arXiv subjects

Patrick Jaillet

Publications and source records attributed to Patrick Jaillet.

At least 73 records · Page 4Linked to original sources

arXiv2021

Robust Entropy-regularized Markov Decision Processes

Stochastic and soft optimal policies resulting from entropy-regularized Markov decision processes (ER-MDP) are desirable for exploration and imitation learning applications. Motivated by the fact that such policies are sensitive with respect to the state transition probabilities, and the estimation of these probabilities may be inaccurate, we study a robust version of the ER-MDP model, where the stochastic optimal policies are required to be robust with respect to the ambiguity in the underlying transition probabilities. Our work is at the crossroads of two important schemes in reinforcement learning (RL), namely, robust MDP and entropy regularized MDP. We show that essential properties that hold for the non-robust ER-MDP and robust unregularized MDP models also hold in our settings, making the robust ER-MDP problem tractable. We show how our framework and results can be integrated into different algorithmic schemes including value or (modified) policy iteration, which would lead to new robust RL and inverse RL algorithms to handle uncertainties. Analyses on computational complexity and error propagation under conventional uncertainty settings are also provided.

cs.LG↗

arXiv2021

Differentially Private Federated Bayesian Optimization with Distributed Exploration

Bayesian optimization (BO) has recently been extended to the federated learning (FL) setting by the federated Thompson sampling (FTS) algorithm, which has promising applications such as federated hyperparameter tuning. However, FTS is not equipped with a rigorous privacy guarantee which is an important consideration in FL. Recent works have incorporated differential privacy (DP) into the training of deep neural networks through a general framework for adding DP to iterative algorithms. Following this general DP framework, our work here integrates DP into FTS to preserve user-level privacy. We also leverage the ability of this general DP framework to handle different parameter vectors, as well as the technique of local modeling for BO, to further improve the utility of our algorithm through distributed exploration (DE). The resulting differentially private FTS with DE (DP-FTS-DE) algorithm is endowed with theoretical guarantees for both the privacy and utility and is amenable to interesting theoretical insights about the privacy-utility trade-off. We also use real-world experiments to show that DP-FTS-DE achieves high utility (competitive performance) with a strong privacy guarantee (small privacy loss) and induces a trade-off between privacy and utility.

cs.LG↗

arXiv2021

Robust Product-line Pricing under Generalized Extreme Value Models

We study robust versions of pricing problems where customers choose products according to a generalized extreme value (GEV) choice model, and the choice parameters are not known exactly but lie in an uncertainty set. We show that, when the robust problem is unconstrained and the price sensitivity parameters are homogeneous, the robust optimal prices have a constant markup over products, and we provide formulas that allow to compute this constant markup by bisection. We further show that, in the case that the price sensitivity parameters are only homogeneous in each partition of the products, under the assumption that the choice probability generating function and the uncertainty set are partition-wise separable, a robust solution will have a constant markup in each subset, and this constant-markup vector can be found efficiently by convex optimization. We provide numerical results to illustrate the advantages of our robust approach in protecting from bad scenarios. Our results hold for convex and bounded uncertainty sets,} and for any arbitrary GEV model, including the multinomial logit, nested or cross-nested logit.

math.OC↗

arXiv2021

Trusted-Maximizers Entropy Search for Efficient Bayesian Optimization

Information-based Bayesian optimization (BO) algorithms have achieved state-of-the-art performance in optimizing a black-box objective function. However, they usually require several approximations or simplifying assumptions (without clearly understanding their effects on the BO performance) and/or their generalization to batch BO is computationally unwieldy, especially with an increasing batch size. To alleviate these issues, this paper presents a novel trusted-maximizers entropy search (TES) acquisition function: It measures how much an input query contributes to the information gain on the maximizer over a finite set of trusted maximizers, i.e., inputs optimizing functions that are sampled from the Gaussian process posterior belief of the objective function. Evaluating TES requires either only a stochastic approximation with sampling or a deterministic approximation with expectation propagation, both of which are investigated and empirically evaluated using synthetic benchmark objective functions and real-world optimization problems, e.g., hyperparameter tuning of a convolutional neural network and synthesizing 'physically realizable' faces to fool a black-box face recognition system. Though TES can naturally be generalized to a batch variant with either approximation, the latter is amenable to be scaled to a much larger batch size in our experiments.

cs.LG↗

arXiv2021

Convolutional Normalizing Flows for Deep Gaussian Processes

Deep Gaussian processes (DGPs), a hierarchical composition of GP models, have successfully boosted the expressive power of their single-layer counterpart. However, it is impossible to perform exact inference in DGPs, which has motivated the recent development of variational inference-based methods. Unfortunately, either these methods yield a biased posterior belief or it is difficult to evaluate their convergence. This paper introduces a new approach for specifying flexible, arbitrarily complex, and scalable approximate posterior distributions. The posterior distribution is constructed through a normalizing flow (NF) which transforms a simple initial probability into a more complex one through a sequence of invertible transformations. Moreover, a novel convolutional normalizing flow (CNF) is developed to improve the time efficiency and capture dependency between layers. Empirical evaluation shows that CNF DGP outperforms the state-of-the-art approximation methods for DGPs.

cs.LG↗

arXiv2021

Value-at-Risk Optimization with Gaussian Processes

Value-at-risk (VaR) is an established measure to assess risks in critical real-world applications with random environmental factors. This paper presents a novel VaR upper confidence bound (V-UCB) algorithm for maximizing the VaR of a black-box objective function with the first no-regret guarantee. To realize this, we first derive a confidence bound of VaR and then prove the existence of values of the environmental random variable (to be selected to achieve no regret) such that the confidence bound of VaR lies within that of the objective function evaluated at such values. Our V-UCB algorithm empirically demonstrates state-of-the-art performance in optimizing synthetic benchmark functions, a portfolio optimization problem, and a simulated robot task.

cs.LG↗

arXiv2021

Efficient Carpooling and Toll Pricing for Autonomous Transportation

In this paper, we address the existence and computation of competitive equilibrium in the transportation market for autonomous carpooling first proposed by [Ostrovsky and Schwarz, 2019]. At equilibrium, the market organizes carpooled trips over a transportation network in a socially optimal manner and sets the corresponding payments for individual riders and toll prices on edges. The market outcome ensures individual rationality, stability of carpooled trips, budget balance, and market clearing properties under heterogeneous rider preferences. We show that the question of market's existence can be resolved by proving the existence of an integer optimal solution of a linear programming problem. We characterize conditions on the network topology and riders' disutility for carpooling under which a market equilibrium can be computed in polynomial time. This characterization relies on ideas from the theory of combinatorial auctions and minimum cost network flow problem. Finally, we characterize a market equilibrium that achieves strategyproofness and maximizes welfare of individual riders.

cs.GT↗

arXiv2020

Top-$k$ Ranking Bayesian Optimization

This paper presents a novel approach to top-$k$ ranking Bayesian optimization (top-$k$ ranking BO) which is a practical and significant generalization of preferential BO to handle top-$k$ ranking and tie/indifference observations. We first design a surrogate model that is not only capable of catering to the above observations, but is also supported by a classic random utility model. Another equally important contribution is the introduction of the first information-theoretic acquisition function in BO with preferential observation called multinomial predictive entropy search (MPES) which is flexible in handling these observations and optimized for all inputs of a query jointly. MPES possesses superior performance compared with existing acquisition functions that select the inputs of a query one at a time greedily. We empirically evaluate the performance of MPES using several synthetic benchmark functions, CIFAR-$10$ dataset, and SUSHI preference dataset.

cs.LG↗

arXiv2020

An Information-Theoretic Framework for Unifying Active Learning Problems

This paper presents an information-theoretic framework for unifying active learning problems: level set estimation (LSE), Bayesian optimization (BO), and their generalized variant. We first introduce a novel active learning criterion that subsumes an existing LSE algorithm and achieves state-of-the-art performance in LSE problems with a continuous input domain. Then, by exploiting the relationship between LSE and BO, we design a competitive information-theoretic acquisition function for BO that has interesting connections to upper confidence bound and max-value entropy search (MES). The latter connection reveals a drawback of MES which has important implications on not only MES but also on other MES-based acquisition functions. Finally, our unifying information-theoretic framework can be applied to solve a generalized problem of LSE and BO involving multiple level sets in a data-efficient manner. We empirically evaluate the performance of our proposed algorithms using synthetic benchmark functions, a real-world dataset, and in hyperparameter tuning of machine learning models.

cs.LG↗

arXiv2020

An Iterative Security Game for Computing Robust and Adaptive Network Flows

The recent advancement in real-world critical infrastructure networks has led to an exponential growth in the use of automated devices which in turn has created new security challenges. In this paper, we study the robust and adaptive maximum flow problem in an uncertain environment where the network parameters (e.g., capacities) are known and deterministic, but the network structure (e.g., edges) is vulnerable to adversarial attacks or failures. We propose a robust and sustainable network flow model to effectively and proactively counter plausible attacking behaviors of an adversary operating under a budget constraint. Specifically, we introduce a novel scenario generation approach based on an iterative two-player game between a defender and an adversary. We assume that the adversary always takes a best myopic response (out of some feasible attacks) against the current flow scenario prepared by the defender. On the other hand, we assume that the defender considers all the attacking behaviors revealed by the adversary in previous iterations in order to generate a new conservative flow strategy that is robust (maximin) against all those attacks. This iterative game continues until the objectives of the adversary and the administrator both converge. We show that the robust network flow problem to be solved by the defender is NP-hard and that the complexity of the adversary's decision problem grows exponentially with the network size and the adversary's budget value. We propose two principled heuristic approaches for solving the adversary's problem at the scale of a large urban network. Extensive computational results on multiple synthetic and real-world data sets demonstrate that the solution provided by the defender's problem significantly increases the amount of flow pushed through the network and reduces the expected lost flow over four state-of-the-art benchmark approaches.

cs.GT↗

arXiv2020

Variational Bayesian Unlearning

This paper studies the problem of approximately unlearning a Bayesian model from a small subset of the training data to be erased. We frame this problem as one of minimizing the Kullback-Leibler divergence between the approximate posterior belief of model parameters after directly unlearning from erased data vs. the exact posterior belief from retraining with remaining data. Using the variational inference (VI) framework, we show that it is equivalent to minimizing an evidence upper bound which trades off between fully unlearning from erased data vs. not entirely forgetting the posterior belief given the full data (i.e., including the remaining data); the latter prevents catastrophic unlearning that can render the model useless. In model training with VI, only an approximate (instead of exact) posterior belief given the full data can be obtained, which makes unlearning even more challenging. We propose two novel tricks to tackle this challenge. We empirically demonstrate our unlearning methods on Bayesian models such as sparse Gaussian process and logistic regression using synthetic and real-world datasets.

cs.LG↗

arXiv2020

Federated Bayesian Optimization via Thompson Sampling

Bayesian optimization (BO) is a prominent approach to optimizing expensive-to-evaluate black-box functions. The massive computational capability of edge devices such as mobile phones, coupled with privacy concerns, has led to a surging interest in federated learning (FL) which focuses on collaborative training of deep neural networks (DNNs) via first-order optimization techniques. However, some common machine learning tasks such as hyperparameter tuning of DNNs lack access to gradients and thus require zeroth-order/black-box optimization. This hints at the possibility of extending BO to the FL setting (FBO) for agents to collaborate in these black-box optimization tasks. This paper presents federated Thompson sampling (FTS) which overcomes a number of key challenges of FBO and FL in a principled way: We (a) use random Fourier features to approximate the Gaussian process surrogate model used in BO, which naturally produces the parameters to be exchanged between agents, (b) design FTS based on Thompson sampling, which significantly reduces the number of parameters to be exchanged, and (c) provide a theoretical convergence guarantee that is robust against heterogeneous agents, which is a major challenge in FL and FBO. We empirically demonstrate the effectiveness of FTS in terms of communication efficiency, computational efficiency, and practical performance.

cs.LG↗

arXiv2020

Competitive Ratios for Online Multi-capacity Ridesharing

In multi-capacity ridesharing, multiple requests (e.g., customers, food items, parcels) with different origin and destination pairs travel in one resource. In recent years, online multi-capacity ridesharing services (i.e., where assignments are made online) like Uber-pool, foodpanda, and on-demand shuttles have become hugely popular in transportation, food delivery, logistics and other domains. This is because multi-capacity ridesharing services benefit all parties involved { the customers (due to lower costs), the drivers (due to higher revenues) and the matching platforms (due to higher revenues per vehicle/resource). Most importantly these services can also help reduce carbon emissions (due to fewer vehicles on roads). Online multi-capacity ridesharing is extremely challenging as the underlying matching graph is no longer bipartite (as in the unit-capacity case) but a tripartite graph with resources (e.g., taxis, cars), requests and request groups (combinations of requests that can travel together). The desired matching between resources and request groups is constrained by the edges between requests and request groups in this tripartite graph (i.e., a request can be part of at most one request group in the final assignment). While there have been myopic heuristic approaches employed for solving the online multi-capacity ridesharing problem, they do not provide any guarantees on the solution quality. To that end, this paper presents the first approach with bounds on the competitive ratio for online multi-capacity ridesharing (when resources rejoin the system at their initial location/depot after serving a group of requests).

cs.AI↗

arXiv2020

Zone pAth Construction (ZAC) based Approaches for Effective Real-Time Ridesharing

Real-time ridesharing systems such as UberPool, Lyft Line, GrabShare have become hugely popular as they reduce the costs for customers, improve per trip revenue for drivers and reduce traffic on the roads by grouping customers with similar itineraries. The key challenge in these systems is to group the "right" requests to travel together in the "right" available vehicles in real-time, so that the objective (e.g., requests served, revenue or delay) is optimized. This challenge has been addressed in existing work by: (i) generating as many relevant feasible (with respect to the available delay for customers) combinations of requests as possible in real-time; and then (ii) optimizing assignment of the feasible request combinations to vehicles. Since the number of request combinations increases exponentially with the increase in vehicle capacity and number of requests, unfortunately, such approaches have to employ ad hoc heuristics to identify a subset of request combinations for assignment. Our key contribution is in developing approaches that employ zone (abstraction of individual locations) paths instead of request combinations. Zone paths allow for generation of significantly more "relevant" combinations (in comparison to ad hoc heuristics) in real-time than competing approaches due to two reasons: (i) Each zone path can typically represent multiple request combinations; (ii) Zone paths are generated using a combination of offline and online methods. Specifically, we contribute both myopic (ridesharing assignment focussed on current requests only) and non-myopic (ridesharing assignment considers impact on expected future requests) approaches that employ zone paths. In our experimental results, we demonstrate that our myopic approach outperforms (with respect to both objective and runtime) the current best myopic approach for ridesharing on both real-world and synthetic datasets.

cs.AI↗

arXiv2020

Probability Distributions on Partially Ordered Sets and Network Interdiction Games

This article poses the following problem: Does there exist a probability distribution over subsets of a finite partially ordered set (poset), such that a set of constraints involving marginal probabilities of the poset's elements and maximal chains is satisfied? We present a combinatorial algorithm to positively resolve this question. The algorithm can be implemented in polynomial time in the special case where maximal chain probabilities are affine functions of their elements. This existence problem is relevant for the equilibrium characterization of a generic strategic interdiction game on a capacitated flow network. The game involves a routing entity that sends its flow through the network while facing path transportation costs, and an interdictor who simultaneously interdicts one or more edges while facing edge interdiction costs. Using our existence result on posets and strict complementary slackness in linear programming, we show that the Nash equilibria of this game can be fully described using primal and dual solutions of a minimum-cost circulation problem. Our analysis provides a new characterization of the critical components in the interdiction game. It also leads to a polynomial-time approach for equilibrium computation.

cs.GT↗

arXiv2020

Generalized Maximum Causal Entropy for Inverse Reinforcement Learning

We consider the problem of learning from demonstrated trajectories with inverse reinforcement learning (IRL). Motivated by a limitation of the classical maximum entropy model in capturing the structure of the network of states, we propose an IRL model based on a generalized version of the causal entropy maximization problem, which allows us to generate a class of maximum entropy IRL models. Our generalized model has an advantage of being able to recover, in addition to a reward function, another expert's function that would (partially) capture the impact of the connecting structure of the states on experts' decisions. Empirical evaluation on a real-world dataset and a grid-world dataset shows that our generalized model outperforms the classical ones, in terms of recovering reward functions and demonstrated trajectories.

cs.LG↗

arXiv2020

A Relation Analysis of Markov Decision Process Frameworks

We study the relation between different Markov Decision Process (MDP) frameworks in the machine learning and econometrics literatures, including the standard MDP, the entropy and general regularized MDP, and stochastic MDP, where the latter is based on the assumption that the reward function is stochastic and follows a given distribution. We show that the entropy-regularized MDP is equivalent to a stochastic MDP model, and is strictly subsumed by the general regularized MDP. Moreover, we propose a distributional stochastic MDP framework by assuming that the distribution of the reward function is ambiguous. We further show that the distributional stochastic MDP is equivalent to the regularized MDP, in the sense that they always yield the same optimal policies. We also provide a connection between stochastic/regularized MDP and constrained MDP. Our work gives a unified view on several important MDP frameworks, which would lead new ways to interpret the (entropy/general) regularized MDP frameworks through the lens of stochastic rewards and vice-versa. Given the recent popularity of regularized MDP in (deep) reinforcement learning, our work brings new understandings of how such algorithmic schemes work and suggest ideas to develop new ones.

math.OC↗

arXiv2020

Learning Structure in Nested Logit Models

This paper introduces a new data-driven methodology for nested logit structure discovery. Nested logit models allow the modeling of positive correlations between the error terms of the utility specifications of the different alternatives in a discrete choice scenario through the specification of a nesting structure. Current nested logit model estimation practices require an a priori specification of a nesting structure by the modeler. In this we work we optimize over all possible specifications of the nested logit model that are consistent with rational utility maximization. We formulate the problem of learning an optimal nesting structure from the data as a mixed integer nonlinear programming (MINLP) optimization problem and solve it using a variant of the linear outer approximation algorithm. We exploit the tree structure of the problem and utilize the latest advances in integer optimization to bring practical tractability to the optimization problem we introduce. We demonstrate the ability of our algorithm to correctly recover the true nesting structure from synthetic data in a Monte Carlo experiment. In an empirical illustration using a stated preference survey on modes of transportation in the U.S. state of Massachusetts, we use our algorithm to obtain an optimal nesting tree representing the correlations between the unobserved effects of the different travel mode choices. We provide our implementation as a customizable and open-source code base written in the Julia programming language.

stat.ME↗