arXiv subjects

Aurelien Bibaut

Publications and source records attributed to Aurelien Bibaut.

8 recordsLinked to original sources

arXiv2026

Semiparametric inference on identification sets in choice modeling

In a discrete choice model, choice probabilities observed for a finite collection of choice sets may not identify a counterfactual choice probability under an unobserved choice set. We represent this counterfactual probability as a linear functional of a mixing distribution. Because the target is a functional of a distribution whose support is not restricted to a finite set, the parameter space is infinite-dimensional, while the data impose only finitely many moment restrictions. Therefore, observed choice probabilities need not point identify such a target. The identified set is defined as the set of target values compatible with observed choice probabilities. Rather than imposing conditions to ensure point identification, we characterize the identified set, and conduct inference on its lower and upper endpoints. We represent each endpoint as the value of a linear program over probability measures, and give conditions to obtain pathwise differentiability of the identification bounds. As a consequence, we are able to prove asymptotic normality of plug-in endpoint estimators. Finally, we provide an Expectation-Maximization-like algorithm for certifying membership of candidate values in the identified set and establish local convergence guarantees.

math.ST↗

arXiv2026

Functional Natural Policy Gradients

We propose a cross-fitted debiasing device for policy learning from offline data. A key consequence of the resulting learning principle is $\sqrt N$ regret even for policy classes with complexity greater than Donsker, provided a product-of-errors nuisance remainder is $O(N^{-1/2})$. The regret bound factors into a plug-in policy error factor governed by policy-class complexity and an environment nuisance factor governed by the complexity of the environment dynamics, making explicit how one may be traded against the other.

stat.ML↗

arXiv2025

Fast Best-in-Class Regret for Contextual Bandits

We study the problem of stochastic contextual bandits in the agnostic setting, where the goal is to compete with the best policy in a given class without assuming realizability or imposing model restrictions on losses or rewards. In this work, we establish the first fast rate for regret relative to the best-in-class policy. Our proposed algorithm updates the policy at every round by minimizing a pessimistic objective, defined as a clipped inverse-propensity estimate of the policy value plus a variance penalty. By leveraging entropy assumptions on the policy class and a H\"olderian error-bound condition (a generalization of the margin condition), we achieve fast best-in-class regret rates, including polylogarithmic rates in the parametric case. The analysis is driven by a sequential self-normalized maximal inequality for bounded martingale empirical processes, which yields uniform variance-adaptive confidence bounds and guarantees pessimism under adaptive data collection.

stat.ML↗

arXiv2025

Inverse Reinforcement Learning with Just Classification and a Few Regressions

Inverse reinforcement learning (IRL) aims to infer rewards from observed behavior, but rewards are not identified from the policy alone: many reward--value pairs can rationalize the same actions. Meaningful reward recovery therefore requires a normalization, yet existing normalized IRL methods often rely on anchor-action restrictions or specialized neural architectures. We study reward recovery in the maximum-entropy, or Gumbel-shock, model under a broad class of statewise affine normalizations, with anchor-action constraints as a special case. This yields Generalized Policy-to-$Q$-to-Reward (GenPQR), a modular procedure that estimates the behavior policy, evaluates its soft $Q$-function through the Bellman equation, and recovers the normalized reward. Both stages can be implemented with off-the-shelf classification and regression methods. We prove modular finite-sample guarantees under general function approximation, with separate policy-estimation and $Q$-estimation errors. As a concrete instantiation, we study GenPQR with fitted $Q$-evaluation, reducing IRL to policy estimation followed by regression. Experiments show that GenPQR matches or improves reward recovery relative to DeepPQR while remaining simpler and more modular. Compared with DeepPQR, our theory goes beyond anchor actions, accommodates large and continuous action spaces, makes coverage requirements explicit, and is not tied to a specific neural-network architecture or training procedure.

cs.LG↗

arXiv2025

Automatic Debiased Machine Learning for Smooth Functionals of Nonparametric M-Estimands

We develop a unified framework for automatic debiased machine learning (autoDML) for inference on a broad class of statistical parameters. The framework applies to any smooth functional of a nonparametric M-estimand, defined as the minimizer of a population risk over an infinite-dimensional linear space. Examples include counterfactual regression, quantile, and survival functions, as well as conditional average treatment effects. Rather than requiring manual derivation of influence functions, our approach automates the construction of debiased estimators using three ingredients: the gradient and Hessian of the loss function and a linear approximation of the target functional. Estimation reduces to solving two risk minimization problems, one for the M-estimand and one for a Riesz representer. The framework accommodates Neyman-orthogonal loss functions that depend on nuisance parameters and extends to vector-valued M-estimands through joint risk minimization. We characterize the efficient influence function and construct efficient autoDML estimators via one-step correction, targeted minimum loss estimation, and sieve-based plug-in methods. Under quadratic risk, these estimators satisfy double robustness for linear functionals. We further show that they are robust to mild misspecification of the M-estimand model, incurring only second-order bias. We illustrate the method by estimating long-term survival probabilities under a semiparametric two-parameter beta-geometric failure model.

stat.ME↗

arXiv2022

Near-Optimal Non-Parametric Sequential Tests and Confidence Sequences with Possibly Dependent Observations

Sequential tests and their implied confidence sequences, which are valid at arbitrary stopping times, promise flexible statistical inference and on-the-fly decision making. However, strong guarantees are limited to parametric sequential tests that under-cover in practice or concentration-bound-based sequences that over-cover and have suboptimal rejection times. In this work, we consider classic delayed-start normal-mixture sequential probability ratio tests, and we provide the first asymptotic type-I-error and expected-rejection-time guarantees under general non-parametric data generating processes, where the asymptotics are indexed by the test's burn-in time. The type-I-error results primarily leverage a martingale strong invariance principle and establish that these tests (and their implied confidence sequences) have type-I error rates asymptotically equivalent to the desired (possibly varying) $\alpha$-level. The expected-rejection-time results primarily leverage an identity inspired by It\^o's lemma and imply that, in certain asymptotic regimes, the expected rejection time is asymptotically equivalent to the minimum possible among $\alpha$-level tests. We show how to apply our results to sequential inference on parameters defined by estimating equations, such as average treatment effects. Together, our results establish these (ostensibly parametric) tests as general-purpose, non-parametric, and near-optimal. We illustrate this via numerical simulations and a real-data application to A/B testing at Netflix.

stat.ME↗

arXiv2021

Adaptive Sequential Design for a Single Time-Series

The current work is motivated by the need for robust statistical methods for precision medicine; as such, we address the need for statistical methods that provide actionable inference for a single unit at any point in time. We aim to learn an optimal, unknown choice of the controlled components of the design in order to optimize the expected outcome; with that, we adapt the randomization mechanism for future time-point experiments based on the data collected on the individual over time. Our results demonstrate that one can learn the optimal rule based on a single sample, and thereby adjust the design at any point t with valid inference for the mean target parameter. This work provides several contributions to the field of statistical precision medicine. First, we define a general class of averages of conditional causal parameters defined by the current context for the single unit time-series data. We define a nonparametric model for the probability distribution of the time-series under few assumptions, and aim to fully utilize the sequential randomization in the estimation procedure via the double robust structure of the efficient influence curve of the proposed target parameter. We present multiple exploration-exploitation strategies for assigning treatment, and methods for estimating the optimal rule. Lastly, we present the study of the data-adaptive inference on the mean under the optimal treatment rule, where the target parameter adapts over time in response to the observed context of the individual. Our target parameter is pathwise differentiable with an efficient influence function that is doubly robust - which makes it easier to estimate than previously proposed variations. We characterize the limit distribution of our estimator under a Donsker condition expressed in terms of a notion of bracketing entropy adapted to martingale settings.

math.ST↗

arXiv2021

Sequential causal inference in a single world of connected units

We consider adaptive designs for a trial involving N individuals that we follow along T time steps. We allow for the variables of one individual to depend on its past and on the past of other individuals. Our goal is to learn a mean outcome, averaged across the N individuals, that we would observe, if we started from some given initial state, and we carried out a given sequence of counterfactual interventions for $\tau$ time steps. We show how to identify a statistical parameter that equals this mean counterfactual outcome, and how to perform inference for this parameter, while adaptively learning an oracle design defined as a parameter of the true data generating distribution. Oracle designs of interest include the design that maximizes the efficiency for a statistical parameter of interest, or designs that mix the optimal treatment rule with a certain exploration distribution. We also show how to design adaptive stopping rules for sequential hypothesis testing. This setting presents unique technical challenges. Unlike in usual statistical settings where the data consists of several independent observations, here, due to network and temporal dependence, the data reduces to one single observation with dependent components. In particular, this precludes the use of sample splitting techniques. We therefore had to develop a new equicontinuity result and guarantees for estimators fitted on dependent data. We were motivated to work on this problem by the following two questions. (1) In the context of a sequential adaptive trial with K treatment arms, how to design a procedure to identify in as few rounds as possible the treatment arm with best final outcome? (2) In the context of sequential randomized disease testing at the scale of a city, how to estimate and infer the value of an optimal testing and isolation strategy?

math.ST↗