Mukund Sudarshan
5 papers · 2020–2023 · 3 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 ↓
π
Conference Polyglot Β· Bronze
π
Interdisciplinary Bridge Β· Bronze
πΊοΈ
Taxonomy Completionist
(10)
π£
Hot Topic Early Bird
β
The Questioner
Venues
Top co-authors
Research topics
Keywords
model explanation
(2)
false discovery rate
(2)
feature importance
(2)
interpretable machine learning
(1)
hypothesis testing
(1)
statistical testing
(1)
mutual information
(1)
statistical hypothesis testing
(1)
conditional independence
(1)
randomization test
(1)
deep neural network
(1)
conditional independence test
(1)
black-box model
(1)
shapley value
(1)
information residual
(1)
type-1 error control
(1)
weighted least square
(1)
covariate selection
(1)
amortized explanation
(1)
fidelity evaluation
(1)
Papers
DIET: Conditional independence testing with marginal dependence measures of residual information
AISTATS 2023
FastSHAP: Real-Time Shapley Value Estimation
ICLR 2022
CONTRA: Contrarian statistics for controlled variable selection
AISTATS 2021
Have We Learned to Explain?: How Interpretability Methods Can Learn to Encode Predictions in their Interpretations.
AISTATS 2021
Deep Direct Likelihood Knockoffs
NeurIPS 2020