Traditional online algorithms encapsulate decision making under uncertainty, and give ways to hedge against all possible future events, while guaranteeing a nearly optimal solution, as compared to an offline optimum. On the other hand, machine learning algorithms are in the business of extrapolating patterns found in the data to predict the future, and usually come with strong guarantees on the expected generalization error. In this work, we develop a framework for augmenting online algorithms with a machine learned predictor to achieve competitive ratios that provably improve upon unconditional worst-case lower bounds when the predictor has low error. Our approach treats the predictor as a complete black box and is not dependent on its inner workings or the exact distribution of its errors. We apply this framework to the traditional caching problem—creating an eviction strategy for a cache of size k . We demonstrate that naively following the oracle’s recommendations may lead to very poor performance, even when the average error is quite low. Instead, we show how to modify the Marker algorithm to take into account the predictions and prove that this combined approach achieves a competitive ratio that both (i) decreases as the predictor’s error decreases and (ii) is always capped by O (log k ), which can be achieved without any assistance from the predictor. We complement our results with an empirical evaluation of our algorithm on real-world datasets and show that it performs well empirically even when using simple off-the-shelf predictions.

We introduce a new model of stochastic bandits with adversarial corruptions which aims to capture settings where most of the input follows a stochastic pattern but some fraction of it can be adversarially changed to trick the algorithm, e.g., click fraud, fake reviews and email spam. The goal of this model is to encourage the design of bandit algorithms that (i) work well in mixed adversarial and stochastic models, and (ii) whose performance deteriorates gracefully as we move from fully stochastic to fully adversarial models.In our model, the rewards for all arms are initially drawn from a distribution and are then altered by an adaptive adversary. We provide a simple algorithm whose performance gracefully degrades with the total corruption the adversary injected in the data, measured by the sum across rounds of the biggest alteration the adversary made in the data in that round; this total corruption is denoted by C. Our algorithm provides a guarantee that retains the optimal guarantee (up to a logarithmic term) if the input is stochastic and whose performance degrades linearly to the amount of corruption C, while crucially being agnostic to it. We also provide a lower bound showing that this linear degradation is necessary if the algorithm achieves optimal performance in the stochastic setting (the lower bound works even for a known amount of corruption, a special case in which our algorithm achieves optimal performance without the extra logarithm).

We study the quality of outcomes in repeated games when the population of players is dynamically changing, and where participants use learning algorithms to adapt to the dynamic environment. Price of anarchy has originally been introduced to study the Nash equilibria of one-shot games. Many games studied in computer science, such as packet routing or ad-auctions, are played repeatedly. Given the computational hardness of Nash equilibria, an attractive alternative in repeated game settings is that players use no-regret learning algorithms. The price of total anarchy considers the quality of such learning outcomes, assuming a steady environment and player population, which is rarely the case in online settings.In this paper we analyze efficiency of repeated games in dynamically changing environments. An important trait of learning behavior is its versatility to changing environments, assuming that the learning method used is adaptive, i.e., doesn't rely too heavily on experience from the distant past. We show that, in large classes of games, if players choose their strategies in a way that guarantees low adaptive regret, high social welfare is ensured, even under very frequent changes.A main technical tool for our analysis is the existence of a solution to the welfare maximization problem that is both close to optimal and relatively stable over time. Such a solution serves as a benchmark in the efficiency analysis of learning outcomes. We show that such a stable and close to optimal solution exists for many problems, even in cases when the exact optimal solution can be very unstable. We further show that a sufficient condition on the existence of stable outcomes is the existence of a differentially private algorithm for

Optimizing shared vehicle systems (bike-sharing/car-sharing/ride-sharing) is more challenging compared to traditional resource allocation settings due to the presence of complex network externalities -changes in the demand/supply at any location affect future supply throughout the system within short timescales. These externalities are well captured by steady-state Markovian models, which are therefore widely used to analyze such systems. However, using such models to design pricing/control policies is computationally difficult since the resulting optimization problems are high-dimensional and non-convex.To this end, we develop a general approximation framework for designing pricing policies in shared vehicle systems, based on a novel convex relaxation which we term elevated flow relaxation. Our approach provides the first efficient algorithms with rigorous approximation guarantees for a wide range of objective functions (throughput, revenue, welfare). For any shared vehicle system with n stations and m vehicles, our framework provides a pricing policy with an approximation ratio of 1 + (n − 1)/m. This guarantee is particularly meaningful when m/n, the average number of vehicles per station is large, as is often the case in practice.Further, the simplicity of our approach allows us to extend it to more complex settings: rebalancing empty vehicles, redirecting riders to nearby vehicles, multi-objective settings (such as Ramsey pricing), incorporating travel-times, etc. Our approach yields efficient algorithms with the same approximation guarantees for all these problems, and in the process, obtains as special cases several existing heuristics and asymptotic guarantees.

The optimal management of shared vehicle systems, such as bike-, scooter-, car-, or ride-sharing, is more challenging compared with traditional resource allocation settings because of the presence of spatial externalities—changes in the demand/supply at any location affect future supply throughout the system within short timescales. These externalities are well captured by steady-state Markovian models, which are therefore widely used to analyze such systems. However, using Markovian models to design pricing and other control policies is computationally difficult because the resulting optimization problems are high dimensional and nonconvex. In our work, we design a framework that provides near-optimal policies, for a range of possible controls, that are based on applying the possible controls to achieve spatial balance on average. The optimality gap of these policies improves as the ratio between supply and the number of locations increases and asymptotically goes to zero.