Srinadh Bhojanapalli
30 papers · 2014–2025 · 7 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+12 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (49) π Academic Marathon Β· Half π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π
Keyword Champion
(3)
π
Triple Crown
π§¬
Topic Evolution
π€
Dynamic Duo
(11)
π
Conference Pioneer
π₯
Unstoppable Β· Silver
β
The Questioner
(3)
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
π
Renaissance Researcher
(5)
π
Trend Setter
ποΈ
Keyword Collector
(130)
Top co-authors
Research topics
Machine Learning
(23)
Deep Learning
(19)
Optimization & Theory Β· Machine Learning
(19)
Architectures
(12)
Mathematics & Optimization
(7)
Optimization
(7)
Optimization & Theory Β· Deep Learning
(6)
Learning Types Β· Deep Learning
(5)
Techniques
(5)
Core Methods
(4)
Learning Types Β· Machine Learning
(4)
Mathematics
(4)
Artificial Intelligence
(3)
Core AI
(3)
Natural Language Processing
(2)
Keywords
transformer architecture
(5)
gradient descent
(5)
neural network
(4)
matrix completion
(4)
generalization bound
(4)
positional encoding
(3)
nuclear norm
(3)
attention mechanism
(3)
matrix factorization
(3)
stochastic gradient descent
(2)
convex optimization
(2)
leverage score
(2)
embedding dimension
(2)
semidefinite programming
(2)
low-rank matrix
(2)
label smoothing
(2)
knowledge distillation
(2)
universal approximation
(2)
permutation equivariance
(2)
spectral norm
(2)
Papers
Arithmetic Transformers Can Length-Generalize in Both Operand Length and Count
ICLR 2025
Dual-Encoders for Extreme Multi-label Classification
ICLR 2024
Functional Interpolation for Relative Positions improves Long Context Transformers
ICLR 2024
Position Coupling: Improving Length Generalization of Arithmetic Transformers Using Task Structure
NeurIPS 2024
On student-teacher deviations in distillation: does it pay to disobey?
NeurIPS 2023
The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers
ICLR 2023
Treeformer: Dense Gradient Trees for Efficient Attention Computation
ICLR 2023
On the Adversarial Robustness of Mixture of Experts
NeurIPS 2022
Robust Training of Neural Networks Using Scale Invariant Architectures
ICML 2022
A Simple and Effective Positional Encoding for Transformers
EMNLP 2021
Coping with Label Shift via Distributionally Robust Optimisation
ICLR 2021
Understanding Robustness of Transformers for Image Classification
ICCV 2021
An efficient nonconvex reformulation of stagewise convex optimization problems
NeurIPS 2020
Are Transformers universal approximators of sequence-to-sequence functions?
ICLR 2020
Does label smoothing mitigate label noise?
ICML 2020
Large Batch Optimization for Deep Learning: Training BERT in 76 minutes
ICLR 2020
Low-Rank Bottleneck in Multi-head Attention Models
ICML 2020
O(n) Connections are Expressive Enough: Universal Approximability of Sparse Transformers
NeurIPS 2020
Semantic Label Smoothing for Sequence to Sequence Problems
EMNLP 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
Exploring Generalization in Deep Learning
NeurIPS 2017
Implicit Regularization in Matrix Factorization
NeurIPS 2017
Dropping Convexity for Faster Semi-definite Optimization
COLT 2016
Global Optimality of Local Search for Low Rank Matrix Recovery
NeurIPS 2016
Single Pass PCA of Matrix Products
NeurIPS 2016
Completing Any Low-rank Matrix, Provably
JMLR 2015
Coherent Matrix Completion
ICML 2014
Universal Matrix Completion
ICML 2014