Sonali Parbhoo
15 papers · 2016–2025 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
π Academic Marathon (9) π§ Keyword Pioneer π Interdisciplinary Bridge π Conference Polyglot (7) π Cross-Pollinator (8)
πΊοΈ
Taxonomy Completionist
(34)
π
Conference Polyglot
(7)
π
Academic Marathon
(9)
π
Century Club
(15)
β
The Questioner
(2)
ποΈ
Keyword Collector
(62)
Conferences
MLHC (5)
AISTATS (3)
ICML (2)
NIPS (2)
AAAI (1)
CVPR (1)
JMLR (1)
Top co-authors
Keywords
discount regularization
(2)
deep information bottleneck
(2)
concept bottleneck model
(2)
transfer learning
(2)
neural network interpretability
(1)
object recognition
(1)
reinforcement learning
(1)
interpretable machine learning
(1)
policy optimization
(1)
explainable ai
(1)
feature selection
(1)
markov decision process
(1)
mutual information
(1)
bellman equation
(1)
model-based reinforcement learning
(1)
gibbs sampling
(1)
posterior estimation
(1)
optimal policy
(1)
regularization parameter
(1)
structure learning
(1)
Papers
Decision-Point Guided Safe Policy Improvement
AISTATS 2025
Improving ARDS Diagnosis Through Context-Aware Concept Bottleneck Models
MLHC 2025
Do Regularization Methods for Shortcut Mitigation Work As Intended?
AISTATS 2025
Rethinking Discount Regularization: New Interpretations, Unintended Consequences, and Solutions for Regularization in Reinforcement Learning
JMLR 2024
Decision-Focused Model-based Reinforcement Learning for Reward Transfer
MLHC 2024
The Unintended Consequences of Discount Regularization: Improving Regularization in Certainty Equivalence Reinforcement Learning
ICML 2023
Which Explanation Makes Sense? A Critical Evaluation of Local Explanations for Assessing Cervical Cancer Risk
MLHC 2023
Learning Optimal Summaries of Clinical Time-series with Concept Bottleneck Models
MLHC 2022
Addressing Leakage in Concept Bottleneck Models
NIPS 2022
Interpretable Off-Policy Evaluation in Reinforcement Learning by Highlighting Influential Transitions
ICML 2020
Regional Tree Regularization for Interpretability in Deep Neural Networks
AAAI 2020
Inverse Learning of Symmetries
NIPS 2020
Transfer Learning from Well-Curated to Less-Resourced Populations with HIV
MLHC 2020
Greedy Structure Learning of Hierarchical Compositional Models
CVPR 2019
Bayesian Markov Blanket Estimation
AISTATS 2016