Srinadh Bhojanapalli

According to our database, Srinadh Bhojanapalli authored at least 49 papers between 2014 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2024

Arithmetic Transformers Can Length-Generalize in Both Operand Length and Count.

Hanseul Cho, Jaeyoung Cha, Srinadh Bhojanapalli, Chulhee Yun

CoRR, 2024

Mimetic Initialization Helps State Space Models Learn to Recall.

Asher Trockman, Hrayr Harutyunyan, J. Zico Kolter, Sanjiv Kumar, Srinadh Bhojanapalli

CoRR, 2024

Position Coupling: Leveraging Task Structure for Improved Length Generalization of Transformers.

Hanseul Cho, Jaeyoung Cha, Pranjal Awasthi, Srinadh Bhojanapalli, Anupam Gupta, Chulhee Yun

CoRR, 2024

Efficient Language Model Architectures for Differentially Private Federated Learning.

Jae Hun Ro, Srinadh Bhojanapalli, Zheng Xu, Yanxiang Zhang, Ananda Theertha Suresh

CoRR, 2024

HiRE: High Recall Approximate Top-k Estimation for Efficient LLM Inference.

Yashas Samaga, Varun Yerram, Chong You, Srinadh Bhojanapalli, Sanjiv Kumar, Prateek Jain, Praneeth Netrapalli

CoRR, 2024

Functional Interpolation for Relative Positions improves Long Context Transformers.

Shanda Li, Chong You, Guru Guruganesh, Joshua Ainslie, Santiago Ontañón, Manzil Zaheer, Sumit Sanghai, Yiming Yang, Sanjiv Kumar, Srinadh Bhojanapalli

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Dual-Encoders for Extreme Multi-label Classification.

Nilesh Gupta, Devvrit, Ankit Singh Rawat, Srinadh Bhojanapalli, Prateek Jain, Inderjit S. Dhillon

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Efficacy of Dual-Encoders for Extreme Multi-Label Classification.

Nilesh Gupta, Devvrit Khatri, Ankit Singh Rawat, Srinadh Bhojanapalli, Prateek Jain, Inderjit S. Dhillon

CoRR, 2023

Depth Dependence of μP Learning Rates in ReLU MLPs.

Samy Jelassi, Boris Hanin, Ziwei Ji, Sashank J. Reddi, Srinadh Bhojanapalli, Sanjiv Kumar

CoRR, 2023

On student-teacher deviations in distillation: does it pay to disobey?

Vaishnavh Nagarajan, Aditya Krishna Menon, Srinadh Bhojanapalli, Hossein Mobahi, Sanjiv Kumar

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Treeformer: Dense Gradient Trees for Efficient Attention Computation.

Lovish Madaan, Srinadh Bhojanapalli, Himanshu Jain, Prateek Jain

Proceedings of the Eleventh International Conference on Learning Representations, 2023

The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers.

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

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

Teacher's pet: understanding and mitigating biases in distillation.

Michal Lukasik, Srinadh Bhojanapalli, Aditya Krishna Menon, Sanjiv Kumar

Trans. Mach. Learn. Res., 2022

Large Models are Parsimonious Learners: Activation Sparsity in Trained Transformers.

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

CoRR, 2022

On the Adversarial Robustness of Mixture of Experts.

Joan Puigcerver, Rodolphe Jenatton, Carlos Riquelme, Pranjal Awasthi, Srinadh Bhojanapalli

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Robust Training of Neural Networks Using Scale Invariant Architectures.

Zhiyuan Li, Srinadh Bhojanapalli, Manzil Zaheer, Sashank J. Reddi, Sanjiv Kumar

Proceedings of the International Conference on Machine Learning, 2022

2021

Leveraging redundancy in attention with Reuse Transformers.

Srinadh Bhojanapalli, Ayan Chakrabarti, Andreas Veit, Michal Lukasik, Himanshu Jain, Frederick Liu, Yin-Wen Chang, Sanjiv Kumar

CoRR, 2021

Eigen Analysis of Self-Attention and its Reconstruction from Partial Computation.

Srinadh Bhojanapalli, Ayan Chakrabarti, Himanshu Jain, Sanjiv Kumar, Michal Lukasik, Andreas Veit

CoRR, 2021

Demystifying the Better Performance of Position Encoding Variants for Transformer.

Pu-Chin Chen, Henry Tsai, Srinadh Bhojanapalli, Hyung Won Chung, Yin-Wen Chang, Chun-Sung Ferng

CoRR, 2021

On the Reproducibility of Neural Network Predictions.

Srinadh Bhojanapalli, Kimberly Wilber, Andreas Veit, Ankit Singh Rawat, Seungyeon Kim, Aditya Krishna Menon, Sanjiv Kumar

CoRR, 2021

Coping with Label Shift via Distributionally Robust Optimisation.

Jingzhao Zhang, Aditya Krishna Menon, Andreas Veit, Srinadh Bhojanapalli, Sanjiv Kumar, Suvrit Sra

Proceedings of the 9th International Conference on Learning Representations, 2021

Understanding Robustness of Transformers for Image Classification.

Srinadh Bhojanapalli, Ayan Chakrabarti, Daniel Glasner, Daliang Li, Thomas Unterthiner, Andreas Veit

Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

A Simple and Effective Positional Encoding for Transformers.

Pu-Chin Chen, Henry Tsai, Srinadh Bhojanapalli, Hyung Won Chung, Yin-Wen Chang, Chun-Sung Ferng

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021

2020

Modifying Memories in Transformer Models.

Chen Zhu, Ankit Singh Rawat, Manzil Zaheer, Srinadh Bhojanapalli, Daliang Li, Felix X. Yu, Sanjiv Kumar

CoRR, 2020

O(n) Connections are Expressive Enough: Universal Approximability of Sparse Transformers.

Chulhee Yun, Yin-Wen Chang, Srinadh Bhojanapalli, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

An efficient nonconvex reformulation of stagewise convex optimization problems.

Rudy Bunel, Oliver Hinder, Srinadh Bhojanapalli, Krishnamurthy Dvijotham

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Does label smoothing mitigate label noise?

Michal Lukasik, Srinadh Bhojanapalli, Aditya Krishna Menon, Sanjiv Kumar

Proceedings of the 37th International Conference on Machine Learning, 2020

Low-Rank Bottleneck in Multi-head Attention Models.

Srinadh Bhojanapalli, Chulhee Yun, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar

Proceedings of the 37th International Conference on Machine Learning, 2020

Are Transformers universal approximators of sequence-to-sequence functions?

Chulhee Yun, Srinadh Bhojanapalli, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar

Proceedings of the 8th International Conference on Learning Representations, 2020

Large Batch Optimization for Deep Learning: Training BERT in 76 minutes.

Yang You, Jing Li, Sashank J. Reddi, Jonathan Hseu, Sanjiv Kumar, Srinadh Bhojanapalli, Xiaodan Song, James Demmel, Kurt Keutzer, Cho-Jui Hsieh

Proceedings of the 8th International Conference on Learning Representations, 2020

Semantic Label Smoothing for Sequence to Sequence Problems.

Michal Lukasik, Himanshu Jain, Aditya Krishna Menon, Seungyeon Kim, Srinadh Bhojanapalli, Felix X. Yu, Sanjiv Kumar

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, 2020

2019

The role of over-parametrization in generalization of neural networks.

Behnam Neyshabur, Zhiyuan Li, Srinadh Bhojanapalli, Yann LeCun, Nathan Srebro

Proceedings of the 7th International Conference on Learning Representations, 2019

2018

Towards Understanding the Role of Over-Parametrization in Generalization of Neural Networks.

Behnam Neyshabur, Zhiyuan Li, Srinadh Bhojanapalli, Yann LeCun, Nathan Srebro

CoRR, 2018

A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks.

Behnam Neyshabur, Srinadh Bhojanapalli, Nathan Srebro

Proceedings of the 6th International Conference on Learning Representations, 2018

Smoothed analysis for low-rank solutions to semidefinite programs in quadratic penalty form.

Srinadh Bhojanapalli, Nicolas Boumal, Prateek Jain, Praneeth Netrapalli

Proceedings of the Conference On Learning Theory, 2018

2017

Provable quantum state tomography via non-convex methods.

Anastasios Kyrillidis, Amir Kalev, Dohyung Park, Srinadh Bhojanapalli, Constantine Caramanis, Sujay Sanghavi

CoRR, 2017

A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks.

Behnam Neyshabur, Srinadh Bhojanapalli, David McAllester, Nathan Srebro

CoRR, 2017

Stabilizing GAN Training with Multiple Random Projections.

Behnam Neyshabur, Srinadh Bhojanapalli, Ayan Chakrabarti

CoRR, 2017

Exploring Generalization in Deep Learning.

Behnam Neyshabur, Srinadh Bhojanapalli, David McAllester, Nati Srebro

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Implicit Regularization in Matrix Factorization.

Suriya Gunasekar, Blake E. Woodworth, Srinadh Bhojanapalli, Behnam Neyshabur, Nati Srebro

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

2016

Provable non-convex projected gradient descent for a class of constrained matrix optimization problems.

Dohyung Park, Anastasios Kyrillidis, Srinadh Bhojanapalli, Constantine Caramanis, Sujay Sanghavi

CoRR, 2016

Single Pass PCA of Matrix Products.

Shanshan Wu, Srinadh Bhojanapalli, Sujay Sanghavi, Alexandros G. Dimakis

Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Global Optimality of Local Search for Low Rank Matrix Recovery.

Srinadh Bhojanapalli, Behnam Neyshabur, Nati Srebro

Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Dropping Convexity for Faster Semi-definite Optimization.

Srinadh Bhojanapalli, Anastasios Kyrillidis, Sujay Sanghavi

Proceedings of the 29th Conference on Learning Theory, 2016

2015

Completing any low-rank matrix, provably.

Yudong Chen, Srinadh Bhojanapalli, Sujay Sanghavi, Rachel A. Ward

J. Mach. Learn. Res., 2015

A New Sampling Technique for Tensors.

Srinadh Bhojanapalli, Sujay Sanghavi

CoRR, 2015

Tighter Low-rank Approximation via Sampling the Leveraged Element.

Srinadh Bhojanapalli, Prateek Jain, Sujay Sanghavi

Proceedings of the Twenty-Sixth Annual ACM-SIAM Symposium on Discrete Algorithms, 2015

2014

Coherent Matrix Completion.

Yudong Chen, Srinadh Bhojanapalli, Sujay Sanghavi, Rachel A. Ward

Proceedings of the 31th International Conference on Machine Learning, 2014

Universal Matrix Completion.

Srinadh Bhojanapalli, Prateek Jain

Proceedings of the 31th International Conference on Machine Learning, 2014