Nicolas Macris
11 papers · 2016–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
🐝 Cross-Pollinator (14) 🌍 Conference Polyglot (4) 🏃 Academic Marathon (9) 🌉 Interdisciplinary Bridge 🗺️ Taxonomy Completionist (22)
🧭
Keyword Pioneer
🐣
Hot Topic Early Bird
💎
Century Club
(11)
Conferences
NIPS (7)
COLT (2)
AISTATS (1)
ICML (1)
Top co-authors
Keywords
approximate message passing
(4)
mutual information
(4)
phase transition
(4)
generalization error
(3)
random matrix theory
(3)
rank-one matrix
(2)
mean square error
(2)
matrix estimation
(2)
high-dimensional inference
(1)
neural network theory
(1)
high-dimensional statistics
(1)
asymptotic analysis
(1)
message passing
(1)
gradient descent
(1)
signal-to-noise ratio
(1)
replica method
(1)
generalized linear model
(1)
gradient flow
(1)
random feature model
(1)
committee machine
(1)
Papers
Sampling in High-Dimensions using Stochastic Interpolants and Forward-Backward Stochastic Differential Equations
AISTATS 2025
Stochastic Gradient Flow Dynamics of Test Risk and its Exact Solution for Weak Features
ICML 2024
Bayesian Extensive-Rank Matrix Factorization with Rotational Invariant Priors
NIPS 2023
Model, sample, and epoch-wise descents: exact solution of gradient flow in the random feature model
NIPS 2021
Rank-one matrix estimation: analytic time evolution of gradient descent dynamics
COLT 2021
Information theoretic limits of learning a sparse rule
NIPS 2020
All-or-nothing statistical and computational phase transitions in sparse spiked matrix estimation
NIPS 2020
The committee machine: Computational to statistical gaps in learning a two-layers neural network
NIPS 2018
Optimal Errors and Phase Transitions in High-Dimensional Generalized Linear Models
COLT 2018
Entropy and mutual information in models of deep neural networks
NIPS 2018
Mutual information for symmetric rank-one matrix estimation: A proof of the replica formula
NIPS 2016