3 citations · 19 across the 50 of their papers we have counts for
25 papers · 1 filter
DiffNash: Finding Nash Equilibrium in High-Dimensional Continuous Action Spaces with Diffusion Policies
Haichuan Wang, Anagha Satish, Jiale Zheng +4
Computing equilibria in high-dimensional continuous games requires learning and representing rich, multi-modal strategy distributions, something conventional neural policies strugg…
Generative Frontier Planning for Adaptive Peer-Referral Recruitment under Covariate-Dependent Arrivals
Lingkai Kong, Hezi Jiang, Andrew Ma +3
Peer-referral recruitment systems such as respondent-driven sampling are critical for studying and intervening on hidden populations affected by infectious diseases. To accelerate…
Bilevel Optimization of Synthetic Trajectories for Multi-Turn LLM Fine-Tuning
Shresth Verma, Mauricio Tec, Cheol Woo Kim +2
While LLMs excel at single-turn generation, they struggle with long-horizon, multi-turn interactions. Offline reinforcement learning (RL) offers a scalable approach, yet its perfor…
Decisions and Deployment: The Five-Year SAHELI Project (2020-2025) on Restless Multi-Armed Bandits for Improving Maternal and Child Health
Shresth Verma, Arpan Dasgupta, Neha Madhiwalla +2
Maternal and child health is a critical concern around the world. In many global health programs disseminating preventive care and health information, limited healthcare worker res…
Reward Shaping for (Inference-Time) Alignment: A Stackelberg Game Perspective
Haichuan Wang, Tao Lin, Lingkai Kong +3
Existing alignment methods directly use the reward model learned from user preference data to optimize an LLM policy, subject to KL regularization with respect to the base policy.…
Latent Spherical Flow Policy for Reinforcement Learning with Combinatorial Actions
Lingkai Kong, Anagha Satish, Hezi Jiang +6
Reinforcement learning (RL) with combinatorial action spaces remains challenging because feasible action sets are exponentially large and governed by complex feasibility constraint…
Lightweight Robust Direct Preference Optimization
Cheol Woo Kim, Shresth Verma, Mauricio Tec +1
Direct Preference Optimization (DPO) has become a popular method for fine-tuning large language models (LLMs) due to its stability and simplicity. However, it is also known to be s…
Beyond Majority Voting: LLM Aggregation by Leveraging Higher-Order Information
Rui Ai, Yuqi Pan, David Simchi-Levi +2
With the rapid progress of multi-agent large language model (LLM) reasoning, how to effectively aggregate answers from multiple LLMs has emerged as a fundamental challenge. Standar…
Preference Robustness for DPO with Applications to Public Health
Cheol Woo Kim, Shresth Verma, Mauricio Tec +1
We study an LLM fine-tuning task for designing reward functions for sequential resource allocation problems in public health, guided by human preferences expressed in natural langu…
Generative AI Against Poaching: Latent Composite Flow Matching for Wildlife Conservation
Lingkai Kong, Haichuan Wang, Charles A. Emogor +3
Poaching poses significant threats to wildlife and biodiversity. A valuable step in reducing poaching is to forecast poacher behavior, which can inform patrol planning and other co…
Composite Flow Matching for Reinforcement Learning with Shifted-Dynamics Data
Lingkai Kong, Haichuan Wang, Tonghan Wang +2
Incorporating pre-collected offline data can substantially improve the sample efficiency of reinforcement learning (RL), but its benefits can break down when the transition dynamic…
Rule-Bottleneck Reinforcement Learning: Joint Explanation and Decision Optimization for Resource Allocation with Language Agents
Mauricio Tec, Guojun Xiong, Haichuan Wang +2
Deep Reinforcement Learning (RL) is remarkably effective in addressing sequential resource allocation problems in domains such as healthcare, public policy, and resource management…
Contrasting Cost-Agnostic and Cost-Sensitive Losses under Limited Model Capacity via -consistency
Jessica Finocchiaro, Sanket Shah, Milind Tambe
There is a prevalent debate in machine learning about whether practitioners should train models to optimize a task-agnostic objective (e.g., cross entropy) or incorporate the downs…
Navigating the Social Welfare Frontier: Portfolios for Multi-objective Reinforcement Learning
Cheol Woo Kim, Jai Moondra, Shresth Verma +4
In many real-world applications of reinforcement learning (RL), deployed policies have varied impacts on different stakeholders, creating challenges in reaching consensus on how to…
IRL for Restless Multi-Armed Bandits with Applications in Maternal and Child Health
Gauri Jain, Pradeep Varakantham, Haifeng Xu +3
Public health practitioners often have the goal of monitoring patients and maximizing patients' time spent in "favorable" or healthy states while being constrained to using limited…
Contrasting local and global modeling with machine learning and satellite data: A case study estimating tree canopy height in African savannas
Esther Rolf, Lucia Gordon, Milind Tambe +1
While advances in machine learning with satellite imagery (SatML) are facilitating environmental monitoring at a global scale, developing SatML models that are accurate and useful…
Bayesian Collaborative Bandits with Thompson Sampling for Improved Outreach in Maternal Health Program
Arpan Dasgupta, Gagan Jain, Arun Suggala +3
Mobile health (mHealth) programs face a critical challenge in optimizing the timing of automated health information calls to beneficiaries. This challenge has been formulated as a…
On Diffusion Models for Multi-Agent Partial Observability: Shared Attractors, Error Bounds, and Composite Flow
Tonghan Wang, Heng Dong, Yanchen Jiang +2
Multiagent systems grapple with partial observability (PO), and the decentralized POMDP (Dec-POMDP) model highlights the fundamental nature of this challenge. Whereas recent approa…
Balancing Act: Prioritization Strategies for LLM-Designed Restless Bandit Rewards
Shresth Verma, Niclas Boehmer, Lingkai Kong +1
LLMs are increasingly used to design reward functions based on human preferences in Reinforcement Learning (RL). We focus on LLM-designed rewards for Restless Multi-Armed Bandits,…
The Bandit Whisperer: Communication Learning for Restless Bandits
Yunfan Zhao, Tonghan Wang, Dheeraj Nagaraj +2
Applying Reinforcement Learning (RL) to Restless Multi-Arm Bandits (RMABs) offers a promising avenue for addressing allocation problems with resource constraints and temporal dynam…
Transcendence: Generative Models Can Outperform The Experts That Train Them
Edwin Zhang, Vincent Zhu, Naomi Saphra +5
Generative models are trained with the simple objective of imitating the conditional probability distribution induced by the data they are trained on. Therefore, when trained on da…
Application-Driven Innovation in Machine Learning
David Rolnick, Alan Aspuru-Guzik, Sara Beery +8
In this position paper, we argue that application-driven research has been systemically under-valued in the machine learning community. As applications of machine learning prolifer…
Evaluating the Effectiveness of Index-Based Treatment Allocation
Niclas Boehmer, Yash Nair, Sanket Shah +3
When resources are scarce, an allocation policy is needed to decide who receives a resource. This problem occurs, for instance, when allocating scarce medical resources and is ofte…
Context in Public Health for Underserved Communities: A Bayesian Approach to Online Restless Bandits
Biyonka Liang, Lily Xu, Aparna Taneja +2
Public health programs often provide interventions to encourage program adherence, and effectively allocating interventions is vital for producing the greatest overall health outco…