Marco Romanelli
8 papers · 2021–2025 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(20)
🐣
Hot Topic Early Bird
⚡
Prolific Year · Productive
Top co-authors
Research topics
Keywords
out-of-distribution detection
(2)
soft prediction
(2)
misclassification detection
(2)
zero-shot learning
(2)
object recognition
(1)
uncertainty quantification
(1)
reinforcement learning
(1)
regret minimization
(1)
adversarial learning
(1)
hypothesis testing
(1)
selective classification
(1)
nearest neighbor retrieval
(1)
shannon entropy
(1)
adversarial attack
(1)
adversarial defense
(1)
regression
(1)
relu activation
(1)
deep neural network
(1)
minority group
(1)
error detection
(1)
Papers
Optimal Zero-shot Regret Minimization for Selective Classification with Out-of-Distribution Detection
UAI 2025
A Data-Driven Measure of Relative Uncertainty for Misclassification Detection
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
On the (In)feasibility of ML Backdoor Detection as an Hypothesis Testing Problem
AISTATS 2024
Optimal Zero-Shot Detector for Multi-Armed Attacks
AISTATS 2024
Retrieval-Guided Reinforcement Learning for Boolean Circuit Minimization
ICLR 2024
DOCTOR: A Simple Method for Detecting Misclassification Errors
NeurIPS 2021