← Authors

Praneeth Netrapalli

55 papers · 2013–2024 · 8 conferences · across top CS/AI conferences

Achievements

🌈 Renaissance Researcher (8) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (13) πŸƒ Academic Marathon (11) πŸŒ‰ Interdisciplinary Bridge 🌍 Conference Polyglot (8) πŸ—ΊοΈ Taxonomy Completionist (20) 🏠 Conference Loyalist (20) 🀝 Dynamic Duo (31) πŸ‘‘ Triple Crown πŸ† Keyword Champion πŸ† Grand Slam πŸ”¬ Deep Specialist (24) ❓ The Questioner (3) πŸ“ˆ Trend Setter πŸš€ Conference Pioneer πŸ”₯ Unstoppable (12) ⚑ Prolific Year (7) πŸ’Ž Century Club (55) πŸ—ƒοΈ Keyword Collector (61)

Conferences

NIPS (20) COLT (13) ICML (10) ICLR (5) JMLR (3) ALT (2) AAAI (1) AISTATS (1)

Top co-authors

Prateek Jain (31) Chi Jin (9) Sham M. Kakade (9) Rahul Kidambi (7) Aaron Sidford (6) Dheeraj Nagaraj (5) Rong Ge (4) Kiran K Thekumparampil (3) Sujay Sanghavi (3) Naman Agarwal (3)

Research topics

Architectures (1)

Keywords

stochastic gradient descent (11) non-convex optimization (10) sample complexity (6) convex optimization (6) matrix completion (4) gradient descent (4) regret bound (4) online learning (4) alternating minimization (3) low-rank matrix (3) bandit convex optimization (3) experience replay (3) streaming algorithm (3) least squares regression (3) convergence rate (3) nesterov acceleration (3) oracle complexity (2) feature learning (2) strongly convex (2) sparse recovery (2)

Papers

The Feature Speed Formula: a flexible approach to scale hyper-parameters of deep neural networks NIPS 2024
Consistent Multiclass Algorithms for Complex Metrics and Constraints JMLR 2024
Tandem Transformers for Inference Efficient LLMs ICML 2024
Second Order Methods for Bandit Optimization and Control COLT 2024
Near Optimal Heteroscedastic Regression with Symbiotic Learning COLT 2023
Multi-User Reinforcement Learning with Low Rank Rewards ICML 2023
Simplicity Bias in 1-Hidden Layer Neural Networks NIPS 2023
Feature Reconstruction From Outputs Can Mitigate Simplicity Bias in Neural Networks ICLR 2023
Focus on the Common Good: Group Distributional Robustness Follows ICLR 2022
Online Target Q-learning with Reverse Experience Replay: Efficiently finding the Optimal Policy for Linear MDPs ICLR 2022
Reproducibility in Optimization: Theoretical Framework and Limits NIPS 2022
Minimax Optimization with Smooth Algorithmic Adversaries ICLR 2022
Near-Optimal Lower Bounds For Convex Optimization For All Orders of Smoothness NIPS 2021
Optimal regret algorithm for Pseudo-1d Bandit Convex Optimization ICML 2021
Streaming Linear System Identification with Reverse Experience Replay NIPS 2021
Efficient Bandit Convex Optimization: Beyond Linear Losses COLT 2021
Do Input Gradients Highlight Discriminative Features? NIPS 2021
Near-optimal Offline and Streaming Algorithms for Learning Non-Linear Dynamical Systems NIPS 2021
Statistically and Computationally Efficient Linear Meta-representation Learning NIPS 2021
The Pitfalls of Simplicity Bias in Neural Networks NIPS 2020
Least Squares Regression with Markovian Data: Fundamental Limits and Algorithms NIPS 2020
MOReL: Model-Based Offline Reinforcement Learning NIPS 2020
Follow the Perturbed Leader: Optimism and Fast Parallel Algorithms for Smooth Minimax Games NIPS 2020
P-SIF: Document Embeddings Using Partition Averaging AAAI 2020
What is Local Optimality in Nonconvex-Nonconcave Minimax Optimization? ICML 2020
Leverage Score Sampling for Faster Accelerated Regression and ERM ALT 2020
Online Non-Convex Learning: Following the Perturbed Leader is Optimal ALT 2020
Efficient Domain Generalization via Common-Specific Low-Rank Decomposition ICML 2020
Projection Efficient Subgradient Method and Optimal Nonsmooth Frank-Wolfe Method NIPS 2020
The Step Decay Schedule: A Near Optimal, Geometrically Decaying Learning Rate Procedure For Least Squares NIPS 2019
Efficient Algorithms for Smooth Minimax Optimization NIPS 2019
Making the Last Iterate of SGD Information Theoretically Optimal COLT 2019
Open Problem: Do Good Algorithms Necessarily Query Bad Points? COLT 2019
SGD without Replacement: Sharper Rates for General Smooth Convex Functions ICML 2019
Accelerated Gradient Descent Escapes Saddle Points Faster than Gradient Descent COLT 2018
Accelerating Stochastic Gradient Descent for Least Squares Regression COLT 2018
On the insufficiency of existing momentum schemes for Stochastic Optimization ICLR 2018
Support Recovery for Orthogonal Matching Pursuit: Upper and Lower bounds NIPS 2018
Smoothed analysis for low-rank solutions to semidefinite programs in quadratic penalty form COLT 2018
Parallelizing Stochastic Gradient Descent for Least Squares Regression: Mini-batching, Averaging, and Model Misspecification JMLR 2018
Thresholding Based Outlier Robust PCA COLT 2017
Global Convergence of Non-Convex Gradient Descent for Computing Matrix Squareroot AISTATS 2017
How to Escape Saddle Points Efficiently ICML 2017
Information-theoretic thresholds for community detection in sparse networks COLT 2016
Faster Eigenvector Computation via Shift-and-Invert Preconditioning ICML 2016
Efficient Algorithms for Large-scale Generalized Eigenvector Computation and Canonical Correlation Analysis ICML 2016
Learning Planar Ising Models JMLR 2016
Provable Efficient Online Matrix Completion via Non-convex Stochastic Gradient Descent NIPS 2016
Streaming PCA: Matching Matrix Bernstein and Near-Optimal Finite Sample Guarantees for Oja’s Algorithm COLT 2016
Convergence Rates of Active Learning for Maximum Likelihood Estimation NIPS 2015
Fast Exact Matrix Completion with Finite Samples COLT 2015
Learning Sparsely Used Overcomplete Dictionaries COLT 2014
Non-convex Robust PCA NIPS 2014
One-Bit Compressed Sensing: Provable Support and Vector Recovery ICML 2013
Phase Retrieval using Alternating Minimization NIPS 2013