Jonathan Lacotte

Publication Activity (10 Years)

Years Active: 2017-2023
Publications (10 Years): 26

Top Topics

Convex Quadratic Optimization

Inverse Reinforcement Learning

Top Venues

Publications

Tolga Ergen, Halil Ibrahim Gulluk, Jonathan Lacotte, Mert Pilanci
Globally Optimal Training of Neural Networks with Threshold Activation Functions. ICLR (2023)
Tolga Ergen, Halil Ibrahim Gulluk, Jonathan Lacotte, Mert Pilanci
Globally Optimal Training of Neural Networks with Threshold Activation Functions. CoRR (2023)
Jonathan Lacotte, Mert Pilanci
Adaptive and Oblivious Randomized Subspace Methods for High-Dimensional Optimization: Sharp Analysis and Lower Bounds. IEEE Trans. Inf. Theory 68 (5) (2022)
Yifei Wang, Jonathan Lacotte, Mert Pilanci
The Hidden Convex Optimization Landscape of Regularized Two-Layer ReLU Networks: an Exact Characterization of Optimal Solutions. ICLR (2022)
Jonathan Lacotte, Mert Pilanci
Fast Convex Quadratic Optimization Solvers with Adaptive Sketching-based Preconditioners. CoRR (2021)
Michal Derezinski, Jonathan Lacotte, Mert Pilanci, Michael W. Mahoney
Newton-LESS: Sparsification without Trade-offs for the Sketched Newton Update. NeurIPS (2021)
Jonathan Lacotte, Yifei Wang, Mert Pilanci
Adaptive Newton Sketch: Linear-time Optimization with Quadratic Convergence and Effective Hessian Dimensionality. CoRR (2021)
Jonathan Lacotte, Yifei Wang, Mert Pilanci
Adaptive Newton Sketch: Linear-time Optimization with Quadratic Convergence and Effective Hessian Dimensionality. ICML (2021)
Michal Derezinski, Jonathan Lacotte, Mert Pilanci, Michael W. Mahoney
Newton-LESS: Sparsification without Trade-offs for the Sketched Newton Update. CoRR (2021)
Jonathan Lacotte, Mert Pilanci
Optimal Randomized First-Order Methods for Least-Squares Problems. CoRR (2020)
Jonathan Lacotte, Mert Pilanci
Optimal Randomized First-Order Methods for Least-Squares Problems. ICML (2020)
Jonathan Lacotte, Mert Pilanci
Effective Dimension Adaptive Sketching Methods for Faster Regularized Least-Squares Optimization. NeurIPS (2020)
Jonathan Lacotte, Mert Pilanci
Effective Dimension Adaptive Sketching Methods for Faster Regularized Least-Squares Optimization. CoRR (2020)
Jonathan Lacotte, Sifan Liu, Edgar Dobriban, Mert Pilanci
Limiting Spectrum of Randomized Hadamard Transform and Optimal Iterative Sketching Methods. CoRR (2020)
Jonathan Lacotte, Mert Pilanci
Adaptive and Oblivious Randomized Subspace Methods for High-Dimensional Optimization: Sharp Analysis and Lower Bounds. CoRR (2020)
Jonathan Lacotte, Sifan Liu, Edgar Dobriban, Mert Pilanci
Optimal Iterative Sketching Methods with the Subsampled Randomized Hadamard Transform. NeurIPS (2020)
Jonathan Lacotte, Mert Pilanci
All Local Minima are Global for Two-Layer ReLU Neural Networks: The Hidden Convex Optimization Landscape. CoRR (2020)
Margaret P. Chapman, Jonathan Lacotte, Aviv Tamar, Donggun Lee, Kevin M. Smith, Victoria Cheng, Jaime F. Fisac, Susmit Jha, Marco Pavone, Claire J. Tomlin
A Risk-Sensitive Finite-Time Reachability Approach for Safety of Stochastic Dynamic Systems. ACC (2019)
Margaret P. Chapman, Jonathan Lacotte, Aviv Tamar, Donggun Lee, Kevin M. Smith, Victoria Cheng, Jaime F. Fisac, Susmit Jha, Marco Pavone, Claire J. Tomlin
A Risk-Sensitive Finite-Time Reachability Approach for Safety of Stochastic Dynamic Systems. CoRR (2019)
Jonathan Lacotte, Mert Pilanci, Marco Pavone
High-Dimensional Optimization in Adaptive Random Subspaces. CoRR (2019)
Jonathan Lacotte, Mert Pilanci, Marco Pavone
High-Dimensional Optimization in Adaptive Random Subspaces. NeurIPS (2019)
Jonathan Lacotte, Mert Pilanci
Faster Least Squares Optimization. CoRR (2019)
Jonathan Lacotte, Mohammad Ghavamzadeh, Yinlam Chow, Marco Pavone
Risk-Sensitive Generative Adversarial Imitation Learning. AISTATS (2019)
Jonathan Lacotte, Yinlam Chow, Mohammad Ghavamzadeh, Marco Pavone
Risk-Sensitive Generative Adversarial Imitation Learning. CoRR (2018)
Sumeet Singh, Jonathan Lacotte, Anirudha Majumdar, Marco Pavone
Risk-sensitive inverse reinforcement learning via semi- and non-parametric methods. Int. J. Robotics Res. 37 (13-14) (2018)
Sumeet Singh, Jonathan Lacotte, Anirudha Majumdar, Marco Pavone
Risk-sensitive Inverse Reinforcement Learning via Semi- and Non-Parametric Methods. CoRR (2017)