End-to-end representation learning has become a powerful tool for estimating causal quantities from high-dimensional observational data, but its efficiency remained unclear. Here, we face a central tension: End-to-end representation learning methods often work well in practice but lack asymptotic optimality in the form of the quasi-oracle efficiency. In contrast, two-stage Neyman-orthogonal learners provide such a theoretical optimality property but do not explicitly benefit from the strengths of representation learning. In this work, we step back and ask two research questions: (1) When do representations strengthen existing Neyman-orthogonal learners? and (2) Can a balancing constraint — commonly proposed technique in the representation learning literature — provide improvements to Neyman-orthogonality? We address these two questions through our theoretical and empirical analysis, where we introduce a unifying framework that connects representation learning with Neyman-orthogonal learners (namely, OR-learners). In particular, we show that, under the low-dimensional manifold hypothesis, the OR-learners can strictly improve the estimation error of the standard Neyman-orthogonal learners. At the same time, we find that the balancing constraint requires an additional inductive bias and cannot generally compensate for the lack of Neyman-orthogonality of the end-to-end approaches. Building on these insights, we offer guidelines for how users can effectively combine representation learning with the classical Neyman-orthogonal learners to achieve both practical performance and theoretical guarantees.

Learning causal relations from observational data is a fundamental problem with wide-ranging applications across many fields. Constraint-based methods infer the underlying causal structure by performing conditional independence tests. However, existing algorithms such as the prominent PC algorithm need to perform a large number of independence tests, which in the worst case is exponential in the maximum degree of the causal graph. Despite extensive research, it remains unclear if there exist algorithms with better complexity without additional assumptions. Here, we establish an algorithm that achieves a better complexity of $p^{\mathcal{O}(s)}$ tests, where $p$ is the number of nodes in the graph and $s$ denotes the maximum undirected clique size of the underlying essential graph. Complementing this result, we prove that any constraint-based algorithm must perform at least $2^{\Omega(s)}$ conditional independence tests, establishing that our proposed algorithm achieves exponent-optimality up to a logarithmic factor in terms of the number of conditional independence tests needed. Finally, we validate our theoretical findings through simulations, on semi-synthetic gene-expression data, and real-world data, demonstrating the efficiency of our algorithm compared to existing methods in terms of number of conditional independence tests needed.

We consider the problem of two-sample testing in a semi-supervised setting with abundant unlabeled covariate data. Standard two-sample tests neglect covariate information, which has the potential to significantly boost performance. However, incorporating covariates potentially breaks the exchangeability assumption under the null, which further complicates a calibration procedure. To address these issues, we propose a semi-supervised method that produces a test statistic with asymptotic normality, while effectively integrating additional information from covariates. Our test is straightforward to calibrate due to the asymptotic normality under the null and achieves asymptotic power that is often much higher than existing kernel tests without covariates. Furthermore, we formally show that the proposed method is consistent in power against fixed and local alternatives. Simulations confirm the practical and theoretical strengths of our approach.

We revisit Wald's celebrated Sequential Probability Ratio Test for sequential tests of two simple hypotheses, under privacy constraints. We propose DP-SPRT, a wrapper that can be calibrated to achieve desired error probabilities and privacy constraints, addressing a significant gap in previous work. DP-SPRT relies on a private mechanism that processes a sequence of queries and stops after privately determining when the query results fall outside a predefined interval. This OutsideInterval mechanism improves upon naive composition of existing techniques like AboveThreshold, achieving a factor-of-2 privacy improvement and thus potentially benefiting other continual monitoring procedures. We prove generic upper bounds on the error and sample complexity of DP-SPRT that can accommodate various noise distributions based on the practitioner's privacy needs. We exemplify them in two settings: Laplace noise (pure Differential Privacy) and Gaussian noise (Rényi differential privacy). In the former setting, by providing a lower bound on the sample complexity of any $\epsilon$-DP test with prescribed type I and type II errors, we show that DP-SPRT is near optimal when both errors are small and the two hypotheses are close. Moreover, we conduct an experimental study revealing its good practical performance.

The manifold hypothesis suggests that the generalization performance of machine learning methods improves significantly when the intrinsic dimension of the input distribution's support is low. In the context of Kernel Ridge Regression (KRR), we investigate two alternative notions of intrinsic dimension. The first, denoted $d_\varrho$, is the upper Minkowski dimension defined with respect to the canonical metric induced by a kernel function $K$ on a domain $\Omega$. The second, denoted $d_K$, is the effective dimension, derived from the decay rate of Kolmogorov $n$-widths associated with $K$ on $\Omega$. Given a probability measure $\mu$ on $\Omega$, we analyze the relationship between these $n$-widths and eigenvalues of the integral operator $\phi \mapsto \int_\Omega K(\cdot,x)\phi(x)\,d\mu(x)$. We show that, for a fixed domain $\Omega$, the Kolmogorov $n$-widths characterize the worst-case eigenvalue decay across all probability measures $\mu$ supported on $\Omega$. These eigenvalues are central to understanding the generalization behavior of constrained KRR, enabling us to derive an excess error bound of order $\mathcal{O}(n^{-\frac{2+d_K}{2+2d_K} + \varepsilon})$ for any $\varepsilon > 0$, when the training set size $n$ is large. We also propose an algorithm that estimates upper bounds on the $n$-widths using only a finite sample from $\mu$. For distributions close to uniform, we prove that $\varepsilon$-accurate upper bounds on all $n$-widths can be computed with high probability using at most $\mathcal{O}\left(\varepsilon^{-d_\varrho}\log\frac{1}{\varepsilon}\right)$ samples, with fewer required for small $n$. Finally, we compute the effective dimension $d_K$ for various fractal sets and present additional numerical experiments. Our results show that, for kernels such as the Laplace kernel, the effective dimension $d_K$ can be significantly smaller than the Minkowski dimension $d_\varrho$, even though $d_K = d_\varrho$ provably holds on regular domains.

As generative models continue to evolve, detecting AI-generated images remains a critical challenge. While effective detection methods exist, they often lack formal interpretability and may rely on implicit assumptions about the nature of fake content, potentially limiting their robustness to distributional shifts. In this work, we introduce a rigorous, statistically grounded framework for fake image detection that focuses on producing a probability score interpretable with respect to the real-image population. Our method leverages the strengths of multiple existing detectors by combining strong training-free statistics. We compute $p$-values over a range of test statistics and aggregate them using classical statistical ensembling to assess alignment with the unified real-image distribution. This framework is generic, flexible, and training-free, making it well-suited for robust fake image detection across diverse and evolving settings.

We study sequential testing for a binary disease outcome when risk follows an unknown logistic model. At each round, the decision maker may either pay for a test revealing the true label or predict the outcome based on patient features and past data. The goal is to minimize costly tests while ensuring the misclassification rate stays below $\alpha$ with probability at least $1-\delta$. We propose a method that jointly estimates the logistic parameter $\theta^{\*}$ and the feature distribution, using a conservative threshold on the logistic score to decide when to test. We prove our procedure achieves the target error with high probability and requires only $\widetilde O(\sqrt{T})$ more tests than an oracle with full knowledge. This is the first no-regret guarantee for error-constrained logistic testing, with direct applications to medical screening. Simulations corroborate our theoretical results, showing safe classification of patients and efficient estimation of $\theta^{\*}$ with few excess tests.

The basic question of delineating those statistical problems that are solvable without making any assumptions on the underlying data distribution has long animated statistics and learning theory. This paper characterizes when a convex M-estimation or stochastic optimization problem is solvable in such an assumption-free setting, providing a precise dividing line between solvable and unsolvable problems. The conditions we identify show that Lipschitz continuity of the loss being minimized is not necessary for distribution free minimization, and they are also distinct from classical characterizations of learnability in machine learning.