Pierre-antoine Manzagol
7 papers · 2007–2021 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (19) π Academic Marathon (14) π Cross-Pollinator (14) π Interdisciplinary Bridge π§ Keyword Pioneer
π£
Hot Topic Early Bird
π
Conference Polyglot
(4)
π±
Topic Pioneer
π
Trend Setter
β
The Questioner
Conferences
NIPS (3)
JMLR (2)
AISTATS (1)
ICLR (1)
Top co-authors
Keywords
stochastic gradient descent
(2)
stochastic optimization
(1)
representation learning
(1)
multi-task learning
(1)
feature learning
(1)
online learning
(1)
code generation
(1)
natural gradient
(1)
fisher information
(1)
graph-based learning
(1)
generalization error
(1)
large scale optimization
(1)
source code
(1)
online optimization
(1)
variance reduction
(1)
natural gradient descent
(1)
online approximation
(1)
bayesian perspective
(1)
hessian matrix
(1)
optimization algorithm
(1)
Papers
PLUR: A Unifying, Graph-Based View of Program Learning, Understanding, and Repair
NIPS 2021
On the interplay between noise and curvature and its effect on optimization and generalization
AISTATS 2020
Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples
ICLR 2020
Reducing the variance in online optimization by transporting past gradients
NIPS 2019
Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion
JMLR 2010
Why Does Unsupervised Pre-training Help Deep Learning?
JMLR 2010
Topmoumoute Online Natural Gradient Algorithm
NIPS 2007