activity
20242026
collaborators
Showing cs.LGShow all

13 papers · 1 filter

cs.LG2026

Perturbative methods for non-parametric instrumental variable

Wei Bu, Arthur Gretton

We introduce a perturbative approach for nonparametric instrumental variable (NPIV) estimation. By drawing inspiration from perturbation theory in physics, we extend standard kerne…

cs.LG2026

Spectral Souping: A Unified Framework for Online Preference Alignment

Yinlam Chow, Guy Tennenholtz, Ted Yun +4

Reinforcement Learning from Human Feedback (RLHF) effectively aligns Large Language Models (LLMs) with aggregate human preferences but often fails to address the diverse and confli…

cs.LG2026

Density Ratio-Free Doubly Robust Proxy Causal Learning

Bariscan Bozkurt, Houssam Zenati, Dimitri Meunier +2

We study the problem of causal function estimation in the Proxy Causal Learning (PCL) framework, where confounders are not observed but proxies for the confounders are available. T…

cs.LG2026

Density Ratio-based Proxy Causal Learning Without Density Ratios

Bariscan Bozkurt, Ben Deaner, Dimitri Meunier +2

We address the setting of Proxy Causal Learning (PCL), which has the goal of estimating causal effects from observed data in the presence of hidden confounding. Proxy methods accom…

cs.LG2025

Regularized least squares learning with heavy-tailed noise is minimax optimal

Mattes Mollenhauer, Nicole Mücke, Dimitri Meunier +1

This paper examines the performance of ridge regression in reproducing kernel Hilbert spaces in the presence of noise that exhibits a finite number of higher moments. We establish…

cs.LG2025

Learning-Order Autoregressive Models with Application to Molecular Graph Generation

Zhe Wang, Jiaxin Shi, Nicolas Heess +2

Autoregressive models (ARMs) have become the workhorse for sequence generation tasks, since many problems can be modeled as next-token prediction. While there appears to be a natur…