We present the first finite time global convergence analysis of policy gradient in the context of infinite horizon average reward Markov decision processes (MDPs). Specifically, we focus on ergodic tabular MDPs with finite state and action spaces. Our analysis shows that the policy gradient iterates converge to the optimal policy at a sublinear rate of $O\left({\frac{1}{T}}\right),$ which translates to $O\left({\log(T)}\right)$ regret, where $T$ represents the number of iterations. Prior work on performance bounds for discounted reward MDPs cannot be extended to average reward MDPs because the bounds grow proportional to the fifth power of the effective horizon. Thus, our primary contribution is in proving that the policy gradient algorithm converges for average-reward MDPs and in obtaining finite-time performance guarantees. In contrast to the existing discounted reward performance bounds, our performance bounds have an explicit dependence on constants that capture the complexity of the underlying MDP. Motivated by this observation, we reexamine and improve the existing performance bounds for discounted reward MDPs. We also present simulations to empirically evaluate the performance of average reward policy gradient algorithm.
Byzantine-robust learning has emerged as a prominent fault-tolerant distributed machine learning framework. However, most techniques consider the static setting, wherein the identity of Byzantine machines remains fixed during the learning process. This assumption does not capture real-world dynamic Byzantine behaviors, which may include transient malfunctions or targeted temporal attacks. Addressing this limitation, we propose $\textsf{DynaBRO}$ -- a new method capable of withstanding $\mathcal{O}(\sqrt{T})$ rounds of Byzantine identity alterations (where $T$ is the total number of training rounds), while matching the asymptotic convergence rate of the static setting. Our method combines a multi-level Monte Carlo (MLMC) gradient estimation technique with robust aggregation of worker updates and incorporates a fail-safe filter to limit bias from dynamic Byzantine strategies. Additionally, by leveraging an adaptive learning rate, our approach eliminates the need for knowing the percentage of Byzantine workers.
We study online meta-learning with bandit feedback, with the goal of improving performance across multiple tasks if they are similar according to some natural similarity measure. As the first to target the adversarial online-within-online partial-information setting, we design meta-algorithms that combine outer learners to simultaneously tune the initialization and other hyperparameters of an inner learner for two important cases: multi-armed bandits (MAB) and bandit linear optimization (BLO). For MAB, the meta-learners initialize and set hyperparameters of the Tsallis-entropy generalization of Exp3, with the task-averaged regret improving if the entropy of the optima-in-hindsight is small. For BLO, we learn to initialize and tune online mirror descent (OMD) with self-concordant barrier regularizers, showing that task-averaged regret varies directly with an action space-dependent measure they induce. Our guarantees rely on proving that unregularized follow-the-leader combined with two levels of low-dimensional hyperparameter tuning is enough to learn a sequence of affine functions of non-Lipschitz and sometimes non-convex Bregman divergences bounding the regret of OMD.
We consider stochastic convex optimization problems where the objective is an expectation over smooth functions. For this setting we suggest a novel gradient estimate that combines two recent mechanism that are related to notion of momentum. Then, we design an SGD-style algorithm as well as an accelerated version that make use of this new estimator, and demonstrate the robustness of these new approaches to the choice of the learning rate. Concretely, we show that these approaches obtain the optimal convergence rates for both noiseless and noisy case with the same choice of fixed learning rate. Moreover, for the noisy case we show that these approaches achieve the same optimal bound for a very wide range of learning rates.
We consider distributed learning scenarios where M machines interact with a parameter server along several communication rounds in order to minimize a joint objective function. Focusing on the heterogeneous case, where different machines may draw samples from different data-distributions, we design the first local update method that provably benefits over the two most prominent distributed baselines: namely Minibatch-SGD and Local-SGD. Key to our approach is a slow querying technique that we customize to the distributed setting, which in turn enables a better mitigation of the bias caused by local updates.
Many compression techniques have been proposed to reduce the communication overhead of Federated Learning training procedures. However, these are typically designed for compressing model updates, which are expected to decay throughout training. As a result, such methods are inapplicable to downlink (i.e., from the parameter server to clients) compression in the cross-device setting, where heterogeneous clients $\textit{may appear only once}$ during training and thus must download the model parameters. In this paper, we propose a new framework ($\texttt{DoCoFL}$) for downlink compression in the cross-device federated learning setting. Importantly, $\texttt{DoCoFL}$ can be seamlessly combined with many uplink compression schemes, rendering it suitable for bi-directional compression. Through extensive evaluation, we demonstrate that $\texttt{DoCoFL}$ offers significant bi-directional bandwidth reduction while achieving competitive accuracy to that of $\texttt{FedAvg}$ without compression.
We study meta-learning for adversarial multi-armed bandits. We consider the online-within-online setup, in which a player (learner) encounters a sequence of multi-armed bandit episodes. The player's performance is measured as regret against the best arm in each episode, according to the losses generated by an adversary. The difficulty of the problem depends on the empirical distribution of the per-episode best arm chosen by the adversary. We present an algorithm that can leverage the non-uniformity in this empirical distribution, and derive problem-dependent regret bounds. This solution comprises an inner learner that plays each episode separately, and an outer learner that updates the hyper-parameters of the inner algorithm between the episodes. In the case where the best arm distribution is far from uniform, it improves upon the best bound that can be achieved by any online algorithm executed on each episode individually without meta-learning.
We consider stochastic optimization problems where data is drawn from a Markov chain. Existing methods for this setting crucially rely on knowing the mixing time of the chain, which in real-world applications is usually unknown. We propose the first optimization method that does not require the knowledge of the mixing time, yet obtains the optimal asymptotic convergence rate when applied to convex problems. We further show that our approach can be extended to: (i) finding stationary points in non-convex optimization with Markovian data, and (ii) obtaining better dependence on the mixing time in temporal difference (TD) learning; in both cases, our method is completely oblivious to the mixing time. Our method relies on a novel combination of multi-level Monte Carlo (MLMC) gradient estimation together with an adaptive learning method.
We investigate robust linear regression where data may be contaminated by an oblivious adversary, i.e., an adversary than may know the data distribution but is otherwise oblivious to the realizations of the data samples. This model has been previously analyzed under strong assumptions. Concretely, $\textbf{(i)}$ all previous works assume that the covariance matrix of the features is positive definite; and $\textbf{(ii)}$ most of them assume that the features are centered (i.e. zero mean). Additionally, all previous works make additional restrictive assumption, e.g., assuming that the features are Gaussian or that the corruptions are symmetrically distributed. In this work we go beyond these assumptions and investigate robust regression under a more general set of assumptions: $\textbf{(i)}$ we allow the covariance matrix to be either positive definite or positive semi definite, $\textbf{(ii)}$ we do not necessarily assume that the features are centered, $\textbf{(iii)}$ we make no further assumption beyond boundedness (sub-Gaussianity) of features and measurement noise. Under these assumption we analyze a natural SGD variant for this problem and show that it enjoys a fast convergence rate when the covariance matrix is positive definite. In the positive semi definite case we show that there are two regimes: if the features are centered we can obtain a standard convergence rate; otherwise the adversary can cause any learner to fail arbitrarily.
We develop an algorithmic framework for solving convex optimization problems using no-regret game dynamics. By converting the problem of minimizing a convex function into an auxiliary problem of solving a min-max game in a sequential fashion, we can consider a range of strategies for each of the two-players who must select their actions one after the other. A common choice for these strategies are so-called no-regret learning algorithms, and we describe a number of such and prove bounds on their regret. We then show that many classical first-order methods for convex optimization -- including average-iterate gradient descent, the Frank-Wolfe algorithm, the Heavy Ball algorithm, and Nesterov's acceleration methods -- can be interpreted as special cases of our framework as long as each player makes the correct choice of no-regret strategy. Proving convergence rates in this framework becomes very straightforward, as they follow from plugging in the appropriate known regret bounds. Our framework also gives rise to a number of new first-order methods for special cases of convex optimization that were not previously known.