arXiv subjects

Patrick Jaillet

Publications and source records attributed to Patrick Jaillet.

At least 55 records · Page 3Linked to original sources

arXiv2023

Multi-channel Autobidding with Budget and ROI Constraints

In digital online advertising, advertisers procure ad impressions simultaneously on multiple platforms, or so-called channels, such as Google Ads, Meta Ads Manager, etc., each of which consists of numerous ad auctions. We study how an advertiser maximizes total conversion (e.g. ad clicks) while satisfying aggregate return-on-investment (ROI) and budget constraints across all channels. In practice, an advertiser does not have control over, and thus cannot globally optimize, which individual ad auctions she participates in for each channel, and instead authorizes a channel to procure impressions on her behalf: the advertiser can only utilize two levers on each channel, namely setting a per-channel budget and per-channel target ROI. In this work, we first analyze the effectiveness of each of these levers for solving the advertiser's global multi-channel problem. We show that when an advertiser only optimizes over per-channel ROIs, her total conversion can be arbitrarily worse than what she could have obtained in the global problem. Further, we show that the advertiser can achieve the global optimal conversion when she only optimizes over per-channel budgets. In light of this finding, under a bandit feedback setting that mimics real-world scenarios where advertisers have limited information on ad auctions in each channels and how channels procure ads, we present an efficient learning algorithm that produces per-channel budgets whose resulting conversion approximates that of the global optimal problem. Finally, we argue that all our results hold for both single-item and multi-item auctions from which channels procure impressions on advertisers' behalf.

cs.GT↗

arXiv2023

Adversarial Rewards in Universal Learning for Contextual Bandits

We study the fundamental limits of learning in contextual bandits, where a learner's rewards depend on their actions and a known context, which extends the canonical multi-armed bandit to the case where side-information is available. We are interested in universally consistent algorithms, which achieve sublinear regret compared to any measurable fixed policy, without any function class restriction. For stationary contextual bandits, when the underlying reward mechanism is time-invariant, Blanchard et. al (2022) characterized learnable context processes for which universal consistency is achievable; and further gave algorithms ensuring universal consistency whenever this is achievable, a property known as optimistic universal consistency. It is well understood, however, that reward mechanisms can evolve over time, possibly adversarially, and depending on the learner's actions. We show that optimistic universal learning for contextual bandits with adversarial rewards is impossible in general, contrary to all previously studied settings in online learning -- including standard supervised learning. We also give necessary and sufficient conditions for universal learning under various adversarial reward models, and an exact characterization for online rewards. In particular, the set of learnable processes for these reward models is still extremely general -- larger than i.i.d., stationary or ergodic -- but in general strictly smaller than that for supervised learning or stationary contextual bandits, shedding light on new adversarial phenomena.

stat.ML↗

arXiv2023

Universal Regression with Adversarial Responses

We provide algorithms for regression with adversarial responses under large classes of non-i.i.d. instance sequences, on general separable metric spaces, with provably minimal assumptions. We also give characterizations of learnability in this regression context. We consider universal consistency which asks for strong consistency of a learner without restrictions on the value responses. Our analysis shows that such an objective is achievable for a significantly larger class of instance sequences than stationary processes, and unveils a fundamental dichotomy between value spaces: whether finite-horizon mean estimation is achievable or not. We further provide optimistically universal learning rules, i.e., such that if they fail to achieve universal consistency, any other algorithms will fail as well. For unbounded losses, we propose a mild integrability condition under which there exist algorithms for adversarial regression under large classes of non-i.i.d. instance sequences. In addition, our analysis also provides a learning rule for mean estimation in general metric spaces that is consistent under adversarial responses without any moment conditions on the sequence, a result of independent interest.

cs.LG↗

arXiv2023

Quadratic Memory is Necessary for Optimal Query Complexity in Convex Optimization: Center-of-Mass is Pareto-Optimal

We give query complexity lower bounds for convex optimization and the related feasibility problem. We show that quadratic memory is necessary to achieve the optimal oracle complexity for first-order convex optimization. In particular, this shows that center-of-mass cutting-planes algorithms in dimension $d$ which use $\tilde O(d^2)$ memory and $\tilde O(d)$ queries are Pareto-optimal for both convex optimization and the feasibility problem, up to logarithmic factors. Precisely, we prove that to minimize $1$-Lipschitz convex functions over the unit ball to $1/d^4$ accuracy, any deterministic first-order algorithms using at most $d^{2-δ}$ bits of memory must make $\tildeΩ(d^{1+δ/3})$ queries, for any $δ\in[0,1]$. For the feasibility problem, in which an algorithm only has access to a separation oracle, we show a stronger trade-off: for at most $d^{2-δ}$ memory, the number of queries required is $\tildeΩ(d^{1+δ})$. This resolves a COLT 2019 open problem of Woodworth and Srebro.

cs.LG↗

arXiv2023

Federated Neural Bandits

Recent works on neural contextual bandits have achieved compelling performances due to their ability to leverage the strong representation power of neural networks (NNs) for reward prediction. Many applications of contextual bandits involve multiple agents who collaborate without sharing raw observations, thus giving rise to the setting of federated contextual bandits. Existing works on federated contextual bandits rely on linear or kernelized bandits, which may fall short when modeling complex real-world reward functions. So, this paper introduces the federated neural-upper confidence bound (FN-UCB) algorithm. To better exploit the federated setting, FN-UCB adopts a weighted combination of two UCBs: $\text{UCB}^{a}$ allows every agent to additionally use the observations from the other agents to accelerate exploration (without sharing raw observations), while $\text{UCB}^{b}$ uses an NN with aggregated parameters for reward prediction in a similar way to federated averaging for supervised learning. Notably, the weight between the two UCBs required by our theoretical analysis is amenable to an interesting interpretation, which emphasizes $\text{UCB}^{a}$ initially for accelerated exploration and relies more on $\text{UCB}^{b}$ later after enough observations have been collected to train the NNs for accurate reward prediction (i.e., reliable exploitation). We prove sub-linear upper bounds on both the cumulative regret and the number of communication rounds of FN-UCB, and empirically demonstrate its competitive performance.

cs.LG↗

arXiv2023

Effective Dimension in Bandit Problems under Censorship

In this paper, we study both multi-armed and contextual bandit problems in censored environments. Our goal is to estimate the performance loss due to censorship in the context of classical algorithms designed for uncensored environments. Our main contributions include the introduction of a broad class of censorship models and their analysis in terms of the effective dimension of the problem -- a natural measure of its underlying statistical complexity and main driver of the regret bound. In particular, the effective dimension allows us to maintain the structure of the original problem at first order, while embedding it in a bigger space, and thus naturally leads to results analogous to uncensored settings. Our analysis involves a continuous generalization of the Elliptical Potential Inequality, which we believe is of independent interest. We also discover an interesting property of decision-making under censorship: a transient phase during which initial misspecification of censorship is self-corrected at an extra cost, followed by a stationary phase that reflects the inherent slowdown of learning governed by the effective dimension. Our results are useful for applications of sequential decision-making models where the feedback received depends on strategic uncertainty (e.g., agents' willingness to follow a recommendation) and/or random uncertainty (e.g., loss or delay in arrival of information).

cs.LG↗

arXiv2023

Incentive-aware Contextual Pricing with Non-parametric Market Noise

We consider a dynamic pricing problem for repeated contextual second-price auctions with multiple strategic buyers who aim to maximize their long-term time discounted utility. The seller has limited information on buyers' overall demand curves which depends on a non-parametric market-noise distribution, and buyers may potentially submit corrupted bids (relative to true valuations) to manipulate the seller's pricing policy for more favorable reserve prices in the future. We focus on designing the seller's learning policy to set contextual reserve prices where the seller's goal is to minimize regret compared to the revenue of a benchmark clairvoyant policy that has full information of buyers' demand. We propose a policy with a phased-structure that incorporates randomized "isolation" periods, during which a buyer is randomly chosen to solely participate in the auction. We show that this design allows the seller to control the number of periods in which buyers significantly corrupt their bids. We then prove that our policy enjoys a $T$-period regret of $\widetilde{\mathcal{O}}(\sqrt{T})$ facing strategic buyers. Finally, we conduct numerical simulations to compare our proposed algorithm to standard pricing policies. Our numerical results show that our algorithm outperforms these policies under various buyer bidding behavior.

cs.LG↗

arXiv2023

Learning to Price against a Budget and ROI Constrained Buyer

Internet advertisers (buyers) repeatedly procure ad impressions from ad platforms (sellers) with the aim to maximize total conversion (i.e. ad value) while respecting both budget and return-on-investment (ROI) constraints for efficient utilization of limited monetary resources. Facing such a constrained buyer who aims to learn her optimal strategy to acquire impressions, we study from a seller's perspective how to learn and price ad impressions through repeated posted price mechanisms to maximize revenue. For this two-sided learning setup, we propose a learning algorithm for the seller that utilizes an episodic binary-search procedure to identify a revenue-optimal selling price. We show that such a simple learning algorithm enjoys low seller regret when within each episode, the budget and ROI constrained buyer approximately best responds to the posted price. We present simple yet natural buyer's bidding algorithms under which the buyer approximately best responds while satisfying budget and ROI constraints, leading to a low regret for our proposed seller pricing algorithm. The design of our seller algorithm is motivated by the fact that the seller's revenue function admits a bell-shaped structure when the buyer best responds to prices under budget and ROI constraints, enabling our seller algorithm to identify revenue-optimal selling prices efficiently.

cs.GT↗

arXiv2022

Contextual Bandits and Optimistically Universal Learning

We consider the contextual bandit problem on general action and context spaces, where the learner's rewards depend on their selected actions and an observable context. This generalizes the standard multi-armed bandit to the case where side information is available, e.g., patients' records or customers' history, which allows for personalized treatment. We focus on consistency -- vanishing regret compared to the optimal policy -- and show that for large classes of non-i.i.d. contexts, consistency can be achieved regardless of the time-invariant reward mechanism, a property known as universal consistency. Precisely, we first give necessary and sufficient conditions on the context-generating process for universal consistency to be possible. Second, we show that there always exists an algorithm that guarantees universal consistency whenever this is achievable, called an optimistically universal learning rule. Interestingly, for finite action spaces, learnable processes for universal learning are exactly the same as in the full-feedback setting of supervised learning, previously studied in the literature. In other words, learning can be performed with partial feedback without any generalization cost. The algorithms balance a trade-off between generalization (similar to structural risk minimization) and personalization (tailoring actions to specific contexts). Lastly, we consider the case of added continuity assumptions on rewards and show that these lead to universal consistency for significantly larger classes of data-generating processes.

stat.ML↗

arXiv2022

Probabilistic bounds on the $k-$Traveling Salesman Problem and the Traveling Repairman Problem

The $k-$traveling salesman problem ($k$-TSP) seeks a tour of minimal length that visits a subset of $k\leq n$ points. The traveling repairman problem (TRP) seeks a complete tour with minimal latency. This paper provides constant-factor probabilistic approximations of both problems. We first show that the optimal length of the $k$-TSP path grows at a rate of $Θ\left(k/n^{\frac{1}{2}\left(1+\frac{1}{k-1}\right)}\right)$. The proof provides a constant-factor approximation scheme, which solves a TSP in a high-concentration zone -- leveraging large deviations of local concentrations. Then, we show that the optimal TRP latency grows at a rate of $Θ(n\sqrt n)$. This result extends the classical Beardwood-Halton-Hammersley theorem to the TRP. Again, the proof provides a constant-factor approximation scheme, which visits zones by decreasing order of probability density. We discuss practical implications of this result in the design of transportation and logistics systems. Finally, we propose dedicated notions of fairness -- randomized population-based fairness for the $k$-TSP and geographical fairness for the TRP -- and give algorithms to balance efficiency and fairness.

cs.DM↗

arXiv2022

Additional Results and Extensions for the paper "Probabilistic bounds on the $k-$Traveling Salesman Problem and the Traveling Repairman Problem''

This technical report provides additional results for the main paper ``Probabilistic bounds on the $k-$Traveling Salesman Problem ($k-$TSP) and the Traveling Repairman Problem (TRP)''. For the $k-$TSP, we extend the probabilistic bounds derived in the main paper to the case of distributions with general densities. For the TRP, we propose a utility-based notion of fairness and derive constant-factor probabilistic bounds for this objective, thus extending the TRP bounds from the main paper to non-linear utilities.

cs.DM↗

arXiv2022

Sample-Then-Optimize Batch Neural Thompson Sampling

Bayesian optimization (BO), which uses a Gaussian process (GP) as a surrogate to model its objective function, is popular for black-box optimization. However, due to the limitations of GPs, BO underperforms in some problems such as those with categorical, high-dimensional or image inputs. To this end, recent works have used the highly expressive neural networks (NNs) as the surrogate model and derived theoretical guarantees using the theory of neural tangent kernel (NTK). However, these works suffer from the limitations of the requirement to invert an extremely large parameter matrix and the restriction to the sequential (rather than batch) setting. To overcome these limitations, we introduce two algorithms based on the Thompson sampling (TS) policy named Sample-Then-Optimize Batch Neural TS (STO-BNTS) and STO-BNTS-Linear. To choose an input query, we only need to train an NN (resp. a linear model) and then choose the query by maximizing the trained NN (resp. linear model), which is equivalently sampled from the GP posterior with the NTK as the kernel function. As a result, our algorithms sidestep the need to invert the large parameter matrix yet still preserve the validity of the TS policy. Next, we derive regret upper bounds for our algorithms with batch evaluations, and use insights from batch BO and NTK to show that they are asymptotically no-regret under certain conditions. Finally, we verify their empirical effectiveness using practical AutoML and reinforcement learning experiments.

cs.LG↗

arXiv2022

Online Resource Allocation with Samples

We study an online resource allocation problem under uncertainty about demand and about the reward of each type of demand (agents) for the resource. Even though dealing with demand uncertainty in resource allocation problems has been the topic of many papers in the literature, the challenge of not knowing rewards has been barely explored. The lack of knowledge about agents' rewards is inspired by the problem of allocating units of a new resource (e.g., newly developed vaccines or drugs) with unknown effectiveness/value. For such settings, we assume that we can \emph{test} the market before the allocation period starts. During the test period, we sample each agent in the market with probability $p$. We study how to optimally exploit the \emph{sample information} in our online resource allocation problem under adversarial arrival processes. We present an asymptotically optimal algorithm that achieves $1-Θ(1/(p\sqrt{m}))$ competitive ratio, where $m$ is the number of available units of the resource. By characterizing an upper bound on the competitive ratio of any randomized and deterministic algorithm, we show that our competitive ratio of $1-Θ(1/(p\sqrt{m}))$ is tight for any $p =ω(1/\sqrt{m})$. That asymptotic optimality is possible with sample information highlights the significant advantage of running a test period for new resources. We demonstrate the efficacy of our proposed algorithm using a dataset that contains the number of COVID-19 related hospitalized patients across different age groups.

math.OC↗

arXiv2022

Weighted Maximum Entropy Inverse Reinforcement Learning

We study inverse reinforcement learning (IRL) and imitation learning (IM), the problems of recovering a reward or policy function from expert's demonstrated trajectories. We propose a new way to improve the learning process by adding a weight function to the maximum entropy framework, with the motivation of having the ability to learn and recover the stochasticity (or the bounded rationality) of the expert policy. Our framework and algorithms allow to learn both a reward (or policy) function and the structure of the entropy terms added to the Markov Decision Processes, thus enhancing the learning procedure. Our numerical experiments using human and simulated demonstrations and with discrete and continuous IRL/IM tasks show that our approach outperforms prior algorithms.

cs.LG↗

arXiv2022

On Provably Robust Meta-Bayesian Optimization

Bayesian optimization (BO) has become popular for sequential optimization of black-box functions. When BO is used to optimize a target function, we often have access to previous evaluations of potentially related functions. This begs the question as to whether we can leverage these previous experiences to accelerate the current BO task through meta-learning (meta-BO), while ensuring robustness against potentially harmful dissimilar tasks that could sabotage the convergence of BO. This paper introduces two scalable and provably robust meta-BO algorithms: robust meta-Gaussian process-upper confidence bound (RM-GP-UCB) and RM-GP-Thompson sampling (RM-GP-TS). We prove that both algorithms are asymptotically no-regret even when some or all previous tasks are dissimilar to the current task, and show that RM-GP-UCB enjoys a better theoretical robustness than RM-GP-TS. We also exploit the theoretical guarantees to optimize the weights assigned to individual previous tasks through regret minimization via online learning, which diminishes the impact of dissimilar tasks and hence further enhances the robustness. Empirical evaluations show that (a) RM-GP-UCB performs effectively and consistently across various applications, and (b) RM-GP-TS, despite being less robust than RM-GP-UCB both in theory and in practice, performs competitively in some scenarios with less dissimilar tasks and is more computationally efficient.

cs.LG↗

arXiv2022

Optimal Information Provision for Strategic Hybrid Workers

We study the problem of information provision by a strategic central planner who can publicly signal about an uncertain infectious risk parameter. Signalling leads to an updated public belief over the parameter, and agents then make equilibrium choices on whether to work remotely or in-person. The planner maintains a set of desirable outcomes for each realization of the uncertain parameter and seeks to maximize the probability that agents choose an acceptable outcome for the true parameter. We distinguish between stateless and stateful objectives. In the former, the set of desirable outcomes does not change as a function of the risk parameter, whereas in the latter it does. For stateless objectives, we reduce the problem to maximizing the probability of inducing mean beliefs that lie in intervals computable from the set of desirable outcomes. We derive the optimal signalling mechanism and show that it partitions the parameter domain into at most two intervals with the signals generated according to an interval-specific distribution. For the stateful case, we consider a practically relevant situation in which the planner can enforce in-person work capacity limits that progressively get more stringent as the risk parameter increases. We show that the optimal signalling mechanism for this case can be obtained by solving a linear program. We numerically verify the improvement in achieving desirable outcomes using our information design relative to no information and full information benchmarks.

cs.MA↗

arXiv2022

No-regret Learning in Price Competitions under Consumer Reference Effects

We study long-run market stability for repeated price competitions between two firms, where consumer demand depends on firms' posted prices and consumers' price expectations called reference prices. Consumers' reference prices vary over time according to a memory-based dynamic, which is a weighted average of all historical prices. We focus on the setting where firms are not aware of demand functions and how reference prices are formed but have access to an oracle that provides a measure of consumers' responsiveness to the current posted prices. We show that if the firms run no-regret algorithms, in particular, online mirror descent(OMD), with decreasing step sizes, the market stabilizes in the sense that firms' prices and reference prices converge to a stable Nash Equilibrium (SNE). Interestingly, we also show that there exist constant step sizesunder which the market stabilizes. We further characterize the rate of convergence to the SNE for both decreasing and constant OMD step sizes.

cs.GT↗

arXiv2022

Rectified Max-Value Entropy Search for Bayesian Optimization

Although the existing max-value entropy search (MES) is based on the widely celebrated notion of mutual information, its empirical performance can suffer due to two misconceptions whose implications on the exploration-exploitation trade-off are investigated in this paper. These issues are essential in the development of future acquisition functions and the improvement of the existing ones as they encourage an accurate measure of the mutual information such as the rectified MES (RMES) acquisition function we develop in this work. Unlike the evaluation of MES, we derive a closed-form probability density for the observation conditioned on the max-value and employ stochastic gradient ascent with reparameterization to efficiently optimize RMES. As a result of a more principled acquisition function, RMES shows a consistent improvement over MES in several synthetic function benchmarks and real-world optimization problems.

cs.LG↗