Picture for Nicolas Macris

Nicolas Macris

Stochastic Gradient Flow Dynamics of Test Risk and its Exact Solution for Weak Features

Add code
Feb 12, 2024
Figure 1 for Stochastic Gradient Flow Dynamics of Test Risk and its Exact Solution for Weak Features
Figure 2 for Stochastic Gradient Flow Dynamics of Test Risk and its Exact Solution for Weak Features
Figure 3 for Stochastic Gradient Flow Dynamics of Test Risk and its Exact Solution for Weak Features
Figure 4 for Stochastic Gradient Flow Dynamics of Test Risk and its Exact Solution for Weak Features
Viaarxiv icon

Gradient flow on extensive-rank positive semi-definite matrix denoising

Add code
Mar 16, 2023
Viaarxiv icon

Gradient flow in the gaussian covariate model: exact solution of learning curves and multiple descent structures

Add code
Dec 18, 2022
Viaarxiv icon

Model, sample, and epoch-wise descents: exact solution of gradient flow in the random feature model

Add code
Oct 22, 2021
Figure 1 for Model, sample, and epoch-wise descents: exact solution of gradient flow in the random feature model
Figure 2 for Model, sample, and epoch-wise descents: exact solution of gradient flow in the random feature model
Figure 3 for Model, sample, and epoch-wise descents: exact solution of gradient flow in the random feature model
Figure 4 for Model, sample, and epoch-wise descents: exact solution of gradient flow in the random feature model
Viaarxiv icon

Statistical limits of dictionary learning: random matrix theory and the spectral replica method

Add code
Sep 14, 2021
Figure 1 for Statistical limits of dictionary learning: random matrix theory and the spectral replica method
Figure 2 for Statistical limits of dictionary learning: random matrix theory and the spectral replica method
Viaarxiv icon

Mismatched Estimation of rank-one symmetric matrices under Gaussian noise

Add code
Jul 19, 2021
Figure 1 for Mismatched Estimation of rank-one symmetric matrices under Gaussian noise
Figure 2 for Mismatched Estimation of rank-one symmetric matrices under Gaussian noise
Figure 3 for Mismatched Estimation of rank-one symmetric matrices under Gaussian noise
Figure 4 for Mismatched Estimation of rank-one symmetric matrices under Gaussian noise
Viaarxiv icon

Rank-one matrix estimation: analytic time evolution of gradient descent dynamics

Add code
May 25, 2021
Figure 1 for Rank-one matrix estimation: analytic time evolution of gradient descent dynamics
Figure 2 for Rank-one matrix estimation: analytic time evolution of gradient descent dynamics
Figure 3 for Rank-one matrix estimation: analytic time evolution of gradient descent dynamics
Figure 4 for Rank-one matrix estimation: analytic time evolution of gradient descent dynamics
Viaarxiv icon

Solving non-linear Kolmogorov equations in large dimensions by using deep learning: a numerical comparison of discretization schemes

Add code
Dec 28, 2020
Figure 1 for Solving non-linear Kolmogorov equations in large dimensions by using deep learning: a numerical comparison of discretization schemes
Figure 2 for Solving non-linear Kolmogorov equations in large dimensions by using deep learning: a numerical comparison of discretization schemes
Figure 3 for Solving non-linear Kolmogorov equations in large dimensions by using deep learning: a numerical comparison of discretization schemes
Figure 4 for Solving non-linear Kolmogorov equations in large dimensions by using deep learning: a numerical comparison of discretization schemes
Viaarxiv icon

Information theoretic limits of learning a sparse rule

Add code
Jun 19, 2020
Figure 1 for Information theoretic limits of learning a sparse rule
Figure 2 for Information theoretic limits of learning a sparse rule
Figure 3 for Information theoretic limits of learning a sparse rule
Figure 4 for Information theoretic limits of learning a sparse rule
Viaarxiv icon

All-or-nothing statistical and computational phase transitions in sparse spiked matrix estimation

Add code
Jun 14, 2020
Figure 1 for All-or-nothing statistical and computational phase transitions in sparse spiked matrix estimation
Figure 2 for All-or-nothing statistical and computational phase transitions in sparse spiked matrix estimation
Viaarxiv icon