11 papers
Mean Velocity Matching: Rethinking Generative Dynamics in Diffusion Models
Yunhong Zhang, Changjie Cao, Zhihua Zhang +4
This work studies prediction parameterization for stochastic generative dynamics in diffusion models. Existing velocity-based generative models provide the simplicity of learning a…
Does 1/2-Tsallis-INF Also Work Well for Best-Arm Identification?
Jingxin Zhan, Yuze Han, Zhihua Zhang
Regret minimization (RM) and best-arm identification (BAI) are two fundamental objectives in multi-armed bandits. Among regret-minimizing algorithms, -Tsallis-INF is a canonic…
Active-Trace Complexity Bounds for Moreau--Yosida Unadjusted Langevin Sampling
Yuchen Xin, Zhihua Zhang
We study the Moreau--Yosida unadjusted Langevin algorithm (MYULA) for the nonsmooth composite target \[ π(dx)\propto \exp\{-f(x)-g(x)\}\,dx, \qquad x\in\mathbb R^d, \] where \(f\)…
Accelerated Distributional Temporal Difference Learning with Linear Function Approximation
Kaicheng Jin, Yang Peng, Jiansheng Yang +1
In this paper, we study the finite-sample statistical rates of distributional temporal difference (TD) learning with linear function approximation. The purpose of distributional TD…
Last-Iterate Analyses of FTRL with the 1/2-Tsallis Entropy in Stochastic Bandits
Jingxin Zhan, Yuze Han, Zhihua Zhang
The convergence analysis of online learning algorithms is central to machine learning theory, where the last-iterate convergence is particularly important, as it captures the learn…
Matrix Moment and Concentration Inequalities for Martingales and Ergodic Markov Chains with Applications in Statistical Learning
Yang Peng, Yuchen Xin, Zhihua Zhang
In this paper, we study moment and concentration inequalities for the spectral norm of sums of dependent random matrices. We establish novel Rosenthal-Burkholder inequalities for t…
Follow-the-Perturbed-Leader Approaches Best-of-Both-Worlds for the m-Set Semi-Bandit Problems
Jingxin Zhan, Yuchen Xin, Chenjie Sun +1
We consider a common case of the combinatorial semi-bandit problem, the -set semi-bandit, where the learner exactly selects arms from the total arms. In the adversarial…
A Finite Sample Analysis of Distributional TD Learning with Linear Function Approximation
Yang Peng, Kaicheng Jin, Liangyu Zhang +1
In this paper, we study the finite-sample statistical rates of distributional temporal difference (TD) learning with linear function approximation. The aim of distributional TD lea…
A Regularized Online Newton Method for Stochastic Convex Bandits with Linear Vanishing Noise
Jingxin Zhan, Yuchen Xin, Kaicheng Jin +1
We study a stochastic convex bandit problem where the subgaussian noise parameter is assumed to decrease linearly as the learner selects actions closer and closer to the minimizer…
Principal-Agent Problem with Third Party: Information Design from Social Planner's Perspective
Shiyun Lin, Zhihua Zhang
We study the principal-agent problem with a third party that we call social planner, whose responsibility is to reconcile the conflicts of interest between the two players and indu…
Constructing Synthetic Treatment Groups without the Mean Exchangeability Assumption
Yuhang Zhang, Yue Liu, Zhihua Zhang
The purpose of this work is to transport the information from multiple randomized controlled trials to the target population where we only have the control group data. Previous wor…