Sujay Sanghavi

21

Papers

96

Total Citations

Papers (21)

Normalized Spectral Map Synchronization

Time Weaver: A Conditional Time Series Generation Model

Single Pass PCA of Matrix Products

NeurIPS 2016arXiv

Understanding Contrastive Learning via Gaussian Mixture Models

Learning Mixtures of Experts with EM: A Mirror Descent Perspective

Geometric Median (GM) Matching for Robust k-Subset Selection from Noisy Data

Improving Computational Complexity in Statistical Models with Local Curvature Information

Understanding the Training Speedup from Sampling with Approximate Losses

Convergence Rates of Active Learning for Maximum Likelihood Estimation

Finite-Time Logarithmic Bayes Regret Upper Bounds

Preference Completion: Large-scale Collaborative Ranking from Pairwise Comparisons

Learning with Bad Training Data via Iterative Trimmed Loss Minimization

Learning a Compressed Sensing Measurement Matrix via Gradient Unrolling

Interaction Hard Thresholding: Consistent Sparse Quadratic Regression in Sub-quadratic Time and Space

Blocking Bandits

Learning Distributions Generated by One-Layer ReLU Networks

Sparse Logistic Regression Learns All Discrete Pairwise Graphical Models

Iterative Least Trimmed Squares for Mixed Linear Regression

Nearly Horizon-Free Offline Reinforcement Learning

Toward Understanding Privileged Features Distillation in Learning-to-Rank

Minimax Regret for Cascading Bandits