Giorgio Patrini
7 papers · 2014–2021 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (14) π Interdisciplinary Bridge π Cross-Pollinator (8) π Renaissance Researcher (5) π§ Keyword Pioneer
π£
Hot Topic Early Bird
π
Conference Polyglot
(5)
π
Academic Marathon
(7)
π
Trend Setter
π
Conference Pioneer
Conferences
ICML (3)
CVPR (1)
IJCAI (1)
NIPS (1)
UAI (1)
Top co-authors
Research topics
Keywords
label noise
(2)
federated learning
(1)
differential privacy
(1)
optimal transport
(1)
weakly supervised learning
(1)
supervised learning
(1)
privacy preserving
(1)
rademacher complexity
(1)
exponential loss
(1)
logistic loss
(1)
empirical risk
(1)
sinkhorn algorithm
(1)
generative model
(1)
deep neural network
(1)
latent space
(1)
model reconstruction
(1)
robust training
(1)
record linkage
(1)
noise estimation
(1)
supervised classifier
(1)
Papers
The Impact of Record Linkage on Learning from Feature Partitioned Data
ICML 2021
Sinkhorn AutoEncoders
UAI 2019
Making Deep Neural Networks Robust to Label Noise: A Loss Correction Approach
CVPR 2017
Loss factorization, weakly supervised learning and label noise robustness
ICML 2016
Fast Learning from Distributed Datasets without Entity Matching
IJCAI 2016
Rademacher Observations, Private Data, and Boosting
ICML 2015
(Almost) No Label No Cry
NIPS 2014