← Authors

Sujay Sanghavi

56 papers · 2007–2025 · 8 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird πŸƒ Academic Marathon (18) 🌍 Conference Polyglot (8) 🌈 Renaissance Researcher (5) πŸŒ‰ Interdisciplinary Bridge 🐝 Cross-Pollinator (7) πŸ—ΊοΈ Taxonomy Completionist (31) 🧭 Keyword Pioneer 🏠 Conference Loyalist (24) 🌟 Keyword Trendsetter Combo (3) πŸ‘‘ Triple Crown πŸ† Keyword Champion (4) πŸ‘₯ Mega-Team (60) 🌱 Topic Pioneer πŸ”¬ Deep Specialist (16) ⚑ Prolific Year (7) πŸ“ˆ Trend Setter πŸ’Ž Century Club (56) πŸ—ƒοΈ Keyword Collector (85) πŸ”₯ Unstoppable (16)

Conferences

NIPS (24) ICML (17) AISTATS (6) ICLR (3) JMLR (3) COLT (1) NAACL (1) UAI (1)

Top co-authors

Sanjay Shakkottai (7) Constantine Caramanis (6) Rudrajit Das (6) Tongzheng Ren (5) Yanyao Shen (5) Inderjit S. Dhillon (4) Yudong Chen (4) Alex Dimakis (4) Shanshan Wu (4) Srinadh Bhojanapalli (4)

Keywords

sample complexity (6) non-convex optimization (6) convex optimization (6) matrix completion (5) regret bound (4) parameter estimation (4) outlier detection (3) convergence rate (3) gradient descent (3) sparse recovery (3) knowledge distillation (3) stochastic gradient descent (3) low-rank matrix (3) multi-armed bandit (3) matrix decomposition (3) alternating minimization (3) graphical model (3) message passing (2) subspace clustering (2) label noise (2)

Papers

Retraining with Predicted Hard Labels Provably Increases Model Accuracy ICML 2025
InfoPO: On Mutual Information Maximization for Large Language Model Alignment NAACL 2025
Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting ICML 2025
Geometric Median (GM) Matching for Robust k-Subset Selection from Noisy Data ICML 2025
Enhancing Language Model Agents using Diversity of Thoughts ICLR 2025
Infilling Score: A Pretraining Data Detection Algorithm for Large Language Models ICLR 2025
Learning Mixtures of Experts with EM: A Mirror Descent Perspective ICML 2025
Understanding the Training Speedup from Sampling with Approximate Losses ICML 2024
Adaptive and Optimal Second-order Optimistic Methods for Minimax Optimization NIPS 2024
In-Context Learning with Transformers: Softmax Attention Adapts to Function Lipschitzness NIPS 2024
Improving Computational Complexity in Statistical Models with Local Curvature Information ICML 2024
DataComp-LM: In search of the next generation of training sets for language models NIPS 2024
SVFT: Parameter-Efficient Fine-Tuning with Singular Vectors NIPS 2024
Time Weaver: A Conditional Time Series Generation Model ICML 2024
Understanding Self-Distillation in the Presence of Label Noise ICML 2023
Finite-Time Logarithmic Bayes Regret Upper Bounds NIPS 2023
Beyond Uniform Lipschitz Condition in Differentially Private Optimization ICML 2023
Latent Variable Representation for Reinforcement Learning ICLR 2023
Sample Efficiency of Data Augmentation Consistency Regularization AISTATS 2023
Faster non-convex federated learning via global and local momentum UAI 2022
Toward Understanding Privileged Features Distillation in Learning-to-Rank NIPS 2022
Minimax Regret for Cascading Bandits NIPS 2022
Towards Statistical and Computational Complexities of Polyak Step Size Gradient Descent AISTATS 2022
Robust Training in High Dimensions via Block Coordinate Geometric Median Descent AISTATS 2022
Asymptotically-Optimal Gaussian Bandits with Side Observations ICML 2022
Linear Bandit Algorithms with Sublinear Time Complexity ICML 2022
Nearly Horizon-Free Offline Reinforcement Learning NIPS 2021
Extreme Multi-label Classification from Aggregated Labels ICML 2020
Choosing the Sample with Lowest Loss makes SGD Robust AISTATS 2020
Learning Distributions Generated by One-Layer ReLU Networks NIPS 2019
Blocking Bandits NIPS 2019
Interaction Hard Thresholding: Consistent Sparse Quadratic Regression in Sub-quadratic Time and Space NIPS 2019
Learning a Compressed Sensing Measurement Matrix via Gradient Unrolling ICML 2019
Sparse Logistic Regression Learns All Discrete Pairwise Graphical Models NIPS 2019
Iterative Least Trimmed Squares for Mixed Linear Regression NIPS 2019
Learning with Bad Training Data via Iterative Trimmed Loss Minimization ICML 2019
The Search Problem in Mixture Models JMLR 2018
Non-square matrix sensing without spurious local minima via the Burer-Monteiro approach AISTATS 2017
Normalized Spectral Map Synchronization NIPS 2016
Dropping Convexity for Faster Semi-definite Optimization COLT 2016
Single Pass PCA of Matrix Products NIPS 2016
Preference Completion: Large-scale Collaborative Ranking from Pairwise Comparisons ICML 2015
Convergence Rates of Active Learning for Maximum Likelihood Estimation NIPS 2015
Completing Any Low-rank Matrix, Provably JMLR 2015
Coherent Matrix Completion ICML 2014
Alternating Minimization for Mixed Linear Regression ICML 2014
Non-convex Robust PCA NIPS 2014
Greedy Subspace Clustering NIPS 2014
Clustering Partially Observed Graphs via Convex Optimization JMLR 2014
Phase Retrieval using Alternating Minimization NIPS 2013
Clustering Sparse Graphs NIPS 2012
On Learning Discrete Graphical Models using Group-Sparse Regularization AISTATS 2011
A Dirty Model for Multi-task Learning NIPS 2010
Robust PCA via Outlier Pursuit NIPS 2010
Message Passing for Max-weight Independent Set NIPS 2007
Linear programming analysis of loopy belief propagation for weighted matching NIPS 2007