10 papers
Learned Neighbor Trust for Collaborative Deployment in Model-Agnostic Decentralized Learning
Michael Lanier, Luise Ge, Sastry Kompella +1
Many decentralized distillation methods are designed around training-time coordination, yet deploy each node in isolation even when more capable neighbors remain available at infer…
COSMOS: Model-Agnostic Personalized Federated Learning with Clustered Server Models and Pseudo-Label-Only Communication
Ben Rachmut, Luise Ge, William Yeoh +2
Federated learning (FL) in heterogeneous environments remains challenging because client models often differ in both architecture and data distribution. While recent approaches att…
Linear Social Choice with Few Queries: A Moment-Based Approach
Luise Ge, Daniel Halpern, Gregory Kehne +1
Most social choice rules assume access to full rankings, while current alignment practice -- despite aiming for diversity -- typically treats voters as anonymous and comparisons as…
Lifted Relational Probabilistic Inference via Implicit Learning
Luise Ge, Brendan Juba, Kris Nilsson +1
Reconciling the tension between inductive learning and deductive reasoning in first-order relational domains is a longstanding challenge in AI. We study the problem of answering qu…
Mind the (DH) Gap! A Contrast in Risky Choices Between Reasoning and Conversational LLMs
Luise Ge, Yongyan Zhang, Yevgeniy Vorobeychik
The use of large language models either as decision support systems, or in agentic workflows, is rapidly transforming the digital ecosystem. However, the understanding of LLM decis…
Optimized Distortion in Linear Social Choice
Luise Ge, Gregory Kehne, Yevgeniy Vorobeychik
Social choice theory offers a wealth of approaches for selecting a candidate on behalf of voters based on their reported preference rankings over options. When voters have underlyi…
Polynomial-Time Relational Probabilistic Inference in Open Universes
Luise Ge, Brendan Juba, Kris Nilsson
Reasoning under uncertainty is a fundamental challenge in Artificial Intelligence. As with most of these challenges, there is a harsh dilemma between the expressive power of the la…
Learning Policy Committees for Effective Personalization in MDPs with Diverse Tasks
Luise Ge, Michael Lanier, Anindya Sarkar +3
Many dynamic decision problems, such as robotic control, involve a series of tasks, many of which are unknown at training time. Typical approaches for these problems, such as multi…
Learning Linear Utility Functions From Pairwise Comparison Queries
Luise Ge, Brendan Juba, Yevgeniy Vorobeychik
We study learnability of linear utility functions from pairwise comparison queries. In particular, we consider two learning objectives. The first objective is to predict out-of-sam…
Axioms for AI Alignment from Human Feedback
Luise Ge, Daniel Halpern, Evi Micha +4
In the context of reinforcement learning from human feedback (RLHF), the reward function is generally derived from maximum likelihood estimation of a random utility model based on…