12 citations · 37 across the 12 of their papers we have counts for
12 papers
Efficient Multinomial Logistic Bandit via Frequent Directions
Linzhe He, Yu-Jie Zhang, Sifan Yang +1
This paper studies efficient online algorithms for multinomial logistic bandits (MLogB), where the feedback distribution over outcomes follows a multinomial logistic model of…
Near-Optimal Regret in Adversarial Kernel Bandits
Yu-Jie Zhang, Hao Qiu, Jonathan Scarlett +1
We study the adversarial kernel bandit problem, in which the loss at each round is induced by an arbitrary bounded element of a reproducing kernel Hilbert space (RKHS). We propose…
Dynamic Regret via Discounted-to-Dynamic Reduction with Applications to Curved Losses and Adam Optimizer
Yan-Feng Xie, Yu-Jie Zhang, Peng Zhao +1
We study dynamic regret minimization in non-stationary online learning, with a primary focus on follow-the-regularized-leader (FTRL) methods. FTRL is important for curved losses an…
Heavy-Tailed Linear Bandits: Huber Regression with One-Pass Update
Jing Wang, Yu-Jie Zhang, Peng Zhao +1
We study the stochastic linear bandits with heavy-tailed noise. Two principled strategies for handling heavy-tailed noise, truncation and median-of-means, have been introduced to h…
Provably Efficient Reinforcement Learning with Multinomial Logit Function Approximation
Long-Fei Li, Yu-Jie Zhang, Peng Zhao +1
We study a new class of MDPs that employs multinomial logit (MNL) function approximation to ensure valid probability distributions over the state space. Despite its significant ben…
Optimistic Online Mirror Descent for Bridging Stochastic and Adversarial Online Convex Optimization
Sijia Chen, Yu-Jie Zhang, Wei-Wei Tu +2
Stochastically Extended Adversarial (SEA) model is introduced by Sachs et al. [2022] as an interpolation between stochastic and adversarial online convex optimization. Under the sm…
Adapting to Continuous Covariate Shift via Online Density Ratio Estimation
Yu-Jie Zhang, Zhen-Yu Zhang, Peng Zhao +1
Dealing with distribution shifts is one of the central challenges for modern machine learning. One fundamental situation is the covariate shift, where the input distributions of da…
Adapting to Online Label Shift with Provable Guarantees
Yong Bai, Yu-Jie Zhang, Peng Zhao +2
The standard supervised learning paradigm works effectively when training data shares the same distribution as the upcoming testing samples. However, this stationary assumption is…
Adaptivity and Non-stationarity: Problem-dependent Dynamic Regret for Online Convex Optimization
Peng Zhao, Yu-Jie Zhang, Lijun Zhang +1
We investigate online convex optimization in non-stationary environments and choose dynamic regret as the performance measure, defined as the difference between cumulative loss inc…
Dynamic Regret of Convex and Smooth Functions
Peng Zhao, Yu-Jie Zhang, Lijun Zhang +1
We investigate online convex optimization in non-stationary environments and choose the dynamic regret as the performance measure, defined as the difference between cumulative loss…
Exploratory Machine Learning with Unknown Unknowns
Peng Zhao, Jia-Wei Shan, Yu-Jie Zhang +1
In conventional supervised learning, a training dataset is given with ground-truth labels from a known label set, and the learned model will classify unseen instances to known labe…
An Unbiased Risk Estimator for Learning with Augmented Classes
Yu-Jie Zhang, Peng Zhao, Zhi-Hua Zhou
This paper studies the problem of learning with augmented classes (LAC), where augmented classes unobserved in the training data might emerge in the testing phase. Previous studies…