activity
20242026
collaborators

7 papers

cs.LG2026

A Markov Chain Approach to Preference Alignment

Takuya Koriyama, Tengyuan Liang

We propose Markov Chain from Human Feedback (MCHF), an elementary approach for aligning generative models from pairwise human preferences. Unlike Reinforcement Learning from Human…

stat.ML2026

Denoising Diffusions with Optimal Transport: Localization, Curvature, and Multi-Scale Complexity

Tengyuan Liang, Kulunu Dharmakeerthi, Takuya Koriyama

Adding noise is easy; what about denoising? Diffusion is easy; what about reverting a diffusion? Diffusion-based generative models aim to denoise a Langevin diffusion chain, moving…

math.ST2026

Asymptotics of resampling without replacement in robust and logistic regression

Pierre C. Bellec, Takuya Koriyama

This paper studies the asymptotics of resampling without replacement in the proportional regime where dimension and sample size are of the same order. For a given dataset $…

math.ST2025

Precise Asymptotics of Bagging Regularized M-estimators

Takuya Koriyama, Pratik Patil, Jin-Hong Du +2

We characterize the squared prediction risk of ensemble estimators obtained through subagging (subsample bootstrap aggregating) regularized M-estimators and construct a consistent…

math.ST2025

Phase transitions for the existence of unregularized M-estimators in single index models

Takuya Koriyama, Pierre C. Bellec

This paper studies phase transitions for the existence of unregularized M-estimators under proportional asymptotics where the sample size and feature dimension grow proport…

math.ST2025

Error estimation and adaptive tuning for unregularized robust M-estimator

Pierre C. Bellec, Takuya Koriyama

We consider unregularized robust M-estimators for linear models under Gaussian design and heavy-tailed noise, in the proportional asymptotics regime where the sample size n and the…