Ambroise Odonnat
5 papers · 2024–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
π
Conference Polyglot
(4)
π
Cross-Pollinator
(7)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(11)
Conferences
NIPS (2)
AISTATS (1)
ICLR (1)
ICML (1)
Top co-authors
Keywords
hyperparameter optimization
(1)
uncertainty quantification
(1)
time series forecasting
(1)
matrix norms
(1)
distribution shift
(1)
multi-task regression
(1)
multivariate time series
(1)
random matrix theory
(1)
out-of-distribution detection
(1)
soft label
(1)
ensemble diversity
(1)
sample selection bia
(1)
confidence measure
(1)
accuracy estimation
(1)
logit normalization
(1)
Papers
Zero-shot Model-based Reinforcement Learning using Large Language Models
ICLR 2025
MaNo: Exploiting Matrix Norm for Unsupervised Accuracy Estimation Under Distribution Shifts
NIPS 2024
Analysing Multi-Task Regression via Random Matrix Theory with Application to Time Series Forecasting
NIPS 2024
Leveraging Ensemble Diversity for Robust Self-Training in the Presence of Sample Selection Bias
AISTATS 2024
SAMformer: Unlocking the Potential of Transformers in Time Series Forecasting with Sharpness-Aware Minimization and Channel-Wise Attention
ICML 2024