arXiv subjects

Joseph J. Williams

Publications and source records attributed to Joseph J. Williams.

6 recordsLinked to original sources

arXiv2026

Algorithms for Adaptive Experiments that Trade-off Statistical Analysis with Reward: Combining Uniform Random Assignment and Reward Maximization

Traditional randomized A/B experiments assign arms with uniform random (UR) probability, such as 50/50 assignment to two versions of a website to discover whether one version engages users more. To more quickly and automatically use data to benefit users, multi-armed bandit algorithms such as Thompson Sampling (TS) have been advocated. While TS is interpretable and incorporates the randomization key to statistical inference, it can cause biased estimates and increase false positives and false negatives in detecting differences in arm means. We introduce a more Statistically Sensitive algorithm, TS-PostDiff (Posterior Probability of Small Difference), that mixes TS with traditional UR by using an additional adaptive step, where the probability of using UR (vs TS) is proportional to the posterior probability that the difference in arms is small. This allows an experimenter to define what counts as a small difference, below which a traditional UR experiment can obtain informative data for statistical inference at low cost, and above which using more TS to maximize user benefits is key. We evaluate TS-PostDiff against UR, TS, and two other TS variants designed to improve statistical inference. We consider results for the common two-armed experiment across a range of settings inspired by real-world applications. Our results provide insight into when and why TS-PostDiff or alternative approaches provide better tradeoffs between benefiting users (reward) and statistical inference (false positive rate and power). TS-PostDiff's adaptivity helps efficiently reduce false positives and increase statistical power when differences are small, while increasing reward more when differences are large. The work highlights important considerations for future Statistically Sensitive algorithm development that balances reward and statistical analysis in adaptive experimentation.

cs.LG↗

arXiv2026

RIE-Greedy: Regularization-Induced Exploration for Contextual Bandits

Real-world contextual bandit problems with complex reward models are often tackled with iteratively trained models, such as boosting trees. However, it is difficult to directly apply simple and effective exploration strategies--such as Thompson Sampling or UCB--on top of those black-box estimators. Existing approaches rely on sophisticated assumptions or intractable procedures that are hard to verify and implement in practice. In this work, we explore the use of an exploration-free (pure-greedy) action selection strategy, that exploits the randomness inherent in model fitting process as an intrinsic source of exploration. More specifically, we note that the stochasticity in cross-validation based regularization process can naturally induce Thompson Sampling-like exploration. We show that this regularization-induced exploration is theoretically equivalent to Thompson Sampling in the two-armed bandit case and empirically leads to reliable exploration in large-scale business environments compared to benchmark methods such as epsilon-greedy and other state-of-the-art approaches. Overall, our work reveals how regularized estimator training itself can induce effective exploration, offering both theoretical insight and practical guidance for contextual bandit design.

stat.ML↗

arXiv2026

A Statistically Reliable Optimization Framework for Bandit Experiments in Scientific Discovery

Scientific experimentation is largely driven by statistical hypothesis testing to determine significant differences in interventions. Traditionally, experimenters allocate samples uniformly between each intervention. However, such an approach may lead to suboptimal outcomes - multi-armed bandits (MABs) addresses this problem by allocating samples adaptively to maximize outcomes. Yet, two challenges have hindered the use of MABs in scientific domains. First, common hypothesis tests (e.g., $t$-tests) become invalid under adaptive sampling without correction, leading to inflated type~I and type~II errors. This is an understudied problem, and prior solutions suffer from issues such as low statistical power which prevent adoption in many practical settings. Second, practitioners must explicitly balance cumulative reward with statistical efficiency, yet no general methodology exists to quantify this trade-off across algorithms. In this paper, we study assumption modification and critical region correction approaches for hypothesis testing that enable common tests to be applied to adaptively collected data. We provide heuristic justification for its power efficiency and show in simulation that it achieves higher power than existing approaches. Further, we derive a theoretically and practically motivated objective function for adaptive experiment evaluation, which we integrate into a unified experimental framework. Our framework asks experimenters to specify an experiment extension cost for their problem, and based on that enables our proposed optimization procedure to select the bandit algorithm that best balances reward and power in their setting. We show that our approach enables practitioners to improve outcomes with only slightly more steps than uniform randomization, while retaining statistical validity.

stat.AP↗

arXiv2024

Data-Driven Discovery of a New Ginzburg-Landau Reduced-Order Model for Vortex Shedding

Vortex shedding is an important physical phenomenon observed across many spatial and temporal scales in fluids. Previous experimental and theoretical studies have established a hierarchy of local and global reduced-order models for vortex shedding based on the Stuart-Landau and Ginzburg-Landau equations. In this work, we employ data-driven methods to discover a new Landau variable for the complex Ginzburg-Landau equation (CGLE) for periodic two-dimensional vortex shedding past a cylinder. We first coarse grain vorticity field data from direct numerical simulations of the fluid by integrating over the vertical spatial dimension, and then time-delay embed this new variable to obtain phase information necessary for CGLE analysis. Finally, we use the sparse identification of nonlinear dynamics (SINDy) to learn an interpretable system of coupled real partial differential equations that balance model complexity and prediction error. We develop local homogeneous models in key regions of the wake, as well as global heterogeneous models that are parameterized by the streamwise coordinate across the entire wake. After computing the normal-form parameters from the discovered equations, we classify the different models and determine behavior and stability in the different regions of the wake, demonstrating the validity of these models across a range of spatiotemporal subdomains. Different dynamics are found to dominate at different stations within the wake. In addition to introducing a novel Landau variable for vortex shedding, this work may also help characterize other vortex shedding systems and inform the design of control schemes.

physics.flu-dyn↗

arXiv2023

Deep Learning Based Object Tracking in Walking Droplet and Granular Intruder Experiments

We present a deep-learning based tracking objects of interest in walking droplet and granular intruder experiments. In a typical walking droplet experiment, a liquid droplet, known as \textit{walker}, propels itself laterally on the free surface of a vibrating bath of the same liquid. This motion is the result of the interaction between the droplets and the surface waves generated by the droplet itself after each successive bounce. A walker can exhibit a highly irregular trajectory over the course of its motion, including rapid acceleration and complex interactions with the other walkers present in the same bath. In analogy with the hydrodynamic experiments, the granular matter experiments consist of a vibrating bath of very small solid particles and a larger solid \textit{intruder}. Like the fluid droplets, the intruder interacts with and travels the domain due to the waves of the bath but tends to move much slower and much less smoothly than the droplets. When multiple intruders are introduced, they also exhibit complex interactions with each other. We leverage the state-of-art object detection model YOLO and the Hungarian Algorithm to accurately extract the trajectory of a walker or intruder in real-time. Our proposed methodology is capable of tracking individual walker(s) or intruder(s) in digital images acquired from a broad spectrum of experimental settings and does not suffer from any identity-switch issues. Thus, the deep learning approach developed in this work could be used to automatize the efficient, fast and accurate extraction of observables of interests in walking droplet and granular flow experiments. Such extraction capabilities are critically enabling for downstream tasks such as building data-driven dynamical models for the coarse-grained dynamics and interactions of the objects of interest.

cs.CV↗

arXiv2021

Efficient Inference Without Trading-off Regret in Bandits: An Allocation Probability Test for Thompson Sampling

Using bandit algorithms to conduct adaptive randomised experiments can minimise regret, but it poses major challenges for statistical inference (e.g., biased estimators, inflated type-I error and reduced power). Recent attempts to address these challenges typically impose restrictions on the exploitative nature of the bandit algorithm$-$trading off regret$-$and require large sample sizes to ensure asymptotic guarantees. However, large experiments generally follow a successful pilot study, which is tightly constrained in its size or duration. Increasing power in such small pilot experiments, without limiting the adaptive nature of the algorithm, can allow promising interventions to reach a larger experimental phase. In this work we introduce a novel hypothesis test, uniquely based on the allocation probabilities of the bandit algorithm, and without constraining its exploitative nature or requiring a minimum experimental size. We characterise our $Allocation\ Probability\ Test$ when applied to $Thompson\ Sampling$, presenting its asymptotic theoretical properties, and illustrating its finite-sample performances compared to state-of-the-art approaches. We demonstrate the regret and inferential advantages of our approach, particularly in small samples, in both extensive simulations and in a real-world experiment on mental health aspects.

stat.ML↗