Jonathan Lacotte

According to our database, Jonathan Lacotte authored at least 16 papers between 2018 and 2023.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2023

Globally Optimal Training of Neural Networks with Threshold Activation Functions.

Tolga Ergen, Halil Ibrahim Gulluk, Jonathan Lacotte, Mert Pilanci

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

Adaptive and Oblivious Randomized Subspace Methods for High-Dimensional Optimization: Sharp Analysis and Lower Bounds.

Jonathan Lacotte, Mert Pilanci

IEEE Trans. Inf. Theory, 2022

The Hidden Convex Optimization Landscape of Regularized Two-Layer ReLU Networks: an Exact Characterization of Optimal Solutions.

Yifei Wang, Jonathan Lacotte, Mert Pilanci

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

Fast Convex Quadratic Optimization Solvers with Adaptive Sketching-based Preconditioners.

Jonathan Lacotte, Mert Pilanci

CoRR, 2021

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

Michal Derezinski, Jonathan Lacotte, Mert Pilanci, Michael W. Mahoney

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Adaptive Newton Sketch: Linear-time Optimization with Quadratic Convergence and Effective Hessian Dimensionality.

Jonathan Lacotte, Yifei Wang, Mert Pilanci

Proceedings of the 38th International Conference on Machine Learning, 2021

2020

All Local Minima are Global for Two-Layer ReLU Neural Networks: The Hidden Convex Optimization Landscape.

Jonathan Lacotte, Mert Pilanci

CoRR, 2020

Limiting Spectrum of Randomized Hadamard Transform and Optimal Iterative Sketching Methods.

Jonathan Lacotte, Sifan Liu, Edgar Dobriban, Mert Pilanci

CoRR, 2020

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

Jonathan Lacotte, Mert Pilanci

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Optimal Iterative Sketching Methods with the Subsampled Randomized Hadamard Transform.

Jonathan Lacotte, Sifan Liu, Edgar Dobriban, Mert Pilanci

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Optimal Randomized First-Order Methods for Least-Squares Problems.

Jonathan Lacotte, Mert Pilanci

Proceedings of the 37th International Conference on Machine Learning, 2020

2019

Faster Least Squares Optimization.

Jonathan Lacotte, Mert Pilanci

CoRR, 2019

High-Dimensional Optimization in Adaptive Random Subspaces.

Jonathan Lacotte, Mert Pilanci, Marco Pavone

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

A Risk-Sensitive Finite-Time Reachability Approach for Safety of Stochastic Dynamic Systems.

Margaret P. Chapman, Jonathan Lacotte, Aviv Tamar, Donggun Lee, Kevin M. Smith, Victoria Cheng, Jaime F. Fisac, Susmit Jha, Marco Pavone, Claire J. Tomlin

Proceedings of the 2019 American Control Conference, 2019

Risk-Sensitive Generative Adversarial Imitation Learning.

Jonathan Lacotte, Mohammad Ghavamzadeh, Yinlam Chow, Marco Pavone

Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

2018

Risk-sensitive inverse reinforcement learning via semi- and non-parametric methods.

Sumeet Singh, Jonathan Lacotte, Anirudha Majumdar, Marco Pavone

Int. J. Robotics Res., 2018