Praneeth Netrapalli
Artificial Intelligence · 2012–2025
A researcher in the Science corpus: 22 papers; trusts 743 researchers and is trusted by 211 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 375 citations into it; #2,647 of 36,961 by trust here, #3,376 by citations
- Optimization & Training — 211 citations into it; #867 of 2,605 by trust here, #1,048 by citations
- Computational Mechanics — 170 citations into it; #266 of 10,021 by trust here, #276 by citations
- Computer Vision and Pattern Recognition — 98 citations into it; #3,830 of 21,973 by trust here, #4,945 by citations
- Management Science and Operations Research — 85 citations into it; #4,483 of 12,201 by trust here, #3,998 by citations
- Reinforcement Learning — 66 citations into it; #957 of 2,250 by trust here, #1,207 by citations
- Computational Theory and Mathematics — 64 citations into it; #4,295 of 12,489 by trust here, #1,214 by citations
- Statistics and Probability — 61 citations into it; #4,750 of 13,188 by trust here, #3,220 by citations
Whom Praneeth Netrapalli trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Yurii E. Nesterov
- Francis R. Bach
- E.J. Candes
- Geoffrey E. Hinton
- Alex Krizhevsky
- Kaiming He
- Diederik P. Kingma
- Yoshua Bengio
- Shai Shalev-Shwartz
- Ilya Sutskever
Who trusts Praneeth Netrapalli overall
- Prateek Jain
- Rong Ge
- Ju Sun
- Yuxin Chen
- Srinadh Bhojanapalli
- Yuejie Chi
- Sanjeev Arora
- E.J. Candes
- Sham M. Kakade
- Mark A. Davenport
Papers from Praneeth Netrapalli's perspective
Ordered by how strongly the researchers Praneeth Netrapalli 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)
- Gradient-based learning applied to document recognition
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet: A large-scale hierarchical image database
- Learning Multiple Layers of Features from Tiny Images
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- MOReL : Model-Based Offline Reinforcement Learning (2020) — 834 citations
- How to Escape Saddle Points Efficiently (2017) — 945 citations
- On the Insufficiency of Existing Momentum Schemes for Stochastic Optimization (2018) — 135 citations
- Low-rank matrix completion using alternating minimization (2012) — 1,135 citations
- The Pitfalls of Simplicity Bias in Neural Networks (2020) — 478 citations
- Parallelizing Stochastic Gradient Descent for Least Squares Regression: Mini-batching, Averaging, and Model Misspecification (2016) — 188 citations
- Accelerated Gradient Descent Escapes Saddle Points Faster than Gradient Descent (2017) — 294 citations
- Phase Retrieval Using Alternating Minimization (2013) — 667 citations
- Minmax Optimization: Stable Limit Points of Gradient Descent Ascent are Locally Optimal (2019) — 87 citations
- Parallelizing Stochastic Approximation Through Mini-Batching and Tail-Averaging (2016) — 39 citations
- Learning Sparsely Used Overcomplete Dictionaries via Alternating Minimization (2013) — 178 citations
- Rethinking learning rate schedules for stochastic optimization (2018) — 14 citations
- Accelerating Stochastic Gradient Descent (2017) — 84 citations
- Non-convex Robust PCA (2014) — 299 citations
- A Markov Chain Theory Approach to Characterizing the Minimax Optimality of Stochastic Gradient Descent (for Least Squares) (2017) — 41 citations
- Streaming PCA: Matching Matrix Bernstein and Near-Optimal Finite Sample Guarantees for Oja's Algorithm (2016) — 140 citations
- The Step Decay Schedule: A Near Optimal, Geometrically Decaying Learning Rate Procedure (2019) — 188 citations
- SGD without Replacement: Sharper Rates for General Smooth Convex Functions (2019) — 101 citations
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities (2025) — 3,609 citations
- What is Local Optimality in Nonconvex-Nonconcave Minimax Optimization? (2019) — 396 citations