6 papers
LLMs can construct powerful representations and streamline sample-efficient supervised learning
Ilker Demirel, Lawrence Shi, Zeshan Hussain +1
As real-world datasets become more complex and heterogeneous, supervised learning is often bottlenecked by input representation design. Modeling multimodal data, such as time-serie…
Using LLMs for Late Multimodal Sensor Fusion for Activity Recognition
Ilker Demirel, Karan Thakkar, Benjamin Elizalde +7
Sensor data streams provide valuable information around activities and context for downstream applications, though integrating complementary information can be challenging. We show…
Prediction-Powered Causal Inferences
Riccardo Cadei, Ilker Demirel, Piersilvio De Bartolomeis +4
In many scientific experiments, the data annotating cost constraints the pace for testing novel hypotheses. Yet, modern machine learning pipelines offer a promising solution, provi…
Uncovering Bias Mechanisms in Observational Studies
Ilker Demirel, Zeshan Hussain, Piersilvio De Bartolomeis +1
Observational studies are a key resource for causal inference but are often affected by systematic biases. Prior work has focused mainly on detecting these biases, via sensitivity…
Federated Multi-Armed Bandits Under Byzantine Attacks
Artun Saday, Ä°lker Demirel, YiÄit Yıldırım +1
Multi-armed bandits (MAB) is a sequential decision-making model in which the learner controls the trade-off between exploration and exploitation to maximize its cumulative reward.…
Prediction-powered Generalization of Causal Inferences
Ilker Demirel, Ahmed Alaa, Anthony Philippakis +1
Causal inferences from a randomized controlled trial (RCT) may not pertain to a target population where some effect modifiers have a different distribution. Prior work studies gene…