arXiv subjects

Houssam Nassif

Publications and source records attributed to Houssam Nassif.

At least 19 recordsLinked to original sources

arXiv2026

Beyond IPS: Reliable Counterfactual Evaluation in Multi-Stage Ad Systems without Logged Propensities

Offline evaluation of ad-ranking policies in multi-stage delivery systems is challenging because action propensities are often unavailable, limiting inverse propensity scoring (IPS). Reward-model-based estimators such as the Direct Method (DM) avoid propensities but can be biased when candidate policies induce impression distributions that differ from the logged data. We formalize DM-based counterfactual replay and propose mixture-weighted reward modeling, which reweights logged data toward a mixture of candidate-policy distributions using density ratios from a multiclass domain classifier. We bound each candidate's value-estimation error by overlap, cold-start, and replay terms, and derive an asymptotic rule that uses the cold-start mass to decide whether to trust offline selection or route candidates to online A/B testing. On an ads-delivery simulator and on production traffic from a large-scale CTR ranking system, the mixture-weighted reward model improves policy selection over its unweighted counterpart in both settings, with the largest gains at low overlap in simulation. Combined with a doubly robust correction, it attains the highest Top-1 accuracy in production and at low and medium overlap in simulation.

cs.IR↗

arXiv2026

Let Them Peek: Group Sequential Designs for A/B Testing

Randomized controlled trials, commonly known as A/B tests, are the standard mechanism for inferring causal effects of product innovations. Standard platforms evaluate these tests with fixed-horizon procedures that control the false positive rate at a predetermined time, forcing teams to wait until the end even when early data strongly indicates success or failure. Unfortunately, continuous monitoring ("peeking") invalidates these guarantees, while always-valid inference is overly conservative under a strict deadline, and group sequential designs (GSD) have received limited traction in large-scale experimentation due to operational barriers: terminal-rule preservation, autocorrelation, latent effect-size distributions, calendar-duration optimization. We fill in this gap by proposing a Predictive Probability of Success (PPoS) group sequential framework that is autocorrelation-aware and duration-optimal while preserving the platform's fixed-horizon terminal rule. Our key insight is that PPoS thresholds map to closed-form lift boundaries that converge to the standard test at the horizon by construction, admit an effective-sample-size correction estimated from historical A/A tests, and suffice to attain the likelihood-ratio efficiency floor. Experimentally on online A/A and A/B experiments, we show that the proposed policy reduces expected duration by 43.1% (7.97 days vs. 14-day baseline), increasing effective platform capacity by 76%, while retaining the guarantees on FPR and power.

stat.AP↗

arXiv2026

Halve-Then-Greedy: Adaptive Sampling for Posterior Success with Near-Optimal Instance Dependence

We study fixed-budget adaptive experimentation aimed at maximizing the probability of obtaining sufficient posterior evidence that a recommended design's mean performance exceeds a target. Unlike best-arm identification, this objective does not require finding the best design. For Gaussian bandits with a Gaussian prior, we propose \emph{Halve-Then-Greedy} (HTG), which combines a large initial balanced allocation, successive halving, and posterior-greedy sampling. We prove instance-dependent, finite-budget exponential bounds on posterior-failure probability that capture both separation from unfavorable arms and the presence of multiple favorable arms. On one-positive-arm families, we establish an asymptotic sample-complexity lower bound that HTG matches up to a logarithmic factor. We further analyze uniform sampling and sequential halving, revealing regimes where they require more samples than HTG by linear and logarithmic factors, respectively. Simulations illustrate HTG's sample-efficiency advantages and their dependence on instance structure.

cs.LG↗

arXiv2026

Neutral Is Not Free: Evaluating Downside Risk in Neutral Launches

Evaluating "neutral launches" (e.g., infrastructure upgrades) using traditional confidence interval overlap is flawed: it is dangerously permissive with scarce data and excessively restrictive with abundant data. To resolve this, this paper introduces Expected Bayesian Loss (EBL), a continuous metric that quantifies both the probability and expected severity of metric degradation. Computable directly from standard frequentist estimates, EBL explicitly penalizes empirical noise and high-variance experiments. Validated against expert decisions, EBL provides experimentation platforms with a rigorous, tunable guardrail that aligns statistical safety with institutional risk appetite.

stat.AP↗

arXiv2026

Estimating the True Effect Size Distribution with SIMEX

Large-scale online experimentation produces noisy effect estimates, which can overstate gains and complicate decisions about launches and testing policies. We propose a nonparametric method based on SIMulation-EXtrapolation (SIMEX) to estimate the latent distribution of true effects from estimated average treatment effects with known variances. The method evaluates quantiles after adding progressively more simulated measurement noise and extrapolates the resulting inverse cumulative distribution function to the zero-noise setting while enforcing monotonicity of the quantiles. In a synthetic example with normally distributed true effects and measurement error, the method recovers the underlying effect distribution and performs nearly as well as a parametric empirical Bayes normal means approach. This provides a flexible way to characterize effect-size distributions without fully specifying a parametric model.

stat.ME↗

arXiv2026

Impression Share Prediction: An Offline Evaluation Task for Ranking Systems

Offline evaluation is a major gateway before online evaluation of ranking models in A/B testing. Standard offline metrics measure predictive accuracy, but are only a surrogate for downstream utility: a model can improve them while redistributing impressions across objective buckets in ways that degrade downstream utility. No offline method surfaces these impression share shifts before online evaluation. We propose \emph{impression share prediction} as an offline evaluation task: given a candidate ranking model, predict the distribution of impressions it would produce across objective buckets - impressions grouped by optimization goal (e.g., click, video view). The task is inherently counterfactual, since the candidate has never served live traffic. We propose a structural causal model of how model predictions and delivery capacity jointly determine impression allocation, and show the counterfactual effect is identified from observational data. Building on this, we develop a statistical learning framework that predicts impression shares from a candidate's early-interaction confidence signals and current system state, trained on historical data. On data from multiple ranking model families, a Random Forest reduces L1 error by 49\% over a constant baseline for models seen during training. For held-out models, evaluated by time since first appearance, the first hour is the closest analog to true online evaluation and the hardest: the Random Forest falls below the baseline because the capacity state still reflects the prior model. An encoder-conditioned architecture that simulates a 2-hour rollout over recent auction dynamics recovers $+$22\% L1 in this regime.

cs.IR↗

arXiv2026

Fixed Budget is No Harder Than Fixed Confidence in Best-Arm Identification up to Logarithmic Factors

The best-arm identification (BAI) problem is one of the most fundamental problems in interactive machine learning, which has two flavors: the fixed-budget setting (FB) and the fixed-confidence setting (FC). For $K$-armed bandits with a unique best arm, the optimal sample complexities for both settings have been settled down, and they match up to logarithmic factors. This prompts an interesting research question about the generic, potentially structured BAI problems: is FB harder than FC or the other way around? In this paper, we show that FB is no harder than FC up to logarithmic factors. We do this constructively: we propose a novel algorithm called FC2FB (fixed confidence to fixed budget), which is a meta algorithm that takes in an FC algorithm $\mathcal{A}$ and turn it into an FB algorithm. We prove that FC2FB enjoys a sample complexity that matches, up to logarithmic factors, that of the sample complexity of $\mathcal{A}$. This means that the optimal FC sample complexity is an upper bound of the optimal FB sample complexity up to logarithmic factors. Our result not only reveals a fundamental relationship between FB and FC, but also has a significant implication: FC2FB combined with existing state-of-the-art FC algorithms leads to improved sample complexity for a number of FB problems.

stat.ML↗

arXiv2026

Breaking the Winner's Curse with Bayesian Hybrid Shrinkage

The widespread adoption of randomized controlled trials (A/B Tests) for decision-making has introduced a pervasive "Winner's Curse": experiments selected for launch often exhibit upwardly biased effect estimates and invalid confidence intervals. This selection bias leads to over-optimistic impact projections and undermines decision-making, particularly in low-power regimes. We propose Bayesian Hybrid Shrinkage (BHS), an empirical Bayes (EB) framework that leverages data-driven priors to mitigate selection bias and provides accurate uncertainty quantification. Unlike traditional EB methods that apply uniform shrinkage, BHS introduces an experiment-specific "local" shrinkage factor that incorporates individual experiment characteristics, improving robustness against prior misspecification. We also derive a closed-form inference strategy designed for high-throughput production environments. Extensive simulations and real-world evaluations at Meta Platforms demonstrate that BHS outperforms existing methods in terms of bias reduction and interval coverage, even under substantial violations of modeling assumptions.

stat.ME↗

arXiv2025

Evaluating Variance Estimates with Relative Efficiency

Experimentation platforms in industry must often deal with customer trust issues. Platforms must prove the validity of their claims as well as catch issues that arise. As a central quantity estimated by experimentation platforms, the validity of confidence intervals is of particular concern. To ensure confidence intervals are reliable, we must understand and diagnose when our variance estimates are biased or noisy, or when the confidence intervals may be incorrect. A common method for this is A/A testing, in which both the control and test arms receive the same treatment. One can then test if the empirical false positive rate (FPR) deviates substantially from the target FPR over many tests. However, this approach turns each A/A test into a simple binary random variable. It is an inefficient estimate of the FPR as it throws away information about the magnitude of each experiment result. We show how to empirically evaluate the effectiveness of statistics that monitor the variance estimates that partly dictate a platform's statistical reliability. We also show that statistics other than empirical FPR are more effective at detecting issues. In particular, we propose a $t^2$-statistic that is more sample efficient.

stat.ME↗

arXiv2025

Breaking the Winner's Curse with Bayesian Hybrid Shrinkage

A 'Winner's Curse' arises in large-scale online experimentation platforms when the same experiments are used to both select treatments and evaluate their effects. In these settings, classical difference-in-means estimators of treatment effects are upwardly biased and conventional confidence intervals are rendered invalid. The bias scales with the magnitude of sampling variability and the selection threshold, and inversely with the treatment's true effect size. We propose a new Bayesian approach that incorporates experiment-specific 'local shrinkage' factors that mitigate sensitivity to the choice of prior and improve robustness to assumption violations. We demonstrate how the associated posterior distribution can be estimated without numerical integration techniques, making it a practical choice for at-scale deployment. Through simulation, we evaluate the performance of our approach under various scenarios and find that it performs well even when assumptions about the sampling and selection processes are violated. In an empirical evaluation, our approach demonstrated superior performance over alternative methods, providing more accurate estimates with well-calibrated uncertainty quantification.

stat.ME↗

arXiv2025

Bayesian Predictive Probabilities for Online Experimentation

The widespread adoption of online randomized controlled experiments (A/B Tests) for decision-making has created ongoing capacity constraints which necessitate interim analyses. As a consequence, platform users are increasingly motivated to use ad-hoc means of optimizing limited resources via peeking. Such processes, however, are error prone and often misaligned with end-of-experiment outcomes (e.g., inflated type-I error). We introduce a system based on Bayesian Predictive Probabilities that enable us to perform interim analyses without compromising fidelity of the experiment; This idea has been widely utilized in applications outside of the technology domain to more efficiently make decisions in experiments. Motivated by at-scale deployment within an experimentation platform, we demonstrate how predictive probabilities can be estimated without numerical integration techniques and recommend systems to study its properties at scale as an ongoing health check, along with system design recommendations - all on experiment data from Instagram - to demonstrate practical benefits that it enables.

stat.AP↗

arXiv2025

On Neural Networks as Infinite Tree-Structured Probabilistic Graphical Models

Deep neural networks (DNNs) lack the precise semantics and definitive probabilistic interpretation of probabilistic graphical models (PGMs). In this paper, we propose an innovative solution by constructing infinite tree-structured PGMs that correspond exactly to neural networks. Our research reveals that DNNs, during forward propagation, indeed perform approximations of PGM inference that are precise in this alternative PGM structure. Not only does our research complement existing studies that describe neural networks as kernel machines or infinite-sized Gaussian processes, it also elucidates a more direct approximation that DNNs make to exact inference in PGMs. Potential benefits include improved pedagogy and interpretation of DNNs, and algorithms that can merge the strengths of PGMs and DNNs.

stat.ML↗

arXiv2024

Counterfactual Evaluation of Ads Ranking Models through Domain Adaptation

We propose a domain-adapted reward model that works alongside an Offline A/B testing system for evaluating ranking models. This approach effectively measures reward for ranking model changes in large-scale Ads recommender systems, where model-free methods like IPS are not feasible. Our experiments demonstrate that the proposed technique outperforms both the vanilla IPS method and approaches using non-generalized reward models.

cs.IR↗

arXiv2024

Best of Three Worlds: Adaptive Experimentation for Digital Marketing in Practice

Adaptive experimental design (AED) methods are increasingly being used in industry as a tool to boost testing throughput or reduce experimentation cost relative to traditional A/B/N testing methods. However, the behavior and guarantees of such methods are not well-understood beyond idealized stationary settings. This paper shares lessons learned regarding the challenges of naively using AED systems in industrial settings where non-stationarity is prevalent, while also providing perspectives on the proper objectives and system specifications in such settings. We developed an AED framework for counterfactual inference based on these experiences, and tested it in a commercial environment.

cs.LG↗

arXiv2024

Estimation of subsidiary performance metrics under optimal policies

In policy learning, the goal is typically to optimize a primary performance metric, but other subsidiary metrics often also warrant attention. This paper presents two strategies for evaluating these subsidiary metrics under a policy that is optimal for the primary one. The first relies on a novel margin condition that facilitates Wald-type inference. Under this and other regularity conditions, we show that the one-step corrected estimator is efficient. Despite the utility of this margin condition, it places strong restrictions on how the subsidiary metric behaves for nearly optimal policies, which may not hold in practice. We therefore introduce alternative, two-stage strategies that do not require a margin condition. The first stage constructs a set of candidate policies and the second builds a uniform confidence interval over this set. We provide numerical simulations to evaluate the performance of these methods in different scenarios.

math.ST↗

arXiv2023

Experimental Designs for Heteroskedastic Variance

Most linear experimental design problems assume homogeneous variance although heteroskedastic noise is present in many realistic settings. Let a learner have access to a finite set of measurement vectors $\mathcal{X}\subset \mathbb{R}^d$ that can be probed to receive noisy linear responses of the form $y=x^{\top}θ^{\ast}+η$. Here $θ^{\ast}\in \mathbb{R}^d$ is an unknown parameter vector, and $η$ is independent mean-zero $σ_x^2$-sub-Gaussian noise defined by a flexible heteroskedastic variance model, $σ_x^2 = x^{\top}Σ^{\ast}x$. Assuming that $Σ^{\ast}\in \mathbb{R}^{d\times d}$ is an unknown matrix, we propose, analyze and empirically evaluate a novel design for uniformly bounding estimation error of the variance parameters, $σ_x^2$. We demonstrate the benefits of this method with two adaptive experimental design problems under heteroskedastic noise, fixed confidence transductive best-arm identification and level-set identification and prove the first instance-dependent lower bounds in these settings. Lastly, we construct near-optimal algorithms and demonstrate the large improvements in sample complexity gained from accounting for heteroskedastic variance in these designs empirically.

math.ST↗

arXiv2023

Neural Insights for Digital Marketing Content Design

In digital marketing, experimenting with new website content is one of the key levers to improve customer engagement. However, creating successful marketing content is a manual and time-consuming process that lacks clear guiding principles. This paper seeks to close the loop between content creation and online experimentation by offering marketers AI-driven actionable insights based on historical data to improve their creative process. We present a neural-network-based system that scores and extracts insights from a marketing content design, namely, a multimodal neural network predicts the attractiveness of marketing contents, and a post-hoc attribution method generates actionable insights for marketers to improve their content in specific marketing locations. Our insights not only point out the advantages and drawbacks of a given current content, but also provide design recommendations based on historical data. We show that our scoring model and insights work well both quantitatively and qualitatively.

cs.LG↗

arXiv2023

A Data-Driven State Aggregation Approach for Dynamic Discrete Choice Models

We study dynamic discrete choice models, where a commonly studied problem involves estimating parameters of agent reward functions (also known as "structural" parameters), using agent behavioral data. Maximum likelihood estimation for such models requires dynamic programming, which is limited by the curse of dimensionality. In this work, we present a novel algorithm that provides a data-driven method for selecting and aggregating states, which lowers the computational and sample complexity of estimation. Our method works in two stages. In the first stage, we use a flexible inverse reinforcement learning approach to estimate agent Q-functions. We use these estimated Q-functions, along with a clustering algorithm, to select a subset of states that are the most pivotal for driving changes in Q-functions. In the second stage, with these selected "aggregated" states, we conduct maximum likelihood estimation using a commonly used nested fixed-point algorithm. The proposed two-stage approach mitigates the curse of dimensionality by reducing the problem dimension. Theoretically, we derive finite-sample bounds on the associated estimation error, which also characterize the trade-off of computational complexity, estimation error, and sample complexity. We demonstrate the empirical performance of the algorithm in two classic dynamic discrete choice estimation applications.

cs.LG↗