Efficiently Solving Discounted MDPs with Predictions on Transition Matrices

We study infinite-horizon Discounted Markov Decision Processes (DMDPs) under a generative model. Motivated by the Algorithm with Advice framework Mitzenmacher and Vassilvitskii 2022, we propose a novel framework to investigate how a prediction on the transition matrix can enhance the sample efficiency in solving DMDPs and improve sample complexity bounds. We focus on the DMDPs with $N$ state-action pairs and discounted factor $\gamma$. Firstly, we provide an impossibility result that, without prior knowledge of the prediction accuracy, no sampling policy can compute an $\epsilon$-optimal policy with a sample complexity bound better than $\tilde{O}((1-\gamma)^{-3} N\epsilon^{-2})$, which matches the state-of-the-art minimax sample complexity bound with no prediction. In complement, we propose an algorithm based on minimax optimization techniques that leverages the prediction on the transition matrix. Our algorithm achieves a sample complexity bound depending on the prediction error, and the bound is uniformly better than $\tilde{O}((1-\gamma)^{-4} N \epsilon^{-2})$, the previous best result derived from convex optimization methods. These theoretical findings are further supported by our numerical experiments.

Online Scheduling for LLM Inference with KV Cache Constraints

Large Language Model (LLM) inference, where a trained model generates text one word at a time in response to user prompts, is a computationally intensive process requiring efficient scheduling to optimize latency and resource utilization. A key challenge in LLM inference is the management of the Key-Value (KV) cache, which reduces redundant computations but introduces memory constraints. In this work, we model LLM inference with KV cache constraints theoretically and propose novel batching and scheduling algorithms that minimize inference latency while effectively managing the KV cache's memory. We analyze both semi-online and fully online scheduling models, and our results are threefold. First, we provide a polynomial-time algorithm that achieves exact optimality in terms of average latency in the semi-online prompt arrival model. Second, in the fully online case with a stochastic prompt arrival, we introduce an efficient online scheduling algorithm with constant regret. Third, we prove that no algorithm (deterministic or randomized) can achieve a constant competitive ratio in fully online adversarial settings. Our empirical evaluations on a public LLM inference dataset, using the Llama-70B model on A100 GPUs, show that our approach significantly outperforms benchmark algorithms used currently in practice, achieving lower latency while reducing energy consumption. Overall, our results offer a path toward more sustainable and cost-effective LLM deployment.

Joint Pricing and Resource Allocation: An Optimal Online-Learning Approach

We study an online learning problem on dynamic pricing and resource allocation, where we make joint pricing and inventory decisions to maximize the overall net profit. We consider the stochastic dependence of demands on the price, which complicates the resource allocation process and introduces significant non-convexity and non-smoothness to the problem. To solve this problem, we develop an efficient algorithm that utilizes a "Lower-Confidence Bound (LCB)" meta-strategy over multiple OCO agents. Our algorithm achieves $\tilde{O}(\sqrt{Tmn})$ regret (for $m$ suppliers and $n$ consumers), which is optimal with respect to the time horizon $T$. Our results illustrate an effective integration of statistical learning methodologies with complex operations research problems.

Learning to Price with Resource Constraints: From Full Information to Machine-Learned Prices

We study the dynamic pricing problem with knapsack, addressing the challenge of balancing exploration and exploitation under resource constraints. We introduce three algorithms tailored to different informational settings: a Boundary Attracted Re-solve Method for full information, an online learning algorithm for scenarios with no prior information, and an estimate-then-select re-solve algorithm that leverages machine-learned informed prices with known upper bound of estimation errors. The Boundary Attracted Re-solve Method achieves logarithmic regret without requiring the non-degeneracy condition, while the online learning algorithm attains an optimal $O(\sqrt{T})$ regret. Our estimate-then-select approach bridges the gap between these settings, providing improved regret bounds when reliable offline data is available. Numerical experiments validate the effectiveness and robustness of our algorithms across various scenarios. This work advances the understanding of online resource allocation and dynamic pricing, offering practical solutions adaptable to different informational structures.

Regret Minimization and Statistical Inference in Online Decision Making with High-dimensional Covariates

This paper investigates regret minimization, statistical inference, and their interplay in high-dimensional online decision-making based on the sparse linear context bandit model. We integrate the $\varepsilon$-greedy bandit algorithm for decision-making with a hard thresholding algorithm for estimating sparse bandit parameters and introduce an inference framework based on a debiasing method using inverse propensity weighting. Under a margin condition, our method achieves either $O(T^{1/2})$ regret or classical $O(T^{1/2})$-consistent inference, indicating an unavoidable trade-off between exploration and exploitation. If a diverse covariate condition holds, we demonstrate that a pure-greedy bandit algorithm, i.e., exploration-free, combined with a debiased estimator based on average weighting can simultaneously achieve optimal $O(\log T)$ regret and $O(T^{1/2})$-consistent inference. We also show that a simple sample mean estimator can provide valid inference for the optimal policy's value. Numerical simulations and experiments on Warfarin dosing data validate the effectiveness of our methods.

Reinforcement Learning with Intrinsically Motivated Feedback Graph for Lost-sales Inventory Control

Reinforcement learning (RL) has proven to be well-performed and general-purpose in the inventory control (IC). However, further improvement of RL algorithms in the IC domain is impeded due to two limitations of online experience. First, online experience is expensive to acquire in real-world applications. With the low sample efficiency nature of RL algorithms, it would take extensive time to train the RL policy to convergence. Second, online experience may not reflect the true demand due to the lost sales phenomenon typical in IC, which makes the learning process more challenging. To address the above challenges, we propose a decision framework that combines reinforcement learning with feedback graph (RLFG) and intrinsically motivated exploration (IME) to boost sample efficiency. In particular, we first take advantage of the inherent properties of lost-sales IC problems and design the feedback graph (FG) specially for lost-sales IC problems to generate abundant side experiences aid RL updates. Then we conduct a rigorous theoretical analysis of how the designed FG reduces the sample complexity of RL methods. Based on the theoretical insights, we design an intrinsic reward to direct the RL agent to explore to the state-action space with more side experiences, further exploiting FG's power. Experimental results demonstrate that our method greatly improves the sample efficiency of applying RL in IC. Our code is available at https://anonymous.4open.science/r/RLIMFG4IC-811D/

Achieving $\tilde{O}(1/ε)$ Sample Complexity for Constrained Markov Decision Process

We consider the reinforcement learning problem for the constrained Markov decision process (CMDP), which plays a central role in satisfying safety or resource constraints in sequential learning and decision-making. In this problem, we are given finite resources and a MDP with unknown transition probabilities. At each stage, we take an action, collecting a reward and consuming some resources, all assumed to be unknown and need to be learned over time. In this work, we take the first step towards deriving optimal problem-dependent guarantees for the CMDP problems. We derive a logarithmic regret bound, which translates into a $O(\frac{\kappa}{\epsilon}\cdot\log^2(1/\epsilon))$ sample complexity bound, with $\kappa$ being a problem-dependent parameter, yet independent of $\epsilon$. Our sample complexity bound improves upon the state-of-art $O(1/\epsilon^2)$ sample complexity for CMDP problems established in the previous literature, in terms of the dependency on $\epsilon$. To achieve this advance, we develop a new framework for analyzing CMDP problems. To be specific, our algorithm operates in the primal space and we resolve the primal LP for the CMDP problem at each period in an online manner, with \textit{adaptive} remaining resource capacities. The key elements of our algorithm are: i). an eliminating procedure that characterizes one optimal basis of the primal LP, and; ii) a resolving procedure that is adaptive to the remaining resources and sticks to the characterized optimal basis.

Constrained Online Two-stage Stochastic Optimization: Algorithm with (and without) Predictions

We consider an online two-stage stochastic optimization with long-term constraints over a finite horizon of $T$ periods. At each period, we take the first-stage action, observe a model parameter realization and then take the second-stage action from a feasible set that depends both on the first-stage decision and the model parameter. We aim to minimize the cumulative objective value while guaranteeing that the long-term average second-stage decision belongs to a set. We develop online algorithms for the online two-stage problem from adversarial learning algorithms. Also, the regret bound of our algorithm can be reduced to the regret bound of embedded adversarial learning algorithms. Based on this framework, we obtain new results under various settings. When the model parameters are drawn from unknown non-stationary distributions and we are given machine-learned predictions of the distributions, we develop a new algorithm from our framework with a regret $O(W_T+\sqrt{T})$, where $W_T$ measures the total inaccuracy of the machine-learned predictions. We then develop another algorithm that works when no machine-learned predictions are given and show the performances.

High-dimensional Linear Bandits with Knapsacks

We study the contextual bandits with knapsack (CBwK) problem under the high-dimensional setting where the dimension of the feature is large. The reward of pulling each arm equals the multiplication of a sparse high-dimensional weight vector and the feature of the current arrival, with additional random noise. In this paper, we investigate how to exploit this sparsity structure to achieve improved regret for the CBwK problem. To this end, we first develop an online variant of the hard thresholding algorithm that performs the sparse estimation in an online manner. We further combine our online estimator with a primal-dual framework, where we assign a dual variable to each knapsack constraint and utilize an online learning algorithm to update the dual variable, thereby controlling the consumption of the knapsack capacity. We show that this integrated approach allows us to achieve a sublinear regret that depends logarithmically on the feature dimension, thus improving the polynomial dependency established in the previous literature. We also apply our framework to the high-dimension contextual bandit problem without the knapsack constraint and achieve optimal regret in both the data-poor regime and the data-rich regime. We finally conduct numerical experiments to show the efficient empirical performance of our algorithms under the high dimensional setting.

Constrained Online Two-stage Stochastic Optimization: New Algorithms via Adversarial Learning

We consider an online two-stage stochastic optimization with long-term constraints over a finite horizon of $T$ periods. At each period, we take the first-stage action, observe a model parameter realization and then take the second-stage action from a feasible set that depends both on the first-stage decision and the model parameter. We aim to minimize the cumulative objective value while guaranteeing that the long-term average second-stage decision belongs to a set. We propose a general algorithmic framework that derives online algorithms for the online two-stage problem from adversarial learning algorithms. Also, the regret bound of our algorithm cam be reduced to the regret bound of embedded adversarial learning algorithms. Based on our framework, we obtain new results under various settings. When the model parameter at each period is drawn from identical distributions, we derive state-of-art regret bound that improves previous bounds under special cases. Our algorithm is also robust to adversarial corruptions of model parameter realizations. When the model parameters are drawn from unknown non-stationary distributions and we are given prior estimates of the distributions, we develop a new algorithm from our framework with a regret $O(W_T+\sqrt{T})$, where $W_T$ measures the total inaccuracy of the prior estimates.