Sonali Parbhoo
15 papers · 2016–2025 · 7 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 ↓+4 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (40) π Conference Polyglot Β· Silver π£ Hot Topic Early Bird π Academic Marathon Β· Sprint
π
Renaissance Researcher
(5)
β
The Questioner
(2)
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(81)
Top co-authors
Research topics
Machine Learning
(13)
Artificial Intelligence
(9)
Core AI
(7)
Learning Types Β· Machine Learning
(7)
Deep Learning
(5)
Core Methods
(5)
Reinforcement Learning
(4)
Learning Types Β· Deep Learning
(4)
Methods
(4)
Optimization & Theory Β· Machine Learning
(4)
Application Areas
(3)
Optimization & Theory Β· Deep Learning
(2)
Computer Vision
(1)
Healthcare & Medicine
(1)
Natural Language Processing
(1)
Keywords
concept bottleneck model
(3)
transfer learning
(2)
discount regularization
(2)
deep information bottleneck
(2)
offline reinforcement learning
(1)
policy optimization
(1)
shortcut learning
(1)
structure learning
(1)
off-policy evaluation
(1)
feature selection
(1)
model robustness
(1)
interpretability
(1)
interpretable machine learning
(1)
explainable ai
(1)
mutual information
(1)
object recognition
(1)
markov decision process
(1)
bellman equation
(1)
gibbs sampling
(1)
neural network interpretability
(1)
Papers
Decision-Point Guided Safe Policy Improvement
AISTATS 2025
Do Regularization Methods for Shortcut Mitigation Work As Intended?
AISTATS 2025
Improving ARDS Diagnosis Through Context-Aware Concept Bottleneck Models
MLHC 2025
Decision-Focused Model-based Reinforcement Learning for Reward Transfer
MLHC 2024
Rethinking Discount Regularization: New Interpretations, Unintended Consequences, and Solutions for Regularization in Reinforcement Learning
JMLR 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
Addressing Leakage in Concept Bottleneck Models
NeurIPS 2022
Learning Optimal Summaries of Clinical Time-series with Concept Bottleneck Models
MLHC 2022
Interpretable Off-Policy Evaluation in Reinforcement Learning by Highlighting Influential Transitions
ICML 2020
Inverse Learning of Symmetries
NeurIPS 2020
Regional Tree Regularization for Interpretability in Deep Neural Networks
AAAI 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