引用次数
引用: 6,854
H-指数: 25
I10-指数 : 35
出版物: 53
Provable compressed sensing quantum state tomography via non-convex methods
Anastasios Kyrillidis , Amir Kalev , Dohyung Park , Srinadh Bhojanapalli
npj Quantum Information 4 ( 1) 1 -7
26
2018
Robust training of neural networks using scale invariant architectures
Zhiyuan Li , Srinadh Bhojanapalli , Manzil Zaheer , Sashank Reddi
Smpte Journal 12656 -12684
6
2022
A simple and effective positional encoding for transformers
Pu-Chin Chen , Henry Tsai , Srinadh Bhojanapalli , Hyung Won Chung
arXiv preprint arXiv:2104.08698
12
2021
Leveraging redundancy in attention with reuse transformers
Srinadh Bhojanapalli , Ayan Chakrabarti , Andreas Veit , Michal Lukasik
arXiv preprint arXiv:2110.06821
7
2021
Treeformer: Dense gradient trees for efficient attention computation
Lovish Madaan , Srinadh Bhojanapalli , Himanshu Jain , Prateek Jain
arXiv preprint arXiv:2208.09015
1
2022
Large models are parsimonious learners: Activation sparsity in trained transformers
Zonglin Li , Chong You , Srinadh Bhojanapalli , Daliang Li
arXiv preprint arXiv:2210.06313
1
2022
On the adversarial robustness of mixture of experts
Joan Puigcerver , Rodolphe Jenatton , Carlos Riquelme , Pranjal Awasthi
Advances in Neural Information Processing Systems 35 9660 -9671
2022
Functional interpolation for relative positions improves long context transformers
Shanda Li , Chong You , Guru Guruganesh , Joshua Ainslie
arXiv preprint arXiv:2310.04418
13
2023
Modifying Memories in Transformer Models
Ankit Singh Rawat , Chen Zhu , Daliang Li , Felix Yu
International Conference on Machine Learning (ICML) 2020
2
2021
A pac-bayesian approach to spectrally-normalized margin bounds for neural networks
Behnam Neyshabur , Srinadh Bhojanapalli , Nathan Srebro
arXiv preprint arXiv:1707.09564
630
2017
Towards understanding the role of over-parametrization in generalization of neural networks
Behnam Neyshabur , Zhiyuan Li , Srinadh Bhojanapalli , Yann LeCun
arXiv preprint arXiv:1805.12076
576
2018
Position Coupling: Leveraging Task Structure for Improved Length Generalization of Transformers
Hanseul Cho , Jaeyoung Cha , Pranjal Awasthi , Srinadh Bhojanapalli
arXiv preprint arXiv:2405.20671
2024
Coping with label shift via distributionally robust optimisation
Jingzhao Zhang , Aditya Menon , Andreas Veit , Srinadh Bhojanapalli
ICLR 2021
67
2020
Teacher's pet: understanding and mitigating biases in distillation
Michal Lukasik , Srinadh Bhojanapalli , Aditya Krishna Menon , Sanjiv Kumar
arXiv preprint arXiv:2106.10494
24
2021
Eigen analysis of self-attention and its reconstruction from partial computation
Srinadh Bhojanapalli , Ayan Chakrabarti , Himanshu Jain , Sanjiv Kumar
arXiv preprint arXiv:2106.08823
8
2021
Stabilizing GAN training with multiple random projections
Behnam Neyshabur , Srinadh Bhojanapalli , Ayan Chakrabarti
arXiv preprint arXiv:1705.07831
102
2017
On student-teacher deviations in distillation: does it pay to disobey?
Vaishnavh Nagarajan , Aditya K Menon , Srinadh Bhojanapalli , Hossein Mobahi
Advances in Neural Information Processing Systems 36 5961 -6000
3
2023
Efficacy of dual-encoders for extreme multi-label classification
Nilesh Gupta , Devvrit Khatri , Ankit S Rawat , Srinadh Bhojanapalli
arXiv preprint arXiv:2310.10636
2
2023
HiRE: High Recall Approximate Top-$ k $ Estimation for Efficient LLM Inference
Varun Yerram , Chong You , Srinadh Bhojanapalli , Sanjiv Kumar
arXiv preprint arXiv:2402.09360
1
2024
DUAL-ENCODERS FOR EXTREME MULTI-LABEL CLASSIFICATION
Nilesh Gupta , Devvrit Khatri , Ankit Singh Rawat , Srinadh Bhojanapalli