Jonathan Lacotte

26 papers A* 8A 1C 1Journal 16
YearRankTypeTitle / Venue / Authors
2023 A* conf
Globally Optimal Training of Neural Networks with Threshold Activation Functions.
ICLR
Tolga Ergen, Halil Ibrahim Gulluk, Jonathan Lacotte, Mert Pilanci
2023 J jnl
Globally Optimal Training of Neural Networks with Threshold Activation Functions.
CoRR
Tolga Ergen, Halil Ibrahim Gulluk, Jonathan Lacotte, Mert Pilanci
2022 J jnl
Adaptive and Oblivious Randomized Subspace Methods for High-Dimensional Optimization: Sharp Analysis and Lower Bounds.
IEEE Trans. Inf. Theory
Jonathan Lacotte, Mert Pilanci
2022 A* conf
The Hidden Convex Optimization Landscape of Regularized Two-Layer ReLU Networks: an Exact Characterization of Optimal Solutions.
ICLR
Yifei Wang, Jonathan Lacotte, Mert Pilanci
2021 A* conf
Adaptive Newton Sketch: Linear-time Optimization with Quadratic Convergence and Effective Hessian Dimensionality.
ICML
Jonathan Lacotte, Yifei Wang, Mert Pilanci
2021 J jnl
Adaptive Newton Sketch: Linear-time Optimization with Quadratic Convergence and Effective Hessian Dimensionality.
CoRR
Jonathan Lacotte, Yifei Wang, Mert Pilanci
2021 J jnl
Fast Convex Quadratic Optimization Solvers with Adaptive Sketching-based Preconditioners.
CoRR
Jonathan Lacotte, Mert Pilanci
2021 A* conf
Newton-LESS: Sparsification without Trade-offs for the Sketched Newton Update.
NeurIPS
Michal Derezinski, Jonathan Lacotte, Mert Pilanci, Michael W. Mahoney
2021 J jnl
Newton-LESS: Sparsification without Trade-offs for the Sketched Newton Update.
CoRR
Michal Derezinski, Jonathan Lacotte, Mert Pilanci, Michael W. Mahoney
2020 J jnl
Adaptive and Oblivious Randomized Subspace Methods for High-Dimensional Optimization: Sharp Analysis and Lower Bounds.
CoRR
Jonathan Lacotte, Mert Pilanci
2020 J jnl
All Local Minima are Global for Two-Layer ReLU Neural Networks: The Hidden Convex Optimization Landscape.
CoRR
Jonathan Lacotte, Mert Pilanci
2020 A* conf
Effective Dimension Adaptive Sketching Methods for Faster Regularized Least-Squares Optimization.
NeurIPS
Jonathan Lacotte, Mert Pilanci
2020 J jnl
Effective Dimension Adaptive Sketching Methods for Faster Regularized Least-Squares Optimization.
CoRR
Jonathan Lacotte, Mert Pilanci
2020 J jnl
Limiting Spectrum of Randomized Hadamard Transform and Optimal Iterative Sketching Methods.
CoRR
Jonathan Lacotte, Sifan Liu, Edgar Dobriban, Mert Pilanci
2020 A* conf
Optimal Iterative Sketching Methods with the Subsampled Randomized Hadamard Transform.
NeurIPS
Jonathan Lacotte, Sifan Liu, Edgar Dobriban, Mert Pilanci
2020 A* conf
Optimal Randomized First-Order Methods for Least-Squares Problems.
ICML
Jonathan Lacotte, Mert Pilanci
2020 J jnl
Optimal Randomized First-Order Methods for Least-Squares Problems.
CoRR
Jonathan Lacotte, Mert Pilanci
2019 C conf
A Risk-Sensitive Finite-Time Reachability Approach for Safety of Stochastic Dynamic Systems.
ACC
Margaret P. Chapman, Jonathan Lacotte, Aviv Tamar, Donggun Lee, Kevin M. Smith, Victoria Cheng, Jaime F. Fisac, Susmit Jha, Marco Pavone, Claire J. Tomlin
2019 J jnl
A Risk-Sensitive Finite-Time Reachability Approach for Safety of Stochastic Dynamic Systems.
CoRR
Margaret P. Chapman, Jonathan Lacotte, Aviv Tamar, Donggun Lee, Kevin M. Smith, Victoria Cheng, Jaime F. Fisac, Susmit Jha, Marco Pavone, Claire J. Tomlin
2019 J jnl
Faster Least Squares Optimization.
CoRR
Jonathan Lacotte, Mert Pilanci
2019 A* conf
High-Dimensional Optimization in Adaptive Random Subspaces.
NeurIPS
Jonathan Lacotte, Mert Pilanci, Marco Pavone
2019 J jnl
High-Dimensional Optimization in Adaptive Random Subspaces.
CoRR
Jonathan Lacotte, Mert Pilanci, Marco Pavone
2019 A conf
Risk-Sensitive Generative Adversarial Imitation Learning.
AISTATS
Jonathan Lacotte, Mohammad Ghavamzadeh, Yinlam Chow, Marco Pavone
2018 J jnl
Risk-Sensitive Generative Adversarial Imitation Learning.
CoRR
Jonathan Lacotte, Yinlam Chow, Mohammad Ghavamzadeh, Marco Pavone
2018 J jnl
Risk-sensitive inverse reinforcement learning via semi- and non-parametric methods.
Int. J. Robotics Res.
Sumeet Singh, Jonathan Lacotte, Anirudha Majumdar, Marco Pavone
2017 J jnl
Risk-sensitive Inverse Reinforcement Learning via Semi- and Non-Parametric Methods.
CoRR
Sumeet Singh, Jonathan Lacotte, Anirudha Majumdar, Marco Pavone