Sample Complexity Bounds for Linear Constrained MDPs with a Generative Model

We consider infinite-horizon $\gamma$-discounted (linear) constrained Markov decision processes (CMDPs) where the objective is to find a policy that maximizes the expected cumulative reward subject to expected cumulative constraints. Given access to a generative model, we propose to solve CMDPs with a primal-dual framework that can leverage any black-box unconstrained MDP solver. For linear CMDPs with feature dimension $d$, we instantiate the framework by using mirror descent value iteration (\texttt{MDVI})~\citep{kitamura2023regularization} an example MDP solver. We provide sample complexity bounds for the resulting CMDP algorithm in two cases: (i) relaxed feasibility, where small constraint violations are allowed, and (ii) strict feasibility, where the output policy is required to exactly satisfy the constraint. For (i), we prove that the algorithm can return an $\epsilon$-optimal policy with high probability by using $\tilde{O}\left(\frac{d^2}{(1-\gamma)^4\epsilon^2}\right)$ samples. We note that these results exhibit a near-optimal dependence on both $d$ and $\epsilon$. For (ii), we show that the algorithm requires $\tilde{O}\left(\frac{d^2}{(1-\gamma)^6\epsilon^2\zeta^2}\right)$ samples, where $\zeta$ is the problem-dependent Slater constant that characterizes the size of the feasible region. Finally, we instantiate our framework for tabular CMDPs and show that it can be used to recover near-optimal sample complexities in this setting.

Improved Rates for Differentially Private Stochastic Convex Optimization with Heavy-Tailed Data

We study stochastic convex optimization with heavy-tailed data under the constraint of differential privacy. Most prior work on this problem is restricted to the case where the loss function is Lipschitz. Instead, as introduced by Wang, Xiao, Devadas, and Xu, we study general convex loss functions with the assumption that the distribution of gradients has bounded $k$-th moments. We provide improved upper bounds on the excess population risk under approximate differential privacy of $\tilde{O}\left(\sqrt{\frac{d}{n}}+\left(\frac{d}{\epsilon n}\right)^{\frac{k-1}{k}}\right)$ and $\tilde{O}\left(\frac{d}{n}+\left(\frac{d}{\epsilon n}\right)^{\frac{2k-2}{k}}\right)$ for convex and strongly convex loss functions, respectively. We also prove nearly-matching lower bounds under the constraint of pure differential privacy, giving strong evidence that our bounds are tight.