Mert Pilanci

14

Papers

9

Total Citations

Papers (14)

Scaling Convex Neural Networks with Burer-Monteiro Factorization

Geometric Algebra Planes: Convex Implicit Neural Volumes

Newton Meets Marchenko-Pastur: Massively Parallel Second-Order Optimization with Hessian Sketching and Debiasing

Active Learning of Deep Neural Networks via Gradient-Free Cutting Planes

Convex Relaxations of ReLU Neural Networks Approximate Global Optima in Polynomial Time

Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models

Fixing the NTK: From Neural Network Linearizations to Exact Convex Programs

Matrix Compression via Randomized Low Rank and Low Precision Factorization

Path Regularization: A Convexity and Sparsity Inducing Regularization for Parallel ReLU Networks

High-Dimensional Optimization in Adaptive Random Subspaces

Debiasing Distributed Second Order Optimization with Surrogate Sketching and Scaled Regularization

Optimal Iterative Sketching Methods with the Subsampled Randomized Hadamard Transform

Effective Dimension Adaptive Sketching Methods for Faster Regularized Least-Squares Optimization

Newton-LESS: Sparsification without Trade-offs for the Sketched Newton Update