arXiv subjects

Benjamin Heymann

Publications and source records attributed to Benjamin Heymann.

At least 19 recordsLinked to original sources

arXiv2026

An Asymptotic Analysis of the Shapley Value for Dataset Valuation

We propose an asymptotic analysis of the Shapley value in a dataset valuation setting in which utilities are modeled as smooth functionals of empirical distributions via reproducing kernel Hilbert space (RKHS) mean embeddings. We prove that, despite its combinatorial definition, the Shapley value of a data source is asymptotically captured by a simple leading term. This term can be interpreted as the first-order contribution of a dataset relative to the surrounding data population. It also identifies the scale of the Shapley value as the number of data sources grows and provides a framework for analyzing existing Shapley value estimators. Moreover, for practitioners working with large numbers of datasets, the leading term becomes a tractable reference against which Shapley value approximations can be benchmarked.

cs.GT↗

arXiv2026

An empirical study of Fictitious Play for estimating Nash equilibria in first-price auctions with correlated values

This study concerns the computation of the Nash equilibria of first-price auctions with correlated values. Although some equilibrium computation methods exist for auctions with independent values, the correlation of bidders' values introduces significant complications that render the existing methods unsatisfactory. Our empirical contribution is a step towards filling this gap. We report surprisingly good numerical convergence of Fictitious Play toward an $\varepsilon$-equilibrium for an extensive set of instances. By doing so, we extend the insights of [39] to the correlated setting. These preliminary results call for further investigations into the properties of fictitious play algorithms on first-price auctions. 1. since the context is clear, we will use the term Nash equilibrium, or just equilibrium in this article

cs.GT↗

arXiv2026

Learning to Bid in Repeated Second-Price Auctions with Dynamic Values and Aggregated Feedback

We study the problem of learning to bid when the bidder's value is dynamic, i.e., when the current value depends on past outcomes. Specifically, we consider a bidder participating in repeated second-price auctions whose value depends on the time elapsed since their last successful bid, with auctions arriving in continuous time and only aggregated feedback revealed at the end of the horizon. Such a bidder must (1) balance the immediate benefit of winning the current auction against its impact on future values and (2) learn unknown environmental parameters. We derive regret bounds for a class of learning methods that combine plug-in estimators with a differential-equation characterization of the optimal policy, and show that a specific confidence bound algorithm learns the optimal policy with a near optimal regret of $\widetilde{O}(\log N)$ for piecewise linear primitives, and $\widetilde{O}(N^{1/3})$ for general, smooth primitives, achieving these regrets without explicit randomization. These theoretical results are supported by numerical experiments.

cs.LG↗

arXiv2026

RecoAtlas: From Semantic Plausibility to Set-Level Utility in LLM Recommendation Agents

LLM recommendation agents increasingly produce structured recommendation reports: sets of items accompanied by natural-language justifications. Yet existing evaluations often reduce this setting to reranking small shortlisted candidate sets or judge reports mainly by semantic plausibility. We introduce Recommendation Atlas (Agentic Tool-Level Assessment for Shopping), or RecoAtlas, a benchmark and toolkit for evaluating shopping agents with behavior-grounded metrics. RecoAtlas complements held-out interaction metrics with learned utility proxies for relevance, complementarity, and diversity derived from interaction data, while separately measuring semantic coherence and explanation quality. Its controlled tool environment exposes agents to either semantic, behavior-aligned, or faulty tools, enabling diagnosis of whether performance gains arise from stronger reasoning, better signals, or more effective tool-use policies. Across controlled experiments, we show that RecoAtlas exhibits key properties of a meaningful benchmark for agentic systems: performance scales with model capacity and test-time compute, improves with stronger and better-aligned tools, degrades under noisy or misaligned signals, and reveals that semantic plausibility does not necessarily capture behavior-grounded utility. RecoAtlas provides a foundation for developing and evaluating shopping assistants that optimize not only for plausible recommendations, but also for coherent, behaviorally grounded recommendation sets.

cs.IR↗

arXiv2025

Shapley-based Data Valuation for LLM Alignment via Sequential Preference Optimization

Data valuation is a natural framework for understanding which preference datasets matter most when aligning a Large Language Model (LLM) using multiple sources. The standard game-theoretic approach assigns each dataset a contribution score via the Shapley value. In practice, however, Shapley-based valuation is computationally prohibitive because it requires fine-tuning a separate model for every possible coalition of preference datasets, i.e., an exponential number of alignments. We address this challenge for a broad family of preference-optimization objectives, including DPO and IPO, that learn directly from log-policy ratios with respect to a reference policy. We introduce Sequential Preference Optimization, an offline procedure that applies existing preference optimization methods sequentially, source by source, updating the current policy after each dataset. Under exact optimization, this procedure yields an additive composition rule in reward space and an equivalent arithmetic composition rule in policy space. This observation enables an efficient approximation of the Shapley value: we train one model per preference dataset and reconstruct coalition policies at inference time from the singleton models, reducing the required alignments from exponential to linear in the number of sources. Leveraging this property, we compute Shapley values for several real-world preference datasets and reveal how each source drives model alignment.

cs.LG↗

arXiv2025

Side-by-side first-price auctions with imperfect bidders

We model a procurement scenario in which two \textit{imperfect} bidders act simultaneously on behalf of a single buyer, a configuration common in display advertising and referred to as \textit{side-by-side bidding} but largely unexplored in theory. We prove that the iterated best response algorithm converges to an equilibrium under standard distributional assumptions and provide sufficient condition for uniqueness. Beyond establishing existence and convergence, our analysis provides a tractable numerical method for quantitative studies of side-by-side procurement.

cs.GT↗

arXiv2025

Counterfactual simulations for large scale systems with burnout variables

We consider large-scale systems influenced by burnout variables - state variables that start active, shape dynamics, and irreversibly deactivate once certain conditions are met. Simulating what-if scenarios in such systems is computationally demanding, as alternative trajectories often require sequential processing, which does not scale very well. This challenge arises in settings like online advertising, because of campaigns budgets, complicating counterfactual analysis despite rich data availability. We introduce a new type of algorithms based on what we refer to as uncertainty relaxation, that enables efficient parallel computation, significantly improving scalability for counterfactual estimation in systems with burnout variables.

cs.DC↗

arXiv2025

Non-Linear Counterfactual Aggregate Optimization

We consider the problem of directly optimizing a non-linear function of an outcome, where this outcome itself is the sum of many small contributions. The non-linearity of the function means that the problem is not equivalent to the maximization of the expectation of the individual contribution. By leveraging the concentration properties of the sum of individual outcomes, we derive a scalable descent algorithm that directly optimizes for our stated objective. This allows for instance to maximize the probability of successful A/B test, for which it can be wiser to target a success criterion, such as exceeding a given uplift, rather than chasing the highest expected payoff.

stat.ML↗

arXiv2025

Offline Contextual Bandit with Counterfactual Sample Identification

In production systems, contextual bandit approaches often rely on direct reward models that take both action and context as input. However, these models can suffer from confounding, making it difficult to isolate the effect of the action from that of the context. We present \emph{Counterfactual Sample Identification}, a new approach that re-frames the problem: rather than predicting reward, it learns to recognize which action led to a successful (binary) outcome by comparing it to a counterfactual action sampled from the logging policy under the same context. The method is theoretically grounded and consistently outperforms direct models in both synthetic experiments and real-world deployments.

cs.LG↗

arXiv2025

Confounding is a Pervasive Problem in Real World Recommender Systems

Unobserved confounding arises when an unmeasured feature influences both the treatment and the outcome, leading to biased causal effect estimates. This issue undermines observational studies in fields like economics, medicine, ecology or epidemiology. Recommender systems leveraging fully observed data seem not to be vulnerable to this problem. However many standard practices in recommender systems result in observed features being ignored, resulting in effectively the same problem. This paper will show that numerous common practices such as feature engineering, A/B testing and modularization can in fact introduce confounding into recommendation systems and hamper their performance. Several illustrations of the phenomena are provided, supported by simulation studies with practical suggestions about how practitioners may reduce or avoid the affects of confounding in real systems.

cs.LG↗

arXiv2025

Adaptive Preference Aggregation

AI alignment, the challenge of ensuring AI systems act in accordance with human values, has emerged as a critical problem in the development of systems such as foundation models and recommender systems. Still, the current dominant approach, reinforcement learning with human feedback (RLHF) faces known theoretical limitations in aggregating diverse human preferences. Social choice theory provides a framework to aggregate preferences, but was not developed for the multidimensional applications typical of AI. Leveraging insights from a recently published urn process, this work introduces a preference aggregation strategy that adapts to the user's context and that inherits the good properties of the maximal lottery, a Condorcet-consistent solution concept.

cs.AI↗

arXiv2025

On the Impact of the Utility in Semivalue-based Data Valuation

Semivalue-based data valuation uses cooperative-game theory intuitions to assign each data point a value reflecting its contribution to a downstream task. Still, those values depend on the practitioner's choice of utility, raising the question: How robust is semivalue-based data valuation to changes in the utility? This issue is critical when the utility is set as a trade-off between several criteria and when practitioners must select among multiple equally valid utilities. We address this by introducing the notion of a dataset's spatial signature: given a semivalue, we embed each data point into a lower-dimensional space in which any utility becomes a linear functional, making the data valuation framework amenable to a simpler geometric picture. Building on this, we propose a practical methodology centered on an explicit robustness metric that informs practitioners whether and by how much their data valuation results will shift as the utility changes. We validate this approach across diverse datasets and semivalues, demonstrating strong agreement with rank-correlation analyses and offering analytical insight into how choosing a semivalue can amplify or diminish robustness.

cs.AI↗

arXiv2024

Learning in Games with Progressive Hiding

When learning to play an imperfect information game, it is often easier to first start with the basic mechanics of the game rules. For example, one can play several example rounds with private cards revealed to all players to better understand the basic actions and their effects. Building on this intuition, this paper introduces {\it progressive hiding}, an algorithm that balances learning the basic mechanics of an imperfect information game and satisfying the information constraints. Progressive hiding is inspired by methods from stochastic multistage optimization, such as scenario decomposition and progressive hedging. We prove that it enables the adaptation of counterfactual regret minimization to games where perfect recall is not satisfied. Numerical experiments illustrate that progressive hiding produces notable improvements in several settings.

cs.GT↗

arXiv2024

A pragmatic policy learning approach to account for users' fatigue in repeated auctions

Online advertising banners are sold in real-time through auctions.Typically, the more banners a user is shown, the smaller the marginalvalue of the next banner for this user is. This fact can be detected bybasic ML models, that can be used to predict how previously won auctionsdecrease the current opportunity value. However, learning is not enough toproduce a bid that correctly accounts for how winning the current auctionimpacts the future values. Indeed, a policy that uses this prediction tomaximize the expected payoff of the current auction could be dubbedimpatient because such policy does not fully account for the repeatednature of the auctions. Under this perspective, it seems that most biddersin the literature are impatient. Unsurprisingly, impatience induces a cost.We provide two empirical arguments for the importance of this cost ofimpatience. First, an offline counterfactual analysis and, second, a notablebusiness metrics improvement by mitigating the cost of impatience withpolicy learning

cs.GT↗

arXiv2023

Maximizing the Success Probability of Policy Allocations in Online Systems

The effectiveness of advertising in e-commerce largely depends on the ability of merchants to bid on and win impressions for their targeted users. The bidding procedure is highly complex due to various factors such as market competition, user behavior, and the diverse objectives of advertisers. In this paper we consider the problem at the level of user timelines instead of individual bid requests, manipulating full policies (i.e. pre-defined bidding strategies) and not bid values. In order to optimally allocate policies to users, typical multiple treatments allocation methods solve knapsack-like problems which aim at maximizing an expected value under constraints. In the industrial contexts such as online advertising, we argue that optimizing for the probability of success is a more suited objective than expected value maximization, and we introduce the SuccessProbaMax algorithm that aims at finding the policy allocation which is the most likely to outperform a fixed reference policy. Finally, we conduct comprehensive experiments both on synthetic and real-world data to evaluate its performance. The results demonstrate that our proposed algorithm outperforms conventional expected-value maximization algorithms in terms of success rate.

cs.IR↗

arXiv2023

Some bidding games converging to their unique pure equilibrium

We introduce a class of Bayesian bidding games for which we prove that the set of pure Nash equilibria is a (non-empty) sublattice and we give a sufficient condition for uniqueness that is often verified in the context of markets with inelastic demand. We propose a dynamic that converges to the extrema of the equilibrium set and derive a scheme to compute the extreme Nash equilibria.

cs.GT↗

arXiv2023

Repeated Bidding with Dynamic Value

We consider a repeated auction where the buyer's utility for an item depends on the time that elapsed since his last purchase. We present an algorithm to build the optimal bidding policy, and then, because optimal might be impractical, we discuss the cost for the buyer of limiting himself to shading policies.

econ.TH↗

arXiv2023

DU-Shapley: A Shapley Value Proxy for Efficient Dataset Valuation

We consider the dataset valuation problem, that is, the problem of quantifying the incremental gain, to some relevant pre-defined utility of a machine learning task, of aggregating an individual dataset to others. The Shapley value is a natural tool to perform dataset valuation due to its formal axiomatic justification, which can be combined with Monte Carlo integration to overcome the computational tractability challenges. Such generic approximation methods, however, remain expensive in some cases. In this paper, we exploit the knowledge about the structure of the dataset valuation problem to devise more efficient Shapley value estimators. We propose a novel approximation, referred to as discrete uniform Shapley, which is expressed as an expectation under a discrete uniform distribution with support of reasonable size. We justify the relevancy of the proposed framework via asymptotic and non-asymptotic theoretical guarantees and illustrate its benefits via an extensive set of numerical experiments.

cs.AI↗