11 citations · 23 across the 14 of their papers we have counts for
15 papers
Does Flatness imply Generalization for Logistic Loss in Univariate Two-Layer ReLU Network?
Dan Qiao, Yu-Xiang Wang
We consider the problem of generalization of arbitrarily overparameterized two-layer ReLU Neural Networks with univariate input. Recent work showed that under square loss, flat sol…
Stable Minima of ReLU Neural Networks Suffer from the Curse of Dimensionality: The Neural Shattering Phenomenon
Tongtong Liang, Dan Qiao, Yu-Xiang Wang +1
We study the implicit bias of flatness / low (loss) curvature and its effects on generalization in two-layer overparameterized ReLU networks with multivariate inputs -- a problem w…
No-Regret Linear Bandits under Gap-Adjusted Misspecification
Chong Liu, Dan Qiao, Ming Yin +2
This work studies linear bandits under a new notion of gap-adjusted misspecification and is an extension of Liu et al. (2023). When the underlying reward function is not linear, ex…
Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes
Dan Qiao, Kaiqi Zhang, Esha Singh +2
We study the generalization of two-layer ReLU neural networks in a univariate nonparametric regression problem with noisy labels. This is a problem where kernels (\emph{e.g.} NTK)…
Differentially Private Reinforcement Learning with Self-Play
Dan Qiao, Yu-Xiang Wang
We study the problem of multi-agent reinforcement learning (multi-agent RL) with differential privacy (DP) constraints. This is well-motivated by various real-world applications in…
Near-Optimal Reinforcement Learning with Self-Play under Adaptivity Constraints
Dan Qiao, Yu-Xiang Wang
We study the problem of multi-agent reinforcement learning (MARL) with adaptivity constraints -- a new problem motivated by real-world applications where deployments of new policie…
Semantically Aligned Task Decomposition in Multi-Agent Reinforcement Learning
Wenhao Li, Dan Qiao, Baoxiang Wang +3
The difficulty of appropriately assigning credit is particularly heightened in cooperative MARL with sparse reward, due to the concurrent time and structural scales involved. Autom…
Logarithmic Switching Cost in Reinforcement Learning beyond Linear MDPs
Dan Qiao, Ming Yin, Yu-Xiang Wang
In many real-life reinforcement learning (RL) problems, deploying new policies is costly. In those scenarios, algorithms must solve exploration (which requires adaptivity) while sw…
Near-Optimal Differentially Private Reinforcement Learning
Dan Qiao, Yu-Xiang Wang
Motivated by personalized healthcare and other applications involving sensitive data, we study online exploration in reinforcement learning with differential privacy (DP) constrain…
Near-Optimal Deployment Efficiency in Reward-Free Reinforcement Learning with Linear Function Approximation
Dan Qiao, Yu-Xiang Wang
We study the problem of deployment efficient reinforcement learning (RL) with linear function approximation under the \emph{reward-free} exploration setting. This is a well-motivat…
Doubly Fair Dynamic Pricing
Jianyu Xu, Dan Qiao, Yu-Xiang Wang
We study the problem of online dynamic pricing with two types of fairness constraints: a "procedural fairness" which requires the proposed prices to be equal in expectation among d…
Offline Reinforcement Learning with Differential Privacy
Dan Qiao, Yu-Xiang Wang
The offline reinforcement learning (RL) problem is often motivated by the need to learn data-driven decision policies in financial, legal and healthcare applications. However, the…
Differentially Private Linear Sketches: Efficient Implementations and Applications
Fuheng Zhao, Dan Qiao, Rachel Redberg +3
Linear sketches have been widely adopted to process fast data streams, and they can be used to accurately answer frequency estimation, approximate top K items, and summarize data d…
Sample-Efficient Reinforcement Learning with loglog(T) Switching Cost
Dan Qiao, Ming Yin, Ming Min +1
We study the problem of reinforcement learning (RL) with low (policy) switching cost - a problem well-motivated by real-life RL applications in which deployments of new policies ar…
Applying Adaptive Gradient Descent to solve matrix factorization
Dan Qiao
Based on the method of FGD, we apply the method of adaptive gradient descent which uses different step length at different epoch. Adaptive gradient descent performs much better tha…