Specifying reward functions for complex tasks like object manipulation or driving is challenging to do by hand. Reward learning seeks to address this by learning a reward model using human feedback on selected query policies. This shifts the burden of reward specification to the optimal design of the queries. We propose a theoretical framework for studying reward learning and the associated optimal experiment design problem. Our framework models rewards and policies as nonparametric functions belonging to subsets of Reproducing Kernel Hilbert Spaces (RKHSs). The learner receives (noisy) oracle access to a true reward and must output a policy that performs well under the true reward. For this setting, we first derive non-asymptotic excess risk bounds for a simple plug-in estimator based on ridge regression. We then solve the query design problem by optimizing these risk bounds with respect to the choice of query set and obtain a finite sample statistical rate, which depends primarily on the eigenvalue spectrum of a certain linear operator on the RKHSs. Despite the generality of these results, our bounds are stronger than previous bounds developed for more specialized problems. We specifically show that the well-studied problem of Gaussian process (GP) bandit optimization is a special case of our framework, and that our bounds either improve or are competitive with known regret guarantees for the Matérn kernel.

In online marketplaces, customers have access to hundreds of reviews for a single product. Buyers often use reviews from other customers that share their type---such as height for clothing, skin type for skincare products, and location for outdoor furniture---to estimate their values, which they may not know a priori. Customers with few relevant reviews may hesitate to make a purchase except at a low price, so for the seller, there is a tension between setting high prices and ensuring that there are enough reviews so that buyers can confidently estimate their values. Simultaneously, sellers may use reviews to gauge the demand for items they wish to sell.

We introduce the “inverse bandit” problem of estimating the rewards of a multi-armed bandit instance from observing the learning process of a low-regret demonstrator. Existing approaches to the related problem of inverse reinforcement learning assume the execution of an optimal policy, and thereby suffer from an identifiability issue. In contrast, we propose to leverage the demonstrator’s behavior en route to optimality, and in particular, the exploration phase, for reward estimation. We begin by establishing a general information-theoretic lower bound under this paradigm that applies to any demonstrator algorithm, which characterizes a fundamental tradeoff between reward estimation and the amount of exploration of the demonstrator. Then, we develop simple and efficient reward estimators for upper-confidence-based demonstrator algorithms that attain the optimal tradeoff, showing in particular that consistent reward estimation—free of identifiability issues—is possible under our paradigm. Extensive simulations on both synthetic and semi-synthetic data corroborate our theoretical results.

The sharing of scarce resources among multiple rational agents is one of the classical problems in economics. In exchange economies, which are used to model such situations, agents begin with an initial endowment of resources and exchange them in a way that is mutually beneficial until they reach a competitive equilibrium (CE). The allocations at a CE are Pareto efficient and fair. Consequently, they are used widely in designing mechanisms for fair division. However, computing CEs requires the knowledge of agent preferences which are unknown in several applications of interest. In this work, we explore a new online learning mechanism, which, on each round, allocates resources to the agents and collects stochastic feedback on their experience in using that allocation. Its goal is to learn the agent utilities via this feedback and imitate the allocations at a CE in the long run. We quantify CE behavior via two losses and propose a randomized algorithm which achieves sublinear loss under a parametric class of utilities. Empirically, we demonstrate the effectiveness of this mechanism through numerical simulations.

Auctions with partially-revealed information about items are broadly employed in real-world applications, but the underlying mechanisms have limited theoretical support. In this work, we study a machine learning formulation of these types of mechanisms, presenting algorithms that are no-regret from the buyer’s perspective. Specifically, a buyer who wishes to maximize his utility interacts repeatedly with a platform over a series of $T$ rounds. In each round, a new item is drawn from an unknown distribution and the platform publishes a price together with incomplete, “masked” information about the item. The buyer then decides whether to purchase the item. We formalize this problem as an online learning task where the goal is to have low regret with respect to a myopic oracle that has perfect knowledge of the distribution over items and the seller’s masking function. When the distribution over items is known to the buyer and the mask is a SimHash function mapping $\R^d$ to $\{0,1\}^{\ell}$, our algorithm has regret $\tilde \cO((Td\ell)^{\nicefrac{1}{2}})$. In a fully agnostic setting when the mask is an arbitrary function mapping to a set of size $n$ and the prices are stochastic, our algorithm has regret $\tilde \cO((Tn)^{\nicefrac{1}{2}})$.

The intersection of causal inference and machine learning for decision-making is rapidly expanding, but the default decision criterion remains an average of individual causal outcomes across a population. In practice, various operational restrictions ensure that a decision-maker's utility is not realized as an average but rather as an output of a downstream decision-making problem (such as matching, assignment, network flow, minimizing predictive risk). In this work, we develop a new framework for off-policy evaluation with policy-dependent linear optimization responses: causal outcomes introduce stochasticity in objective function coefficients. Under this framework, a decision-maker's utility depends on the policy-dependent optimization, which introduces a fundamental challenge of optimization bias even for the case of policy evaluation. We construct unbiased estimators for the policy-dependent estimand by a perturbation method, and discuss asymptotic variance properties for a set of adjusted plug-in estimators. Lastly, attaining unbiased policy evaluation allows for policy optimization: we provide a general algorithm for optimizing causal interventions. We corroborate our theoretical results with numerical simulations.

We study the problem of learning revenue-optimal multi-bidder auctions from samples when the samples of bidders' valuations can be adversarially corrupted or drawn from distributions that are adversarially perturbed. First, we prove tight upper bounds on the revenue we can obtain with a corrupted distribution under a population model, for both regular valuation distributions and distributions with monotone hazard rate (MHR). We then propose new algorithms that, given only an ``approximate distribution'' for the bidder's valuation, can learn a mechanism whose revenue is nearly optimal simultaneously for all ``true distributions'' that are $\alpha$-close to the original distribution in Kolmogorov-Smirnov distance. The proposed algorithms operate beyond the setting of bounded distributions that have been studied in prior works, and are guaranteed to obtain a fraction $1-O(\alpha)$ of the optimal revenue under the true distribution when the distributions are MHR. Moreover, they are guaranteed to yield at least a fraction $1-O(\sqrt{\alpha})$ of the optimal revenue when the distributions are regular. We prove that these upper bounds cannot be further improved, by providing matching lower bounds. Lastly, we derive sample complexity upper bounds for learning a near-optimal auction for both MHR and regular distributions.

An increasingly common setting in machine learning involves multiple parties, each with their own data, who want to jointly make predictions on future test points. Agents wish to benefit from the collective expertise of the full set of agents to make better predictions than they would individually, but may not be willing to release labeled data or model parameters. In this work, we explore a decentralized mechanism to make collective predictions at test time, that is inspired by the literature in social science on human consensus-making. Building on a query model to facilitate information exchange among agents, our approach leverages each agent’s pre-trained model without relying on external validation, model retraining, or data pooling. A theoretical analysis shows that our approach recovers inverse mean-squared-error (MSE) weighting in the large-sample limit which is known to be the optimal way to combine independent, unbiased estimators. Empirically, we demonstrate that our scheme effectively combines models with differing quality across the input space: the proposed consensus prediction achieves significant gains over classical model averaging, and even outperforms weighted averaging schemes that have access to additional validation data. Finally, we propose a decentralized Jackknife procedure as a tool to evaluate the sensitivity of the collective predictions with respect to a single agent's opinion.

We provide theoretical complexity analysis for new algorithms to compute the optimal transport (OT) distance between two discrete probability distributions, and demonstrate their favorable practical performance compared to state-of-art primal-dual algorithms. First, we introduce the \emph{accelerated primal-dual randomized coordinate descent} (APDRCD) algorithm for computing the OT distance. We show that its complexity is $\bigOtil(\frac{n^{5/2}}{\varepsilon})$, where $n$ stands for the number of atoms of these probability measures and $\varepsilon > 0$ is the desired accuracy. This complexity bound matches the best known complexities of primal-dual algorithms for the OT problems, including the adaptive primal-dual accelerated gradient descent (APDAGD) and the adaptive primal-dual accelerated mirror descent (APDAMD) algorithms. Then, we demonstrate the improved practical efficiency of the APDRCD algorithm through extensive comparative experimental studies. We also propose a greedy version of APDRCD, which we refer to as \emph{accelerated primal-dual greedy coordinate descent} (APDGCD), to further enhance practical performance. Finally, we generalize the APDRCD and APDGCD algorithms to distributed algorithms for computing the Wasserstein barycenter for multiple probability distributions.

We investigate the connections between neural networks and simple building blocks in kernel space. In particular, using well established feature space tools such as direct sum, averaging, and moment lifting, we present an algebra for creating “compositional” kernels from bags of features. We show that these operations correspond to many of the building blocks of “neural tangent kernels (NTK)”. Experimentally, we show that there is a correlation in test error between neural network architectures and the associated kernels. We construct a simple neural network architecture using only 3x3 convolutions, 2x2 average pooling, ReLU, and optimized with SGD and MSE loss that achieves 96% accuracy on CIFAR10, and whose corresponding compositional kernel achieves 90% accuracy. We also use our constructions to investigate the relative performance of neural networks, NTKs, and compositional kernels in the small dataset regime. In particular, we find that compositional kernels outperform NTKs and neural networks outperform both kernel methods.

In machine learning applications such as ranking fairness or fairness over intersectional groups, one often encounters optimization problems with an extremely large number of constraints. In particular, with ranking fairness tasks, there may even be a variable number of constraints, e.g. one for each query in the training set. In these cases, the standard approach of optimizing a Lagrangian while maintaining one Lagrange multiplier per constraint may no longer be practical. Our proposal is to associate a feature vector with each constraint, and to learn a ``multiplier model’’ that maps each such vector to the corresponding Lagrange multiplier. We prove optimality, approximate feasibility and generalization guarantees under assumptions on the flexibility of the multiplier model, and empirically demonstrate that our method is effective on real-world case studies.

Many existing fairness criteria for machine learning involve equalizing some metric across protected groups such as race or gender. However, practitioners trying to audit or enforce such group-based criteria can easily face the problem of noisy or biased protected group information. First, we study the consequences of naively relying on noisy protected group labels: we provide an upper bound on the fairness violations on the true groups $G$ when the fairness criteria are satisfied on noisy groups $\hat{G}$. Second, we introduce two new approaches using robust optimization that, unlike the naive approach of only relying on $\hat{G}$, are guaranteed to satisfy fairness criteria on the true protected groups $G$ while minimizing a training objective. We provide theoretical guarantees that one such approach converges to an optimal feasible solution. Using two case studies, we show empirically that the robust approaches achieve better true group fairness guarantees than the naive approach.

Directed network with flow dynamics is an important topic in realistic complex systems such as banking systems. We study the stability of these financial networks using a homogeneous and a more general inhomogeneous model. The nodes of the networks are banks and they are under four different kinds of disturbance that may lead to bankruptcy, which is defined by the condition that the capital value of the bank is below a critical value, such as zero. The stability of this network is measured by the minimum value of capital of the nodes after a fixed time of money flow in the network. The smaller the minimum value, the higher the probability of the first bankruptcy. By means of genetic algorithm with networks as the chromosome, the edges between nodes as genes, we can perform evolutionary computation using rewiring of edges as the genetic operators to search for a network topology with high stability. Our analytical results on flow dynamics are based on the linear relation between net change and PageRank centrality under small damping factor. Our numerical analysis shows that genetic algorithm can be very efficient in finding network with given connectivity that is stable against four categories of disturbance, namely under internal (and external) perturbation that is cumulative or noncumulative. Our results show that a banking network with each bank with similar relative wealth (thus small Gini coefficient in wealth distribution) is more stable than one with highly unequal wealth distribution. We also find our optimization method works for delaying the second bankruptcy after the first. These results may be useful in practical applications for the prevention of the first failure, as well as cascade failures in real complex systems.