Matched-pair experimental designs aim to detect treatment effects by pairing participants and comparing within-pair outcome differences. In many situations, the overall effect size across the entire population is small. Then, the focus naturally shifts to identifying and targeting high treatment-effect regions where the intervention is most effective. This paper proposes a matched-pair experimental design that sequentially and actively enrolls patients in high treatment-effect regions. Importantly, we frame the identification of the target region as a classification problem and propose an active learning framework tailored to matched-pair designs. Our design not only reduces the experimental cost of detecting treatment efficacy, but also ensures that the identified regions enclose the entire high-treatment-effect regions. Our theoretical analysis of the framework's label complexity and experiments in practical scenarios demonstrate the efficiency and advantages of the approach.

Large language models (LLMs) are typically trained by reinforcement learning (RL) with verifiable rewards (RLVR) and supervised fine-tuning (SFT) on reasoning traces to improve their reasoning abilities. However, how these methods shape reasoning capabilities remains largely elusive. Going beyond an accuracy-based investigation of how these two components sculpt the reasoning process, this paper introduces a novel analysis framework that quantifies reasoning paths and captures their qualitative changes under each training process (with models of 1.5B, 7B, and 14B parameters on mathematical domains). Specifically, we investigate the reasoning process at two levels of granularity: the trajectory-level, which examines complete reasoning outputs, and the step-level, which analyzes reasoning graphs whose nodes correspond to individual reasoning steps. Notably, clustering of unique reasoning trajectories shows complementary effects: RL compresses incorrect trajectories, whereas SFT expands correct ones. Step-level analysis reveals that RL steepens (about 2.5 times), while SFT flattens (reduced to about one-third), the decay rates of node visitation frequency, degree, and betweenness centrality distributions in the reasoning graph. This indicates that RL concentrates reasoning functionality into a small subset of steps, while SFT homogenizes it across many steps. Furthermore, by evaluating the reasoning graph topologies from multiple perspectives, we delineate the shared and distinct characteristics of RL and SFT. Our work presents a novel reasoning path perspective that explains why the current best practice of two-stage training, with SFT followed by RL, is successful, and offers practical implications for data construction and more efficient learning approaches.

This note responds to "Promises and Pitfalls of Deep Kernel Learning" (Ober et al., 2021). The marginal likelihood of a Gaussian process can be compartmentalized into a data fit term and a complexity penalty. Ober et al. (2021) shows that if a kernel can be multiplied by a signal variance coefficient, then reparametrizing and substituting in the maximized value of this parameter sets a reparametrized data fit term to a fixed value. They use this finding to argue that the complexity penalty, a log determinant of the kernel matrix, then dominates in determining the other values of kernel hyperparameters, which can lead to data overcorrelation. By contrast, we show that the reparametrization in fact introduces another data-fit term which influences all other kernel hyperparameters. Thus, a balance between data fit and complexity still plays a significant role in determining kernel hyperparameters.

For overparameterized linear regression with isotropic Gaussian design and minimum-$\ell_p$ interpolator $p\in(1,2]$, we give a unified, high-probability characterization for the scaling of the family of parameter norms $ \\{ \lVert \widehat{w_p} \rVert_r \\}_{r \in [1,p]} $ with sample size. We solve this basic, but unresolved question through a simple dual-ray analysis, which reveals a competition between a signal *spike* and a *bulk* of null coordinates in $X^\top Y$, yielding closed-form predictions for (i) a data-dependent transition $n_\star$ (the "elbow"), and (ii) a universal threshold $r_\star=2(p-1)$ that separates $\lVert \widehat{w_p} \rVert_r$'s which plateau from those that continue to grow with an explicit exponent. This unified solution resolves the scaling of *all* $\ell_r$ norms within the family $r\in [1,p]$ under $\ell_p$-biased interpolation, and explains in one picture which norms saturate and which increase as $n$ grows. We then study diagonal linear networks (DLNs) trained by gradient descent. By calibrating the initialization scale $α$ to an effective $p_{\mathrm{eff}}(α)$ via the DLN separable potential, we show empirically that DLNs inherit the same elbow/threshold laws, providing a predictive bridge between explicit and implicit bias. Given that many generalization proxies depend on $\lVert \widehat {w_p} \rVert_r$, our results suggest that their predictive power will depend sensitively on which $l_r$ norm is used.

Inverse reinforcement learning (IRL) aims to explain observed behavior by uncovering an underlying reward. In the maximum-entropy or Gumbel-shocks-to-reward frameworks, this amounts to fitting a reward function and a soft value function that together satisfy the soft Bellman consistency condition and maximize the likelihood of observed actions. While this perspective has had enormous impact in imitation learning for robotics and understanding dynamic choices in economics, practical learning algorithms often involve delicate inner-loop optimization, repeated dynamic programming, or adversarial training, all of which complicate the use of modern, highly expressive function approximators like neural nets and boosting. We revisit softmax IRL and show that the population maximum-likelihood solution is characterized by a linear fixed-point equation involving the behavior policy. This observation reduces IRL to two off-the-shelf supervised learning problems: probabilistic classification to estimate the behavior policy, and iterative regression to solve the fixed point. The resulting method is simple and modular across function approximation classes and algorithms. We provide a precise characterization of the optimal solution, a generic oracle-based algorithm, finite-sample error bounds, and empirical results showing competitive or superior performance to MaxEnt IRL.

The core of generalization theory was developed for independent observations. Some PAC and PAC-Bayes bounds are available for data that exhibit a temporal dependence. However, there are constants in these bounds that depend on properties of the data-generating process: mixing coefficients, mixing time, spectral gap... Such constants are unknown in practice. In this paper, we prove a new PAC-Bayes bound for Markov chains. This bound depends on a quantity called the pseudo-spectral gap. The main novelty is that we can provide an empirical bound on the pseudo-spectral gap when the state space is finite. Thus, we obtain the first fully empirical PAC-Bayes bound for Markov chains. This extends beyond the finite case, although this requires additional assumptions. On simulated experiments, the empirical version of the bound is essentially as tight as the non-empirical one.

Biopharmaceutical manufacturing is vital to public health but lacks the agility for rapid, on-demand production of biotherapeutics due to the complexity and variability of bioprocesses. T o overcome this, we introduce RApid PosT eriOR GENerator (RAPTOR-GEN), a mechanism-informed Bayesian learning framework designed to accelerate intelligent digital twin development from sparse and heterogeneous experimental data. This framework is built on a multi-scale probabilistic knowledge graph (pKG), formulated as a stochastic differential equation (SDE)-based foundational model that captures the nonlinear dynamics of bioprocesses. RAPTOR-GEN consists of two ingredients: (i) an interpretable metamodel integrating linear noise approximation (LNA) that exploits the structural information of bioprocessing mechanisms and a sequential learning strategy to fuse heterogeneous and sparse data, enabling inference of latent state variables and explicit approximation of the intractable likelihood function; and (ii) an efficient Bayesian posterior sampling method that utilizes Langevin diffusion (LD) to accelerate posterior exploration by exploiting the gradients of the derived likelihood. It generalizes the LNA approach to circumvent the challenge of step size selection, facilitating robust learning of mechanistic parameters with provable finite-sample performance guarantees. We develop a fast and robust RAPTOR-GEN algorithm with controllable error. Numerical experiments demonstrate its effectiveness in uncovering the underlying regulatory mechanisms of biomanufacturing processes. Funding: This research was supported by National Science Foundation Grant CAREER CMMI-2442970 and National Institute of Standards and T echnology Grant 70NANB21H086.

The analysis of spatial data from biological imaging technology, such as imaging mass spectrometry (IMS) or imaging mass cytometry (IMC), is challenging because of a competitive sampling process which convolves signals from molecules in a single pixel. To address this, we develop a scalable Bayesian framework that leverages natural sparsity in spatial signal patterns to recover relative rates for each molecule across the entire image. Our method relies on the use of a heavy-tailed variant of the graphical lasso prior and a novel hierarchical variational family, enabling efficient inference via automatic differentiation variational inference. Simulation results show that our approach outperforms state-of-the-practice point estimate methodologies in IMS, and has superior posterior coverage than mean-field variational inference techniques. Results on real IMS data demonstrate that our approach better recovers the true anatomical structure of known tissue, removes artifacts, and detects active regions missed by the standard analysis approach.

The celebrated Vapnik-Chervonenkis dimension vc(F) of a binary-valued function class F and the scale-sensitive dimension vc(F, α) of a real-valued function class F are central notions in the study of empirical processes and convergence of statistical learning methods [VC71, BLW94, KS94]. Sequential analogues of these notions--the Littlestone dimension ldim(F) and the sequential scale-sensitive dimension sfat(F, α)-- have been shown to play an analogously central role in the study of uniform martingale laws and online prediction [Lit88, BDPSS09, RST10]. In this paper, we study "gapped" versions of vc(F,α) and sfat(F, α). The modification yields a dimension that is no larger than the original one, yet can still be shown to control covering numbers in both sequential and non-sequential cases. More importantly, the new notion gives us a more precise control on the functions involved in "shattering" and thus yields non-vacuous lower bounds for offset Rademacher complexities for any uniformly bounded class--both in the classical and sequential cases--and, as a consequence, tighter lower bounds for online prediction problems, such as online regression or transductive learning. Our definition in the non-sequential case can also be seen as a modification of the Natarajan dimension [NT88, Nat89], and was, in fact, introduced in [AB00]. We first motivate the development in this paper on the simpler case of non-sequential data. We start by recalling the definition of the Vapnik-Chervonenkis dimension and its scale-sensitive version.

We study an unsupervised domain adaptation problem where the source domain consists of subpopulations defined by the binary label $Y$ and a binary background (or environment) $A$. We focus on a challenging setting in which one such subpopulation in the source domain is unobservable. Naively ignoring this unobserved group can result in biased estimates and degraded predictive performance. Despite this structured missingness, we show that the prediction in the target domain can still be recovered. Specifically, we rigorously derive both background-specific and overall prediction models for the target domain. For practical implementation, we propose the distribution matching method to estimate the subpopulation proportions. We provide theoretical guarantees for the asymptotic behavior of our estimator, and establish an upper bound on the prediction error. Experiments on both synthetic and real-world datasets show that our method outperforms the naive benchmark that does not account for this unobservable source subpopulation.