Deepak Ravikumar
5 papers · 2024–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
π§
Keyword Pioneer
π
Conference Polyglot
(3)
π
Cross-Pollinator
(13)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(14)
Conferences
ICML (3)
AAAI (1)
NIPS (1)
Top co-authors
Keywords
privacy attack
(1)
model robustness
(1)
machine unlearning
(1)
label noise
(1)
singular value decomposition
(1)
noise robustness
(1)
deep neural network
(1)
membership inference
(1)
input loss curvature
(1)
train-test distinguishability
(1)
hessian analysis
(1)
weight projection
(1)
generalization improvement
(1)
privacy-preserving technique
(1)
noise robust training
(1)
Papers
SAP: Corrective Machine Unlearning with Scaled Activation Projection for Label Noise Robustness
AAAI 2025
Towards Memorization Estimation: Fast, Formal and Free
ICML 2025
Curvature Clues: Decoding Deep Learning Privacy with Input Loss Curvature
NIPS 2024
Memorization Through the Lens of Curvature of Loss Function Around Samples
ICML 2024
Unveiling Privacy, Memorization, and Input Curvature Links
ICML 2024