Jonathan Lacotte
9 papers · 2019–2023 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (15) 🏆 Keyword Champion (2) 🔥 Unstoppable · Bronze
🗃️
Keyword Collector
(52)
Venues
Top co-authors
Research topics
Keywords
convex optimization
(3)
convergence rate
(3)
matrix sketching
(2)
effective dimension
(2)
subsampled randomized hadamard transform
(2)
hessian sketch
(2)
function approximation
(1)
logistic regression
(1)
reinforcement learning
(1)
matrix approximation
(1)
coordinate descent
(1)
least squares regression
(1)
hessian matrix
(1)
high-dimensional optimization
(1)
random projection
(1)
iterative sketching
(1)
random matrix theory
(1)
adaptive sampling
(1)
randomized hadamard transform
(1)
second-order optimization
(1)
Papers
Globally Optimal Training of Neural Networks with Threshold Activation Functions
ICLR 2023
The Hidden Convex Optimization Landscape of Regularized Two-Layer ReLU Networks: an Exact Characterization of Optimal Solutions
ICLR 2022
Adaptive Newton Sketch: Linear-time Optimization with Quadratic Convergence and Effective Hessian Dimensionality
ICML 2021
Newton-LESS: Sparsification without Trade-offs for the Sketched Newton Update
NeurIPS 2021
Effective Dimension Adaptive Sketching Methods for Faster Regularized Least-Squares Optimization
NeurIPS 2020
Optimal Iterative Sketching Methods with the Subsampled Randomized Hadamard Transform
NeurIPS 2020
Optimal Randomized First-Order Methods for Least-Squares Problems
ICML 2020
High-Dimensional Optimization in Adaptive Random Subspaces
NeurIPS 2019
Risk-Sensitive Generative Adversarial Imitation Learning
AISTATS 2019