Natasa Tagasovska
9 papers · 2019–2025 · 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 ↓+2 more ↓ Show less ↑
🗺️ Taxonomy Completionist (19) 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🌍 Conference Polyglot · Silver 🐣 Hot Topic Early Bird
🏆
Keyword Champion
(2)
🗃️
Keyword Collector
(50)
Top co-authors
Research topics
Deep Learning
(6)
Machine Learning
(6)
Artificial Intelligence
(5)
Architectures
(4)
Optimization & Theory
(4)
Core AI
(3)
Core Methods
(3)
Models
(3)
Application Areas
(2)
Bayesian & Probabilistic · Artificial Intelligence
(2)
Learning Types
(2)
Computer Vision
(1)
Mathematics & Optimization
(1)
Analysis
(1)
Bayesian & Probabilistic · Machine Learning
(1)
Keywords
uncertainty estimation
(2)
generative model
(2)
vine copula
(2)
quantile regression
(2)
gradient-based optimization
(1)
uncertainty quantification
(1)
transfer learning
(1)
deep learning
(1)
causal discovery
(1)
self-supervised learning
(1)
distribution shift
(1)
protein design
(1)
minimum description length
(1)
copula
(1)
option pricing
(1)
bayesian optimization
(1)
epistemic uncertainty
(1)
latent representation
(1)
disentangled representation
(1)
bayesian inference
(1)
Papers
Uncertainty modeling for fine-tuned implicit functions
ICLR 2025
BOtied: Multi-objective Bayesian optimization with tied multivariate ranks
ICML 2024
Implicitly Guided Design with PropEn: Match your Data to Follow the Gradient
NeurIPS 2024
Learning Causal Representations of Single Cells via Sparse Mechanism Shift Modeling
CLeaR 2023
Retrospective Uncertainties for Deep Models using Vine Copulas
AISTATS 2023
Deep Smoothing of the Implied Volatility Surface
NeurIPS 2020
Distinguishing Cause from Effect Using Quantiles: Bivariate Quantile Causal Discovery
ICML 2020
Copulas as High-Dimensional Generative Models: Vine Copula Autoencoders
NeurIPS 2019
Single-Model Uncertainties for Deep Learning
NeurIPS 2019