadh Bhojanapalli, Behnam Neyshabur, Nati Srebro
2016	J	`jnl`	Global Optimality of Local Search for Low Rank Matrix Recovery. CoRR Srinadh Bhojanapalli, Behnam Neyshabur, Nathan Srebro
2016	J	`jnl`	Provable non-convex projected gradient descent for a class of constrained matrix optimization problems. CoRR Dohyung Park, Anastasios Kyrillidis, Srinadh Bhojanapalli, Constantine Caramanis, Sujay Sanghavi
2016	—	`conf`	Single Pass PCA of Matrix Products. NIPS Shanshan Wu, Srinadh Bhojanapalli, Sujay Sanghavi, Alexandros G. Dimakis
2016	J	`jnl`	Single Pass PCA of Matrix Products. CoRR Shanshan Wu, Srinadh Bhojanapalli, Sujay Sanghavi, Alexandros G. Dimakis
2015	J	`jnl`	A New Sampling Technique for Tensors. CoRR Srinadh Bhojanapalli, Sujay Sanghavi
2015	J	`jnl`	Completing any low-rank matrix, provably. J. Mach. Learn. Res. Yudong Chen, Srinadh Bhojanapalli, Sujay Sanghavi, Rachel A. Ward
2015	J	`jnl`	Dropping Convexity for Faster Semi-definite Optimization. CoRR Srinadh Bhojanapalli, Anastasios Kyrillidis, Sujay Sanghavi
2015	A*	`conf`	Tighter Low-rank Approximation via Sampling the Leveraged Element. SODA Srinadh Bhojanapalli, Prateek Jain, Sujay Sanghavi
2014	A*	`conf`	Coherent Matrix Completion. ICML Yudong Chen, Srinadh Bhojanapalli, Sujay Sanghavi, Rachel A. Ward
2014	J	`jnl`	Tighter Low-rank Approximation via Sampling the Leveraged Element. CoRR Srinadh Bhojanapalli, Prateek Jain, Sujay Sanghavi
2014	A*	`conf`	Universal Matrix Completion. ICML Srinadh Bhojanapalli, Prateek Jain
2014	J	`jnl`	Universal Matrix Completion. CoRR Srinadh Bhojanapalli, Prateek Jain
2013	J	`jnl`	Coherent Matrix Completion. CoRR Srinadh Bhojanapalli, Yudong Chen, Sujay Sanghavi, Rachel A. Ward