Marco Romanelli
8 papers · 2021–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (5) π Cross-Pollinator (8) πΊοΈ Taxonomy Completionist (10)
β‘
Prolific Year
(6)
Conferences
AISTATS (2)
ICLR (2)
ICML (2)
NIPS (1)
UAI (1)
Top co-authors
Keywords
information theory
(1)
zero-shot learning
(1)
adversarial learning
(1)
object recognition
(1)
hypothesis testing
(1)
adversarial attack
(1)
deep neural network
(1)
adversarial defense
(1)
out-of-distribution detection
(1)
zero-shot detection
(1)
backdoor detection
(1)
pac learnability
(1)
adversary-aware detection
(1)
multi-armed attack
(1)
detector aggregation
(1)
false rejection rate
(1)
misclassification detection
(1)
soft prediction
(1)
Papers
Optimal Zero-shot Regret Minimization for Selective Classification with Out-of-Distribution Detection
UAI 2025
Optimal Zero-Shot Detector for Multi-Armed Attacks
AISTATS 2024
On the (In)feasibility of ML Backdoor Detection as an Hypothesis Testing Problem
AISTATS 2024
Retrieval-Guided Reinforcement Learning for Boolean Circuit Minimization
ICLR 2024
Beyond the Norms: Detecting Prediction Errors in Regression Models
ICML 2024
Disparate Impact on Group Accuracy of Linearization for Private Inference
ICML 2024
A Data-Driven Measure of Relative Uncertainty for Misclassification Detection
ICLR 2024
DOCTOR: A Simple Method for Detecting Misclassification Errors
NIPS 2021