More Like this

1. Near-Optimal Differentially Private Reinforcement Learning

   Qiao, Dan; Wang, Yu-Xiang (April 2023, Proceedings of Machine Learning Research)

   Motivated by personalized healthcare and other applications involving sensitive data, we study online exploration in reinforcement learning with differential privacy (DP) constraints. Existing work on this problem established that no-regret learning is possible under joint differential privacy (JDP) and local differential privacy (LDP) but did not provide an algorithm with optimal regret. We close this gap for the JDP case by designing an ϵ-JDP algorithm with a regret of O˜(sqrt(SAH^2T) +S^2AH^3/ϵ) which matches the information-theoretic lower bound of non-private learning for all choices of ϵ>S^1.5A^0.5H^2/sqrt(T). In the above, S, A denote the number of states and actions, H denotes the planning horizon, and T is the number of steps. To the best of our knowledge, this is the first private RL algorithm that achieves \emph{privacy for free} asymptotically as T→∞. Our techniques -- which could be of independent interest -- include privately releasing Bernstein-type exploration bonuses and an improved method for releasing visitation statistics. The same techniques also imply a slightly improved regret bound for the LDP case. 

   more » « less
2. Dynamic Global Sensitivity for Differentially Private Contextual Bandits

   https://doi.org/10.1145/3523227.3546781  

   Wang, Huazheng; Zhao, David; Wang, Hongning (September 2022, Proceedings of the 16th ACM Conference on Recommender Systems)

   We propose a differentially private linear contextual bandit algorithm, via a tree-based mechanism to add Laplace or Gaussian noise to model parameters. Our key insight is that as the model converges during online update, the global sensitivity of its parameters shrinks over time (thus named dynamic global sensitivity). Compared with existing solutions, our dynamic global sensitivity analysis allows us to inject less noise to obtain $$(\epsilon, \delta)$$-differential privacy with added regret caused by noise injection in $$\tilde O(\log{T}\sqrt{T}/\epsilon)$$. We provide a rigorous theoretical analysis over the amount of noise added via dynamic global sensitivity and the corresponding upper regret bound of our proposed algorithm. Experimental results on both synthetic and real-world datasets confirmed the algorithm's advantage against existing solutions. 

   more » « less
3. Sample-Efficient Reinforcement Learning with loglog({T}) Switching Cost

   Qiao, Dan; Yin, Ming; Min, Ming; Wang, Yu-Xiang (June 2022, Proceedings of Machine Learning Research)

   Chaudhuri, Kamalika and (Ed.)

   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 are costly and the number of policy updates must be low. In this paper, we propose a new algorithm based on stage-wise exploration and adaptive policy elimination that achieves a regret of $$\widetilde{O}(\sqrt{H^4S^2AT})$$ while requiring a switching cost of $$O(HSA \log\log T)$$. This is an exponential improvement over the best-known switching cost $$O(H^2SA\log T)$$ among existing methods with $$\widetilde{O}(\mathrm{poly}(H,S,A)\sqrt{T})$$ regret. In the above, $S,A$ denotes the number of states and actions in an $$H$$-horizon episodic Markov Decision Process model with unknown transitions, and $$T$$ is the number of steps. As a byproduct of our new techniques, we also derive a reward-free exploration algorithm with a switching cost of $O(HSA)$. Furthermore, we prove a pair of information-theoretical lower bounds which say that (1) Any no-regret algorithm must have a switching cost of $$\Omega(HSA)$$; (2) Any $$\widetilde{O}(\sqrt{T})$$ regret algorithm must incur a switching cost of $$\Omega(HSA\log\log T)$$. Both our algorithms are thus optimal in their switching costs. 

   more » « less
4. Parameter-Free Locally Differentially Private Stochastic Subgradient Descent

   Jun, Kwang-Sung; Orabona, Francesco (January 2019, Workshop on Privacy in Machine Learning at NeurIPS'19)

   null (Ed.)

   We consider the problem of minimizing a convex risk with stochastic subgradients guaranteeing $$\epsilon$$-locally differentially private ($$\epsilon$$-LDP). While it has been shown that stochastic optimization is possible with $$\epsilon$$-LDP via the standard SGD, its convergence rate largely depends on the learning rate, which must be tuned via repeated runs. Further, tuning is detrimental to privacy loss since it significantly increases the number of gradient requests. In this work, we propose BANCO (Betting Algorithm for Noisy COins), the first $$\epsilon$$-LDP SGD algorithm that essentially matches the convergence rate of the tuned SGD without any learning rate parameter, reducing privacy loss and saving privacy budget. 

   more » « less
5. Sharper Model-free Reinforcement Learning for Average-reward Markov Decision Processes

   Zhang, Zihan; Xie, Qiaomin (July 2023, Conference on Learning Theory)

   We study model-free reinforcement learning (RL) algorithms for infinite-horizon average-reward Markov decision process (MDP), which is more appropriate for applications that involve continuing operations not divided into episodes. In contrast to episodic/discounted MDPs, theoretical understanding of model-free RL algorithms is relatively inadequate for the average-reward setting. In this paper, we consider both the online setting and the setting with access to a simulator. We develop computationally efficient model-free algorithms that achieve sharper guarantees on regret/sample complexity compared with existing results. In the online setting, we design an algorithm, UCB-AVG, based on an optimistic variant of variance-reduced Q-learning. We show that UCB-AVG achieves a regret bound $$\widetilde{O}(S^5A^2sp(h^*)\sqrt{T})$$ after $$T$$ steps, where $$S\times A$$ is the size of state-action space, and $sp(h^*)$ the span of the optimal bias function. Our result provides the first computationally efficient model-free algorithm that achieves the optimal dependence in $$T$$ (up to log factors) for weakly communicating MDPs, which is necessary for low regret. In contrast, prior results either are suboptimal in $$T$$ or require strong assumptions of ergodicity or uniformly mixing of MDPs. In the simulator setting, we adapt the idea of UCB-AVG to develop a model-free algorithm that finds an $$\epsilon$$-optimal policy with sample complexity $$\widetilde{O}(SAsp^2(h^*)\epsilon^{-2} + S^2Asp(h^*)\epsilon^{-1}).$$ This sample complexity is near-optimal for weakly communicating MDPs, in view of the minimax lower bound $$\Omega(SAsp(^*)\epsilon^{-2})$$. Existing work mainly focuses on ergodic MDPs and the results typically depend on $$t_{mix},$$ the worst-case mixing time induced by a policy. We remark that the diameter $$D$$ and mixing time $$t_{mix}$$ are both lower bounded by $sp(h^*)$, and $$t_{mix}$$ can be arbitrarily large for certain MDPs. On the technical side, our approach integrates two key ideas: learning an $$\gamma$$-discounted MDP as an approximation, and leveraging reference-advantage decomposition for variance in optimistic Q-learning. As recognized in prior work, a naive approximation by discounted MDPs results in suboptimal guarantees. A distinguishing feature of our method is maintaining estimates of value-difference between state pairs to provide a sharper bound on the variance of reference advantage. We also crucially use a careful choice of the discounted factor $$\gamma$$ to balance approximation error due to discounting and the statistical learning error, and we are able to maintain a good-quality reference value function with $O(SA)$ space complexity. 

   more » « less