Srinadh Bhojanapalli
Artificial Intelligence · 2014–2025
A researcher in the Science corpus: 18 papers; trusts 856 researchers and is trusted by 256 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 311 citations into it; #2,395 of 36,961 by trust here, #1,952 by citations
- Computer Vision and Pattern Recognition — 152 citations into it; #3,803 of 21,973 by trust here, #2,277 by citations
- Computational Mechanics — 85 citations into it; #1,191 of 10,021 by trust here, #1,086 by citations
- Optimization & Training — 75 citations into it; #1,377 of 2,605 by trust here, #429 by citations
- Natural Language Processing — 57 citations into it
- Model Architectures — 55 citations into it
- Statistical Learning Theory — 41 citations into it; #394 of 1,040 by trust here, #235 by citations
- Scaling & Learning Theory — 39 citations into it; #43 of 429 by trust here, #41 by citations
Whom Srinadh Bhojanapalli trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- David A. McAllester
- E.J. Candes
- Geoffrey E. Hinton
- B. Recht
- Alex Krizhevsky
- Peter L. Bartlett
- Yoshua Bengio
- Kaiming He
- Diederik P. Kingma
- Behnam Neyshabur
Who trusts Srinadh Bhojanapalli overall
- Samet Oymak
- Vaishnavh Nagarajan
- Colin Wei
- Yuanzhi Li
- Behnam Neyshabur
- Tengyu Ma
- Zhiwei Jia
- Jason D. Lee
- J. Kolter
- Rong Ge
Papers from Srinadh Bhojanapalli's perspective
Ordered by how strongly the researchers Srinadh Bhojanapalli trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Learning Multiple Layers of Features from Tiny Images
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- Large Batch Optimization for Deep Learning: Training BERT in 76 minutes (2019) — 1,222 citations
- Exploring Generalization in Deep Learning (2017) — 1,437 citations
- A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks (2017) — 677 citations
- Towards Understanding the Role of Over-Parametrization in Generalization of Neural Networks (2018) — 403 citations
- Modifying Memories in Transformer Models (2020) — 278 citations
- The role of over-parametrization in generalization of neural networks (2019) — 214 citations
- Understanding Robustness of Transformers for Image Classification (2021) — 515 citations
- Are Transformers universal approximators of sequence-to-sequence functions? (2019) — 533 citations
- Stabilizing GAN Training with Multiple Random Projections (2017) — 85 citations
- Does label smoothing mitigate label noise? (2020) — 424 citations
- $O(n)$ Connections are Expressive Enough: Universal Approximability of Sparse Transformers (2020) — 108 citations
- Global Optimality of Local Search for Low Rank Matrix Recovery (2016) — 412 citations
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities (2025) — 3,609 citations
- SPECTRALLY-NORMALIZED MARGIN BOUNDS FOR NEURAL NETWORKS (2018)
- Implicit Regularization in Matrix Factorization (2017) — 585 citations
- Dropping Convexity for Faster Semi-definite Optimization (2015) — 183 citations
- Universal Matrix Completion (2014) — 106 citations
- Tighter Low-rank Approximation via Sampling the Leveraged Element (2014) — 37 citations