activity
20162026
most citedEstimating Certain Integral Probability Metric (IPM) is as Hard as Estimating under the IPM

11 citations · 22 across the 17 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

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…

cs.LG2024

Learning When the Concept Shifts: Confounding, Invariance, and Dimension Reduction

Kulunu Dharmakeerthi, YoonHaeng Hur, Tengyuan Liang

Practitioners often face the challenge of deploying prediction models in new environments with shifted distributions of covariates and responses. With observational data, such shif…

cs.LG2022★ 1 cited

Online Learning to Transport via the Minimal Selection Principle

Wenxuan Guo, YoonHaeng Hur, Tengyuan Liang +1

Motivated by robust dynamic resource allocation in operations research, we study the \textit{Online Learning to Transport} (OLT) problem where the decision variable is a probabilit…

cs.LG2018

Local Optimality and Generalization Guarantees for the Langevin Algorithm via Empirical Metastability

Belinda Tzen, Tengyuan Liang, Maxim Raginsky

We study the detailed path-wise behavior of the discrete-time Langevin algorithm for non-convex Empirical Risk Minimization (ERM) through the lens of metastability, adopting some t…

cs.LG2017

Fisher-Rao Metric, Geometry, and Complexity of Neural Networks

Tengyuan Liang, Tomaso Poggio, Alexander Rakhlin +1

We study the relationship between geometry and capacity measures for deep neural networks from an invariance viewpoint. We introduce a new notion of capacity --- the Fisher-Rao nor…

cs.LG2017

Adaptive Feature Selection: Computationally Efficient Online Sparse Linear Regression under RIP

Satyen Kale, Zohar Karnin, Tengyuan Liang +1

Online sparse linear regression is an online problem where an algorithm repeatedly chooses a subset of coordinates to observe in an adversarially chosen feature vector, makes a rea…