Aristide Baratin
8 papers · 2018–2024 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π£ Hot Topic Early Bird π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (4) π Academic Marathon (6)
π
Cross-Pollinator
(13)
πΊοΈ
Taxonomy Completionist
(18)
π
Triple Crown
Conferences
ICML (5)
AISTATS (1)
ICLR (1)
NIPS (1)
Top co-authors
Keywords
neural network
(2)
representation learning
(2)
neural tangent kernel
(1)
stochastic gradient descent
(1)
variational inference
(1)
information bottleneck
(1)
deep learning theory
(1)
fourier analysis
(1)
adversarial training
(1)
deep learning
(1)
mutual information
(1)
label noise
(1)
semi-supervised training
(1)
gaussian mixture model
(1)
implicit regularization
(1)
sgd dynamics
(1)
spectral bia
(1)
memorization mitigation
(1)
teacher-student setup
(1)
spurious feature
(1)
Papers
Bias in Motion: Theoretical Insights into the Dynamics of Bias in SGD Training
NIPS 2024
How connectivity structure shapes rich and lazy learning in neural circuits
ICLR 2024
Unsupervised Concept Discovery Mitigates Spurious Correlations
ICML 2024
Lookbehind-SAM: k steps back, 1 step forward
ICML 2024
CrossSplit: Mitigating Label Noise Memorization through Data Splitting
ICML 2023
Implicit Regularization via Neural Feature Alignment
AISTATS 2021
On the Spectral Bias of Neural Networks
ICML 2019
Mutual Information Neural Estimation
ICML 2018