Srinadh Bhojanapalli
30 papers · 2014–2025 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+14 more ↓ Show less ↑
π Renaissance Researcher (7) π Interdisciplinary Bridge π Academic Marathon (11) π Conference Polyglot (7) πΊοΈ Taxonomy Completionist (38)
πΊοΈ
Taxonomy Completionist
(38)
π§
Keyword Pioneer
π£
Hot Topic Early Bird
π€
Dynamic Duo
(11)
π
Triple Crown
π§¬
Topic Evolution
π
Keyword Champion
(3)
π
Conference Pioneer
π
Century Club
(30)
π₯
Unstoppable
(12)
ποΈ
Keyword Collector
(92)
π
Trend Setter
β
The Questioner
(3)
β‘
Prolific Year
(7)
Conferences
ICLR (10)
NIPS (9)
ICML (5)
COLT (2)
EMNLP (2)
ICCV (1)
JMLR (1)
Top co-authors
Keywords
matrix completion
(4)
gradient descent
(4)
nuclear norm
(3)
matrix factorization
(3)
attention mechanism
(3)
transformer architecture
(3)
positional encoding
(2)
neural network
(2)
convex optimization
(2)
stochastic gradient descent
(2)
generalization bound
(2)
semidefinite programming
(2)
label smoothing
(2)
low-rank matrix
(2)
leverage score
(2)
knowledge distillation
(2)
natural language processing
(1)
adversarial robustness
(1)
principal component analysis
(1)
vision transformer
(1)
Papers
Arithmetic Transformers Can Length-Generalize in Both Operand Length and Count
ICLR 2025
Position Coupling: Improving Length Generalization of Arithmetic Transformers Using Task Structure
NIPS 2024
Dual-Encoders for Extreme Multi-label Classification
ICLR 2024
Functional Interpolation for Relative Positions improves Long Context Transformers
ICLR 2024
The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers
ICLR 2023
Treeformer: Dense Gradient Trees for Efficient Attention Computation
ICLR 2023
On student-teacher deviations in distillation: does it pay to disobey?
NIPS 2023
Robust Training of Neural Networks Using Scale Invariant Architectures
ICML 2022
On the Adversarial Robustness of Mixture of Experts
NIPS 2022
A Simple and Effective Positional Encoding for Transformers
EMNLP 2021
Understanding Robustness of Transformers for Image Classification
ICCV 2021
Coping with Label Shift via Distributionally Robust Optimisation
ICLR 2021
Does label smoothing mitigate label noise?
ICML 2020
Semantic Label Smoothing for Sequence to Sequence Problems
EMNLP 2020
Are Transformers universal approximators of sequence-to-sequence functions?
ICLR 2020
Large Batch Optimization for Deep Learning: Training BERT in 76 minutes
ICLR 2020
O(n) Connections are Expressive Enough: Universal Approximability of Sparse Transformers
NIPS 2020
An efficient nonconvex reformulation of stagewise convex optimization problems
NIPS 2020
Low-Rank Bottleneck in Multi-head Attention Models
ICML 2020
The role of over-parametrization in generalization of neural networks
ICLR 2019
A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks
ICLR 2018
Smoothed analysis for low-rank solutions to semidefinite programs in quadratic penalty form
COLT 2018
Implicit Regularization in Matrix Factorization
NIPS 2017
Exploring Generalization in Deep Learning
NIPS 2017
Single Pass PCA of Matrix Products
NIPS 2016
Global Optimality of Local Search for Low Rank Matrix Recovery
NIPS 2016
Dropping Convexity for Faster Semi-definite Optimization
COLT 2016
Completing Any Low-rank Matrix, Provably
JMLR 2015
Universal Matrix Completion
ICML 2014
Coherent Matrix Completion
ICML 2014