From the 1 of 17 linked papers with an AI index.
17 papers
Polynomial-time computation of -contraction fixed points for even
Constantinos Daskalakis, Gabriele Farina, Brian Hu Zhang
We give a -time algorithm that computes an -approximate fixed point of any -nonexpansive map , where $\m…
Causal Inference for Sequential Settings under Interference and Latent Confounding
Phevos Paschalidis, Constantinos Daskalakis, Devavrat Shah
The paper proposes a method to estimate causal effects in sequential observational data where units influence each other and hidden factors affect outcomes, using an Ising model wi…
Ambient Diffusion Policy: Imitation Learning from Suboptimal Data in Robotics
Adam Wei, Nicholas Pfaff, Thomas Cohn +4
We propose Ambient Diffusion Policy, a simple and principled method for imitation learning from suboptimal data in robotics. High-quality, task-specific robot data is expensive and…
Learning Correlated Reward Models: Statistical Barriers and Opportunities
Yeshwanth Cherapanamjeri, Constantinos Daskalakis, Gabriele Farina +1
Random Utility Models (RUMs) are a classical framework for modeling user preferences and play a key role in reward modeling for Reinforcement Learning from Human Feedback (RLHF). H…
High-accuracy log-concave sampling with stochastic queries
Fan Chen, Sinho Chewi, Constantinos Daskalakis +1
We show that high-accuracy guarantees for log-concave sampling -- that is, iteration and query complexities which scale as , where is the desired targ…
High-accuracy sampling for diffusion models and log-concave distributions
Fan Chen, Sinho Chewi, Constantinos Daskalakis +1
We present algorithms for diffusion model sampling which obtain -error in steps, given access to -accurate score estimates in .…