Mathias Lécuyer
6 papers · 2021–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
🗺️ Taxonomy Completionist (17) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (4)
🐝
Cross-Pollinator
(6)
🌈
Renaissance Researcher
(5)
📈
Trend Setter
Conferences
ICML (2)
NIPS (2)
AAAI (1)
OSDI (1)
Top co-authors
Research topics
Keywords
differential privacy
(3)
causal inference
(1)
adversarial robustness
(1)
model security
(1)
data valuation
(1)
deep learning
(1)
gradient descent
(1)
renyi divergence
(1)
lasso regression
(1)
bias correction
(1)
adam optimizer
(1)
randomized smoothing
(1)
model training
(1)
influence function
(1)
privacy auditing
(1)
privacy budget
(1)
adversarial example
(1)
privacy leakage
(1)
membership inference
(1)
machine learning model
(1)
Papers
Connecting Thompson Sampling and UCB: Towards More Efficient Trade-offs Between Privacy and Regret
ICML 2025
PANORAMIA: Privacy Auditing of Machine Learning Models without Retraining
NIPS 2024
Adaptive Randomized Smoothing: Certified Adversarial Robustness for Multi-Step Defences
NIPS 2024
DP-AdamBC: Your DP-Adam Is Actually DP-SGD (Unless You Apply Bias Correction)
AAAI 2024
Measuring the Effect of Training Data on Deep Learning Predictions via Randomized Experiments
ICML 2022
Privacy Budget Scheduling
OSDI 2021