arXiv subjects

Nathan Kallus

Publications and source records attributed to Nathan Kallus.

At least 73 records · Page 4Linked to original sources

arXiv2024

Smooth Non-Stationary Bandits

In many applications of online decision making, the environment is non-stationary and it is therefore crucial to use bandit algorithms that handle changes. Most existing approaches are designed to protect against non-smooth changes, constrained only by total variation or Lipschitzness over time. However, in practice, environments often change {\em smoothly}, so such algorithms may incur higher-than-necessary regret. We study a non-stationary bandits problem where each arm's mean reward sequence can be embedded into a $β$-Hölder function, i.e., a function that is $(β-1)$-times Lipschitz-continuously differentiable. The non-stationarity becomes more smooth as $β$ increases. When $β=1$, this corresponds to the non-smooth regime, where \cite{besbes2014stochastic} established a minimax regret of $\tilde Θ(T^{2/3})$. We show the first separation between the smooth (i.e., $β\ge 2$) and non-smooth (i.e., $β=1$) regimes by presenting a policy with $\tilde O(k^{4/5} T^{3/5})$ regret on any $k$-armed, $2$-Hölder instance. We complement this result by showing that the minimax regret on the $β$-Hölder family of instances is $Ω(T^{(β+1)/(2β+1)})$ for any integer $β\ge 1$. This matches our upper bound for $β=2$ up to logarithmic factors. Furthermore, we validated the effectiveness of our policy through a comprehensive numerical study using real-world click-through rate data.

cs.LG↗

arXiv2024

Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processes

We study the evaluation of a policy under best- and worst-case perturbations to a Markov decision process (MDP), using transition observations from the original MDP, whether they are generated under the same or a different policy. This is an important problem when there is the possibility of a shift between historical and future environments, $\textit{e.g.}$ due to unmeasured confounding, distributional shift, or an adversarial environment. We propose a perturbation model that allows changes in the transition kernel densities up to a given multiplicative factor or its reciprocal, extending the classic marginal sensitivity model (MSM) for single time-step decision-making to infinite-horizon RL. We characterize the sharp bounds on policy value under this model $\unicode{x2013}$ $\textit{i.e.}$, the tightest possible bounds based on transition observations from the original MDP $\unicode{x2013}$ and we study the estimation of these bounds from such transition observations. We develop an estimator with several important guarantees: it is semiparametrically efficient, and remains so even when certain necessary nuisance functions, such as worst-case Q-functions, are estimated at slow, nonparametric rates. Our estimator is also asymptotically normal, enabling straightforward statistical inference using Wald confidence intervals. Moreover, when certain nuisances are estimated inconsistently, the estimator still provides valid, albeit possibly not sharp, bounds on the policy value. We validate these properties in numerical simulations. The combination of accounting for environment shifts from train to test (robustness), being insensitive to nuisance-function estimation (orthogonality), and addressing the challenge of learning from finite samples (inference) together leads to credible and reliable policy evaluation.

cs.AI↗

arXiv2024

Estimating Heterogeneous Treatment Effects by Combining Weak Instruments and Observational Data

Accurately predicting conditional average treatment effects (CATEs) is crucial in personalized medicine and digital platform analytics. Since the treatments of interest often cannot be directly randomized, observational data is leveraged to learn CATEs, but this approach can incur significant bias from unobserved confounding. One strategy to overcome these limitations is to leverage instrumental variables (IVs) as latent quasi-experiments, such as randomized intent-to-treat assignments or randomized product recommendations. This approach, on the other hand, can suffer from low compliance, $\textit{i.e.}$, IV weakness. Some subgroups may even exhibit zero compliance, meaning we cannot instrument for their CATEs at all. In this paper, we develop a novel approach to combine IV and observational data to enable reliable CATE estimation in the presence of unobserved confounding in the observational data and low compliance in the IV data, including no compliance for some subgroups. We propose a two-stage framework that first learns $\textit{biased}$ CATEs from the observational data, and then applies a compliance-weighted correction using IV data, effectively leveraging IV strength variability across covariates. We characterize the convergence rates of our method and validate its effectiveness through a simulation study. Additionally, we demonstrate its utility with real data by analyzing the heterogeneous effects of 401(k) plan participation on wealth.

stat.ME↗

arXiv2024

Reward Maximization for Pure Exploration: Minimax Optimal Good Arm Identification for Nonparametric Multi-Armed Bandits

In multi-armed bandits, the tasks of reward maximization and pure exploration are often at odds with each other. The former focuses on exploiting arms with the highest means, while the latter may require constant exploration across all arms. In this work, we focus on good arm identification (GAI), a practical bandit inference objective that aims to label arms with means above a threshold as quickly as possible. We show that GAI can be efficiently solved by combining a reward-maximizing sampling algorithm with a novel nonparametric anytime-valid sequential test for labeling arm means. We first establish that our sequential test maintains error control under highly nonparametric assumptions and asymptotically achieves the minimax optimal e-power, a notion of power for anytime-valid tests. Next, by pairing regret-minimizing sampling schemes with our sequential test, we provide an approach that achieves minimax optimal stopping times for labeling arms with means above a threshold, under an error probability constraint. Our empirical results validate our approach beyond the minimax setting, reducing the expected number of samples for all stopping times by at least 50% across both synthetic and real-world settings.

cs.LG↗

arXiv2024

Anytime-Valid Continuous-Time Confidence Processes for Inhomogeneous Poisson Processes

Motivated by monitoring the arrival of incoming adverse events such as customer support calls or crash reports from users exposed to an experimental product change, we consider sequential hypothesis testing of continuous-time inhomogeneous Poisson point processes. Specifically, we provide an interval-valued confidence process $C^α(t)$ over continuous time $t$ for the cumulative arrival rate $Λ(t) = \int_0^t λ(s) \mathrm{d}s$ with a continuous-time anytime-valid coverage guarantee $\mathbb{P}[Λ(t) \in C^α(t) \, \forall t >0] \geq 1-α$. We extend our results to compare two independent arrival processes by constructing multivariate confidence processes and a closed-form $e$-process for testing the equality of rates with a time-uniform Type-I error guarantee at a nominal $α$. We characterize the asymptotic growth rate of the proposed $e$-process under the alternative and show that it has power 1 when the average rates of the two Poisson process differ in the limit. We also observe a complementary relationship between our multivariate confidence process and the universal inference $e$-process for testing composite null hypotheses.

stat.ME↗

arXiv2024

On the role of surrogates in the efficient estimation of treatment effects with limited outcome data

In many experimental and observational studies, the outcome of interest is often difficult or expensive to observe, reducing effective sample sizes for estimating average treatment effects (ATEs) even when identifiable. We study how incorporating data on units for which only surrogate outcomes not of primary interest are observed can increase the precision of ATE estimation. We refrain from imposing stringent surrogacy conditions, which permit surrogates as perfect replacements for the target outcome. Instead, we supplement the available, albeit limited, observations of the target outcome with abundant observations of surrogate outcomes, without any assumptions beyond unconfounded treatment assignment and missingness and corresponding overlap conditions. To quantify the potential gains, we derive the difference in efficiency bounds on ATE estimation with and without surrogates, both when an overwhelming or comparable number of units have missing outcomes. We develop robust ATE estimation and inference methods that realize these efficiency gains. We empirically demonstrate the gains by studying long-term-earning effects of job training.

stat.ML↗

arXiv2024

Nonparametric Jackknife Instrumental Variable Estimation and Confounding Robust Surrogate Indices

Jackknife instrumental variable estimation (JIVE) is a classic method to leverage many weak instrumental variables (IVs) to estimate linear structural models, overcoming the bias of standard methods like two-stage least squares. In this paper, we extend the jackknife approach to nonparametric IV (NPIV) models with many weak IVs. Since NPIV characterizes the structural regression as having residuals projected onto the IV being zero, existing approaches minimize an estimate of the average squared projected residuals, but their estimates are biased under many weak IVs. We introduce an IV splitting device inspired by JIVE to remove this bias, and by carefully studying this split-IV empirical process we establish learning rates that depend on generic complexity measures of the nonparametric hypothesis class. We then turn to leveraging this for semiparametric inference on average treatment effects (ATEs) on unobserved long-term outcomes predicted from short-term surrogates, using historical experiments as IVs to learn this nonparametric predictive relationship even in the presence of confounding between short- and long-term observations. Using split-IV estimates of a debiasing nuisance, we develop asymptotically normal estimates for predicted ATEs, enabling inference.

math.ST↗

arXiv2024

Adjusting Regression Models for Conditional Uncertainty Calibration

Conformal Prediction methods have finite-sample distribution-free marginal coverage guarantees. However, they generally do not offer conditional coverage guarantees, which can be important for high-stakes decisions. In this paper, we propose a novel algorithm to train a regression function to improve the conditional coverage after applying the split conformal prediction procedure. We establish an upper bound for the miscoverage gap between the conditional coverage and the nominal coverage rate and propose an end-to-end algorithm to control this upper bound. We demonstrate the efficacy of our method empirically on synthetic and real-world datasets.

stat.ML↗

arXiv2024

Long-term Causal Inference Under Persistent Confounding via Data Combination

We study the identification and estimation of long-term treatment effects when both experimental and observational data are available. Since the long-term outcome is observed only after a long delay, it is not measured in the experimental data, but only recorded in the observational data. However, both types of data include observations of some short-term outcomes. In this paper, we uniquely tackle the challenge of persistent unmeasured confounders, i.e., some unmeasured confounders that can simultaneously affect the treatment, short-term outcomes and the long-term outcome, noting that they invalidate identification strategies in previous literature. To address this challenge, we exploit the sequential structure of multiple short-term outcomes, and develop three novel identification strategies for the average long-term treatment effect. We further propose three corresponding estimators and prove their asymptotic consistency and asymptotic normality. We finally apply our methods to estimate the effect of a job training program on long-term employment using semi-synthetic data. We numerically show that our proposals outperform existing methods that fail to handle persistent confounders.

stat.ME↗

arXiv2024

CSPI-MT: Calibrated Safe Policy Improvement with Multiple Testing for Threshold Policies

When modifying existing policies in high-risk settings, it is often necessary to ensure with high certainty that the newly proposed policy improves upon a baseline, such as the status quo. In this work, we consider the problem of safe policy improvement, where one only adopts a new policy if it is deemed to be better than the specified baseline with at least pre-specified probability. We focus on threshold policies, a ubiquitous class of policies with applications in economics, healthcare, and digital advertising. Existing methods rely on potentially underpowered safety checks and limit the opportunities for finding safe improvements, so too often they must revert to the baseline to maintain safety. We overcome these issues by leveraging the most powerful safety test in the asymptotic regime and allowing for multiple candidates to be tested for improvement over the baseline. We show that in adversarial settings, our approach controls the rate of adopting a policy worse than the baseline to the pre-specified error level, even in moderate sample sizes. We present CSPI and CSPI-MT, two novel heuristics for selecting cutoff(s) to maximize the policy improvement from baseline. We demonstrate through both synthetic and external datasets that our approaches improve both the detection rates of safe policies and the realized improvement, particularly under stringent safety requirements and low signal-to-noise conditions.

cs.LG↗

arXiv2024

Switching the Loss Reduces the Cost in Batch (Offline) Reinforcement Learning

We propose training fitted Q-iteration with log-loss (FQI-log) for batch reinforcement learning (RL). We show that the number of samples needed to learn a near-optimal policy with FQI-log scales with the accumulated cost of the optimal policy, which is zero in problems where acting optimally achieves the goal and incurs no cost. In doing so, we provide a general framework for proving small-cost bounds, i.e. bounds that scale with the optimal achievable cost, in batch RL. Moreover, we empirically verify that FQI-log uses fewer samples than FQI trained with squared loss on problems where the optimal policy reliably achieves the goal.

cs.LG↗

arXiv2024

Learning the Covariance of Treatment Effects Across Many Weak Experiments

When primary objectives are insensitive or delayed, experimenters may instead focus on proxy metrics derived from secondary outcomes. For example, technology companies often infer the long-term impacts of product interventions from their effects on short-term user engagement signals. We consider the meta-analysis of many historical experiments to learn the covariance of treatment effects on these outcomes, which can support the construction of such proxies. Even when experiments are plentiful, if treatment effects are weak, the covariance of estimated treatment effects across experiments can be highly biased. We overcome this with techniques inspired by weak instrumental variable analysis. We show that Limited Information Maximum Likelihood (LIML) learns a parameter equivalent to fitting total least squares to a transformation of the scatterplot of treatment effects, and that Jackknife Instrumental Variables Estimation (JIVE) learns another parameter computable from the average of Jackknifed covariance matrices across experiments. We also present a total covariance estimator for the latter estimand under homoskedasticity, which is equivalent to a $k$-class estimator. We show how these parameters can be used to construct unbiased proxy metrics under various structural models. Lastly, we discuss the real-world application of our methods at Netflix.

stat.ME↗

arXiv2024

Multi-Armed Bandits with Interference

Experimentation with interference poses a significant challenge in contemporary online platforms. Prior research on experimentation with interference has concentrated on the final output of a policy. The cumulative performance, while equally crucial, is less well understood. To address this gap, we introduce the problem of {\em Multi-armed Bandits with Interference} (MABI), where the learner assigns an arm to each of $N$ experimental units over a time horizon of $T$ rounds. The reward of each unit in each round depends on the treatments of {\em all} units, where the influence of a unit decays in the spatial distance between units. Furthermore, we employ a general setup wherein the reward functions are chosen by an adversary and may vary arbitrarily across rounds and units. We first show that switchback policies achieve an optimal {\em expected} regret $\tilde O(\sqrt T)$ against the best fixed-arm policy. Nonetheless, the regret (as a random variable) for any switchback policy suffers a high variance, as it does not account for $N$. We propose a cluster randomization policy whose regret (i) is optimal in {\em expectation} and (ii) admits a high probability bound that vanishes in $N$.

cs.LG↗

arXiv2024

Inferring the Long-Term Causal Effects of Long-Term Treatments from Short-Term Experiments

We study inference on the long-term causal effect of a continual exposure to a novel intervention, which we term a long-term treatment, based on an experiment involving only short-term observations. Key examples include the long-term health effects of regularly-taken medicine or of environmental hazards and the long-term effects on users of changes to an online platform. This stands in contrast to short-term treatments or "shocks," whose long-term effect can reasonably be mediated by short-term observations, enabling the use of surrogate methods. Long-term treatments by definition have direct effects on long-term outcomes via continual exposure, so surrogacy conditions cannot reasonably hold. We connect the problem with offline reinforcement learning, leveraging doubly-robust estimators to estimate long-term causal effects for long-term treatments and construct confidence intervals.

stat.AP↗

arXiv2024

Peeking with PEAK: Sequential, Nonparametric Composite Hypothesis Tests for Means of Multiple Data Streams

We propose a novel nonparametric sequential test for composite hypotheses for means of multiple data streams. Our proposed method, \emph{peeking with expectation-based averaged capital} (PEAK), builds upon the testing-by-betting framework and provides a non-asymptotic $α$-level test across any stopping time. Our contributions are two-fold: (1) we propose a novel betting scheme and provide theoretical guarantees on type-I error control, power, and asymptotic growth rate/$e$-power in the setting of a single data stream; (2) we introduce PEAK, a generalization of this betting scheme to multiple streams, that (i) avoids using wasteful union bounds via averaging, (ii) is a test of power one under mild regularity conditions on the sampling scheme of the streams, and (iii) reduces computational overhead when applying the testing-as-betting approaches for pure-exploration bandit problems. We illustrate the practical benefits of PEAK using both synthetic and real-world HeartSteps datasets. Our experiments show that PEAK provides up to an 85\% reduction in the number of samples before stopping compared to existing stopping rules for pure-exploration bandit problems, and matches the performance of state-of-the-art sequential tests while improving upon computational complexity.

stat.ME↗

arXiv2024

Reindex-Then-Adapt: Improving Large Language Models for Conversational Recommendation

Large language models (LLMs) are revolutionizing conversational recommender systems by adeptly indexing item content, understanding complex conversational contexts, and generating relevant item titles. However, controlling the distribution of recommended items remains a challenge. This leads to suboptimal performance due to the failure to capture rapidly changing data distributions, such as item popularity, on targeted conversational recommendation platforms. In conversational recommendation, LLMs recommend items by generating the titles (as multiple tokens) autoregressively, making it difficult to obtain and control the recommendations over all items. Thus, we propose a Reindex-Then-Adapt (RTA) framework, which converts multi-token item titles into single tokens within LLMs, and then adjusts the probability distributions over these single-token item titles accordingly. The RTA framework marries the benefits of both LLMs and traditional recommender systems (RecSys): understanding complex queries as LLMs do; while efficiently controlling the recommended item distributions in conversational recommendations as traditional RecSys do. Our framework demonstrates improved accuracy metrics across three different conversational recommendation datasets and two adaptation settings

cs.IR↗

arXiv2024

Demistifying Inference after Adaptive Experiments

Adaptive experiments such as multi-arm bandits adapt the treatment-allocation policy and/or the decision to stop the experiment to the data observed so far. This has the potential to improve outcomes for study participants within the experiment, to improve the chance of identifying best treatments after the experiment, and to avoid wasting data. Seen as an experiment (rather than just a continually optimizing system) it is still desirable to draw statistical inferences with frequentist guarantees. The concentration inequalities and union bounds that generally underlie adaptive experimentation algorithms can yield overly conservative inferences, but at the same time the asymptotic normality we would usually appeal to in non-adaptive settings can be imperiled by adaptivity. In this article we aim to explain why, how, and when adaptivity is in fact an issue for inference and, when it is, understand the various ways to fix it: reweighting to stabilize variances and recover asymptotic normality, always-valid inference based on joint normality of an asymptotic limiting sequence, and characterizing and inverting the non-normal distributions induced by adaptivity.

stat.ME↗

arXiv2024

Low-Rank MDPs with Continuous Action Spaces

Low-Rank Markov Decision Processes (MDPs) have recently emerged as a promising framework within the domain of reinforcement learning (RL), as they allow for provably approximately correct (PAC) learning guarantees while also incorporating ML algorithms for representation learning. However, current methods for low-rank MDPs are limited in that they only consider finite action spaces, and give vacuous bounds as $|\mathcal{A}| \to \infty$, which greatly limits their applicability. In this work, we study the problem of extending such methods to settings with continuous actions, and explore multiple concrete approaches for performing this extension. As a case study, we consider the seminal FLAMBE algorithm (Agarwal et al., 2020), which is a reward-agnostic method for PAC RL with low-rank MDPs. We show that, without any modifications to the algorithm, we obtain a similar PAC bound when actions are allowed to be continuous. Specifically, when the model for transition functions satisfies a Hölder smoothness condition w.r.t. actions, and either the policy class has a uniformly bounded minimum density or the reward function is also Hölder smooth, we obtain a polynomial PAC bound that depends on the order of smoothness.

cs.LG↗