Lacotte, Jonathan

9 publications

ICLR 2023 Globally Optimal Training of Neural Networks with Threshold Activation Functions Tolga Ergen, Halil Ibrahim Gulluk, Jonathan Lacotte, Mert Pilanci

ICLR 2022 The Hidden Convex Optimization Landscape of Regularized Two-Layer ReLU Networks: An Exact Characterization of Optimal Solutions Yifei Wang, Jonathan Lacotte, Mert Pilanci

ICML 2021 Adaptive Newton Sketch: Linear-Time Optimization with Quadratic Convergence and Effective Hessian Dimensionality Jonathan Lacotte, Yifei Wang, Mert Pilanci

NeurIPS 2021 Newton-LESS: Sparsification Without Trade-Offs for the Sketched Newton Update Michal Derezinski, Jonathan Lacotte, Mert Pilanci, Michael W. Mahoney

NeurIPS 2020 Effective Dimension Adaptive Sketching Methods for Faster Regularized Least-Squares Optimization Jonathan Lacotte, Mert Pilanci

NeurIPS 2020 Optimal Iterative Sketching Methods with the Subsampled Randomized Hadamard Transform Jonathan Lacotte, Sifan Liu, Edgar Dobriban, Mert Pilanci

ICML 2020 Optimal Randomized First-Order Methods for Least-Squares Problems Jonathan Lacotte, Mert Pilanci

NeurIPS 2019 High-Dimensional Optimization in Adaptive Random Subspaces Jonathan Lacotte, Mert Pilanci, Marco Pavone

AISTATS 2019 Risk-Sensitive Generative Adversarial Imitation Learning Jonathan Lacotte, Mohammad Ghavamzadeh, Yinlam Chow, Marco Pavone