Srinadh Bhojanapalli

Publication Activity (10 Years)

Years Active: 2013-2024
Publications (10 Years): 62

Top Topics

Convex Optimization

Top Venues

Publications

Nilesh Gupta, Devvrit, Ankit Singh Rawat, Srinadh Bhojanapalli, Prateek Jain, Inderjit S. Dhillon
Dual-Encoders for Extreme Multi-label Classification. ICLR (2024)
Jae Hun Ro, Srinadh Bhojanapalli, Zheng Xu, Yanxiang Zhang, Ananda Theertha Suresh
Efficient Language Model Architectures for Differentially Private Federated Learning. CoRR (2024)
Shanda Li, Chong You, Guru Guruganesh, Joshua Ainslie, Santiago Ontañón, Manzil Zaheer, Sumit Sanghai, Yiming Yang, Sanjiv Kumar, Srinadh Bhojanapalli
Functional Interpolation for Relative Positions improves Long Context Transformers. ICLR (2024)
Hanseul Cho, Jaeyoung Cha, Pranjal Awasthi, Srinadh Bhojanapalli, Anupam Gupta, Chulhee Yun
Position Coupling: Leveraging Task Structure for Improved Length Generalization of Transformers. CoRR (2024)
Yashas Samaga, Varun Yerram, Chong You, Srinadh Bhojanapalli, Sanjiv Kumar, Prateek Jain, Praneeth Netrapalli
HiRE: High Recall Approximate Top-k Estimation for Efficient LLM Inference. CoRR (2024)
Vaishnavh Nagarajan, Aditya Krishna Menon, Srinadh Bhojanapalli, Hossein Mobahi, Sanjiv Kumar
On student-teacher deviations in distillation: does it pay to disobey? NeurIPS (2023)
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
The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers. ICLR (2023)
Samy Jelassi, Boris Hanin, Ziwei Ji, Sashank J. Reddi, Srinadh Bhojanapalli, Sanjiv Kumar
Depth Dependence of μP Learning Rates in ReLU MLPs. CoRR (2023)
Shanda Li, Chong You, Guru Guruganesh, Joshua Ainslie, Santiago Ontañón, Manzil Zaheer, Sumit Sanghai, Yiming Yang, Sanjiv Kumar, Srinadh Bhojanapalli
Functional Interpolation for Relative Positions Improves Long Context Transformers. CoRR (2023)
Nilesh Gupta, Devvrit Khatri, Ankit S. Rawat, Srinadh Bhojanapalli, Prateek Jain, Inderjit S. Dhillon
Efficacy of Dual-Encoders for Extreme Multi-Label Classification. CoRR (2023)
Lovish Madaan, Srinadh Bhojanapalli, Himanshu Jain, Prateek Jain
Treeformer: Dense Gradient Trees for Efficient Attention Computation. ICLR (2023)
Vaishnavh Nagarajan, Aditya Krishna Menon, Srinadh Bhojanapalli, Hossein Mobahi, Sanjiv Kumar
On student-teacher deviations in distillation: does it pay to disobey? CoRR (2023)
Lovish Madaan, Srinadh Bhojanapalli, Himanshu Jain, Prateek Jain
Treeformer: Dense Gradient Trees for Efficient Attention Computation. CoRR (2022)
Joan Puigcerver, Rodolphe Jenatton, Carlos Riquelme, Pranjal Awasthi, Srinadh Bhojanapalli
On the Adversarial Robustness of Mixture of Experts. CoRR (2022)
Michal Lukasik, Srinadh Bhojanapalli, Aditya Krishna Menon, Sanjiv Kumar
Teacher's pet: understanding and mitigating biases in distillation. Trans. Mach. Learn. Res. 2022 (2022)
Zhiyuan Li, Srinadh Bhojanapalli, Manzil Zaheer, Sashank J. Reddi, Sanjiv Kumar
Robust Training of Neural Networks using Scale Invariant Architectures. CoRR (2022)
Zonglin Li, Chong You, Srinadh Bhojanapalli, Daliang Li, Ankit Singh Rawat, Sashank J. Reddi, Ke Ye, Felix X. Chern, Felix X. Yu, Ruiqi Guo, Sanjiv Kumar
Large Models are Parsimonious Learners: Activation Sparsity in Trained Transformers. CoRR (2022)
Joan Puigcerver, Rodolphe Jenatton, Carlos Riquelme, Pranjal Awasthi, Srinadh Bhojanapalli
On the Adversarial Robustness of Mixture of Experts. NeurIPS (2022)
Zhiyuan Li, Srinadh Bhojanapalli, Manzil Zaheer, Sashank J. Reddi, Sanjiv Kumar
Robust Training of Neural Networks Using Scale Invariant Architectures. ICML (2022)
Srinadh Bhojanapalli, Ayan Chakrabarti, Andreas Veit, Michal Lukasik, Himanshu Jain, Frederick Liu, Yin-Wen Chang, Sanjiv Kumar
Leveraging redundancy in attention with Reuse Transformers. CoRR (2021)
Pu-Chin Chen, Henry Tsai, Srinadh Bhojanapalli, Hyung Won Chung, Yin-Wen Chang, Chun-Sung Ferng
Demystifying the Better Performance of Position Encoding Variants for Transformer. CoRR (2021)
Michal Lukasik, Srinadh Bhojanapalli, Aditya Krishna Menon, Sanjiv Kumar
Teacher's pet: understanding and mitigating biases in distillation. CoRR (2021)
Srinadh Bhojanapalli, Ayan Chakrabarti, Himanshu Jain, Sanjiv Kumar, Michal Lukasik, Andreas Veit
Eigen Analysis of Self-Attention and its Reconstruction from Partial Computation. CoRR (2021)
Srinadh Bhojanapalli, Ayan Chakrabarti, Daniel Glasner, Daliang Li, Thomas Unterthiner, Andreas Veit
Understanding Robustness of Transformers for Image Classification. ICCV (2021)
Jingzhao Zhang, Aditya Krishna Menon, Andreas Veit, Srinadh Bhojanapalli, Sanjiv Kumar, Suvrit Sra
Coping with Label Shift via Distributionally Robust Optimisation. ICLR (2021)
Srinadh Bhojanapalli, Kimberly Wilber, Andreas Veit, Ankit Singh Rawat, Seungyeon Kim, Aditya Krishna Menon, Sanjiv Kumar
On the Reproducibility of Neural Network Predictions. CoRR (2021)
Pu-Chin Chen, Henry Tsai, Srinadh Bhojanapalli, Hyung Won Chung, Yin-Wen Chang, Chun-Sung Ferng
A Simple and Effective Positional Encoding for Transformers. EMNLP (1) (2021)
Srinadh Bhojanapalli, Ayan Chakrabarti, Daniel Glasner, Daliang Li, Thomas Unterthiner, Andreas Veit
Understanding Robustness of Transformers for Image Classification. CoRR (2021)
Chen Zhu, Ankit Singh Rawat, Manzil Zaheer, Srinadh Bhojanapalli, Daliang Li, Felix X. Yu, Sanjiv Kumar
Modifying Memories in Transformer Models. CoRR (2020)
Srinadh Bhojanapalli, Chulhee Yun, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar
Low-Rank Bottleneck in Multi-head Attention Models. CoRR (2020)
Rudy Bunel, Oliver Hinder, Srinadh Bhojanapalli, Krishnamurthy Dvijotham
An efficient nonconvex reformulation of stagewise convex optimization problems. CoRR (2020)
Michal Lukasik, Srinadh Bhojanapalli, Aditya Krishna Menon, Sanjiv Kumar
Does label smoothing mitigate label noise? CoRR (2020)
Michal Lukasik, Himanshu Jain, Aditya Krishna Menon, Seungyeon Kim, Srinadh Bhojanapalli, Felix X. Yu, Sanjiv Kumar
Semantic Label Smoothing for Sequence to Sequence Problems. EMNLP (1) (2020)
Chulhee Yun, Srinadh Bhojanapalli, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar
Are Transformers universal approximators of sequence-to-sequence functions? ICLR (2020)
Srinadh Bhojanapalli, Chulhee Yun, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar
Low-Rank Bottleneck in Multi-head Attention Models. ICML (2020)
Michal Lukasik, Himanshu Jain, Aditya Krishna Menon, Seungyeon Kim, Srinadh Bhojanapalli, Felix X. Yu, Sanjiv Kumar
Semantic Label Smoothing for Sequence to Sequence Problems. CoRR (2020)
Chulhee Yun, Yin-Wen Chang, Srinadh Bhojanapalli, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar
$O(n)$ Connections are Expressive Enough: Universal Approximability of Sparse Transformers. CoRR (2020)
Chulhee Yun, Yin-Wen Chang, Srinadh Bhojanapalli, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar
O(n) Connections are Expressive Enough: Universal Approximability of Sparse Transformers. NeurIPS (2020)
Rudy Bunel, Oliver Hinder, Srinadh Bhojanapalli, Krishnamurthy Dvijotham
An efficient nonconvex reformulation of stagewise convex optimization problems. NeurIPS (2020)
Yang You, Jing Li, Sashank J. Reddi, Jonathan Hseu, Sanjiv Kumar, Srinadh Bhojanapalli, Xiaodan Song, James Demmel, Kurt Keutzer, Cho-Jui Hsieh
Large Batch Optimization for Deep Learning: Training BERT in 76 minutes. ICLR (2020)
Michal Lukasik, Srinadh Bhojanapalli, Aditya Krishna Menon, Sanjiv Kumar
Does label smoothing mitigate label noise? ICML (2020)
Jingzhao Zhang, Aditya Krishna Menon, Andreas Veit, Srinadh Bhojanapalli, Sanjiv Kumar, Suvrit Sra
Coping with Label Shift via Distributionally Robust Optimisation. CoRR (2020)
Chulhee Yun, Srinadh Bhojanapalli, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar
Are Transformers universal approximators of sequence-to-sequence functions? CoRR (2019)
Behnam Neyshabur, Zhiyuan Li, Srinadh Bhojanapalli, Yann LeCun, Nathan Srebro
The role of over-parametrization in generalization of neural networks. ICLR (Poster) (2019)
Behnam Neyshabur, Srinadh Bhojanapalli, Nathan Srebro
A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks. ICLR (Poster) (2018)
Suriya Gunasekar, Blake E. Woodworth, Srinadh Bhojanapalli, Behnam Neyshabur, Nathan Srebro
Implicit Regularization in Matrix Factorization. ITA (2018)
Srinadh Bhojanapalli, Nicolas Boumal, Prateek Jain, Praneeth Netrapalli
Smoothed analysis for low-rank solutions to semidefinite programs in quadratic penalty form. COLT (2018)
Behnam Neyshabur, Zhiyuan Li, Srinadh Bhojanapalli, Yann LeCun, Nathan Srebro
Towards Understanding the Role of Over-Parametrization in Generalization of Neural Networks. CoRR (2018)
Srinadh Bhojanapalli, Nicolas Boumal, Prateek Jain, Praneeth Netrapalli
Smoothed analysis for low-rank solutions to semidefinite programs in quadratic penalty form. CoRR (2018)
Suriya Gunasekar, Blake E. Woodworth, Srinadh Bhojanapalli, Behnam Neyshabur, Nathan Srebro
Implicit Regularization in Matrix Factorization. CoRR (2017)
Behnam Neyshabur, Srinadh Bhojanapalli, David McAllester, Nathan Srebro
A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks. CoRR (2017)
Behnam Neyshabur, Srinadh Bhojanapalli, David McAllester, Nati Srebro
Exploring Generalization in Deep Learning. NIPS (2017)
Suriya Gunasekar, Blake E. Woodworth, Srinadh Bhojanapalli, Behnam Neyshabur, Nati Srebro
Implicit Regularization in Matrix Factorization. NIPS (2017)
Anastasios Kyrillidis, Amir Kalev, Dohyung Park, Srinadh Bhojanapalli, Constantine Caramanis, Sujay Sanghavi
Provable quantum state tomography via non-convex methods. CoRR (2017)
Behnam Neyshabur, Srinadh Bhojanapalli, Ayan Chakrabarti
Stabilizing GAN Training with Multiple Random Projections. CoRR (2017)
Behnam Neyshabur, Srinadh Bhojanapalli, David McAllester, Nathan Srebro
Exploring Generalization in Deep Learning. CoRR (2017)
Srinadh Bhojanapalli, Behnam Neyshabur, Nathan Srebro
Global Optimality of Local Search for Low Rank Matrix Recovery. CoRR (2016)
Srinadh Bhojanapalli, Behnam Neyshabur, Nati Srebro
Global Optimality of Local Search for Low Rank Matrix Recovery. NIPS (2016)
Shanshan Wu, Srinadh Bhojanapalli, Sujay Sanghavi, Alexandros G. Dimakis
Single Pass PCA of Matrix Products. CoRR (2016)
Srinadh Bhojanapalli, Anastasios Kyrillidis, Sujay Sanghavi
Dropping Convexity for Faster Semi-definite Optimization. COLT (2016)
Shanshan Wu, Srinadh Bhojanapalli, Sujay Sanghavi, Alexandros G. Dimakis
Single Pass PCA of Matrix Products. NIPS (2016)
Dohyung Park, Anastasios Kyrillidis, Srinadh Bhojanapalli, Constantine Caramanis, Sujay Sanghavi
Provable non-convex projected gradient descent for a class of constrained matrix optimization problems. CoRR (2016)
Yudong Chen, Srinadh Bhojanapalli, Sujay Sanghavi, Rachel Ward
Completing any low-rank matrix, provably. J. Mach. Learn. Res. 16 (2015)
Srinadh Bhojanapalli, Prateek Jain, Sujay Sanghavi
Tighter Low-rank Approximation via Sampling the Leveraged Element. SODA (2015)
Srinadh Bhojanapalli, Sujay Sanghavi
A New Sampling Technique for Tensors. CoRR (2015)
Srinadh Bhojanapalli, Anastasios Kyrillidis, Sujay Sanghavi
Dropping Convexity for Faster Semi-definite Optimization. CoRR (2015)
Srinadh Bhojanapalli, Prateek Jain
Universal Matrix Completion. ICML (2014)
Srinadh Bhojanapalli, Prateek Jain, Sujay Sanghavi
Tighter Low-rank Approximation via Sampling the Leveraged Element. CoRR (2014)
Srinadh Bhojanapalli, Prateek Jain
Universal Matrix Completion. CoRR (2014)
Yudong Chen, Srinadh Bhojanapalli, Sujay Sanghavi, Rachel Ward
Coherent Matrix Completion. ICML (2014)
Srinadh Bhojanapalli, Yudong Chen, Sujay Sanghavi, Rachel Ward
Coherent Matrix Completion. CoRR (2013)