Ard A. Louis
4 papers · 2019–2024 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Conference Polyglot (4) π Academic Marathon (5) π Interdisciplinary Bridge π§ Keyword Pioneer π Cross-Pollinator (15)
β
The Questioner
Conferences
AAAI (1)
ICLR (1)
JMLR (1)
NIPS (1)
Top co-authors
Keywords
neural network
(2)
multitask learning
(1)
theoretical analysis
(1)
gaussian process
(1)
generalization error
(1)
kernel regression
(1)
bayesian posterior
(1)
random matrix theory
(1)
deep neural network
(1)
scaling law
(1)
training dynamics
(1)
feature covariance
(1)
overparameterized regime
(1)
double-descent curve
(1)
stochastic gradient descent
(1)
sigmoid emergence
(1)
Papers
An exactly solvable model for emergence and scaling laws in the multitask sparse parity problem
NIPS 2024
Double-Descent Curves in Neural Networks: A New Perspective Using Gaussian Processes
AAAI 2024
Is SGD a Bayesian sampler? Well, almost
JMLR 2021
Deep learning generalizes because the parameter-function map is biased towards simple functions
ICLR 2019