PyTorchKR Papers

최신 논문

총 523,801편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2610.12235v2cs.CL

Language Models as AI Research World Models

AI research agents automate the cycle of proposing, implementing, and evaluating experiments, opening a path toward recursive self-improvement. Yet their ability to propose experiments outpaces their capacity to execute them in real environments, making outcome prediction a key capability for sustained self-improvement under limited experimental budgets. We investigate language models as Research World Models (RWMs), which predict the outcomes of candidate interventions across research environments. Our evaluation draws on over 2,600 experimental records from nine research environments spanning pretraining, post-training, and inference, representing more than 171,000 H100 GPU-hours of experimentation. Research knowledge acquired from real experimental experience improves RWM predictions of unseen interventions within the same environment (Spearman +0.27), and can be reused across environments. For example, using only pretraining experience from OLMo3, Marin, and Nanochat, an RWM reduces selection regret in the Qwen3 environment by 78% compared with zero-experience setting. These benefits extend to multi-round Autoresearch under a fixed selection budget: RWMs with in-env and cross-env research knowledge increase the best gain achieved by 15.8% and 11.6%, respectively. Ablations across 13 language models used as RWMs show that adding research knowledge can improve intervention ranking more than changing models or increasing reasoning effort alone. These findings support language models as RWMs and motivate accumulating experimental data for future RWM training.

arXiv:2610.10087v3cs.LG

Multi-Agent Coordination via Support-Preserving Distillation

Offline MARL increasingly relies on generative policies to model multimodal joint behavior, typically by distilling a centralized teacher into decentralized one-step actors under the CTDE. We identify a failure mode at the teacher training stage: standard flow-based teachers pair noise with replay targets independently, so nearby noise samples can be routed toward conflicting coordination modes. The teacher then produces samples between valid modes, and because the distillation loss regresses each local actor onto the conditional mean of the teacher's output given local input, this error is not absorbed but propagated to the student. To remove this teacher-side artifact, we propose Mode-Support Semi-Discrete Optimal Transport (MoSDOT), which summarizes multimodal replay into a finite mode support with prescribed capacities and uses conditional semi-discrete optimal transport to assign each noise sample to a single mode before teacher training. We additionally study a shared-randomness variant that uses a shared noise component at execution to expose the residual gap intrinsic to strict-product execution. On controlled diagnostics and offline MARL benchmarks, MoSDOT improves endpoint quality and routing consistency, particularly on datasets exhibiting multimodal joint behavior.

arXiv:2610.07739v2cs.LG

Cite What You Explore: Budget-Aware LLM Reasoning over Medical KGs with Verifiable Evidence

Post-discharge risk prediction from electronic health records (EHRs) is difficult because many dependencies that link discharge-time observations to downstream complications, such as comorbidity cascades and drug-disease interactions, are absent from the record. External medical knowledge graphs (KGs) can supply these missing dependencies, but tracing them in a clinical setting demands three properties. KG exploration must remain cost-bounded, retrieved evidence must be differentiated by source quality, and the resulting rationale must be citable for review. Large language models (LLMs) can plan and verify over structured evidence, making them natural candidates for KG reasoning, but existing LLM-based methods do not satisfy these three properties jointly. In this paper, we propose BAR, a Budget-Aware LLM Reasoning framework over medical KGs with three contributions. First, BAR refines the raw KG into disease-specific evidence graphs whose edges carry support scores and provenance records, turning the KG into a quality-annotated reasoning space rather than a static feature source. Second, an LLM reasons over this graph through a plan-navigate-verify loop that decomposes the question into steps, retrieves evidence under a patient-specific budget, and revises when verification fails. Third, a reasoning policy is trained with a reward that compares predictions with and without acquired evidence, combined with acquisition cost and citation-integrity terms. Across 8 diseases and 3 prediction horizons on MIMIC-III and MIMIC-IV, BAR achieves higher performance and citation precision than strong baselines while using fewer LLM tokens. Its gain over EHR-only prediction grows at longer horizons, and its advantage carries over to an external benchmark.

arXiv:2610.04624v2cs.LG

Backward-Consistent Diffusion Sampling for Sparsely Observed PDE Inverse Problems

Recovering Partial Differential Equation (PDE) coefficient fields from extremely sparse observations is a severely ill-posed inverse problem for which generative machine learning methods (e.g., diffusion models) have become a leading way to encode the prior. Recent state-of-the-art diffusion solvers lift these priors to function spaces, finding a physics-consistent reconstruction in the output space of the diffusion denoiser. We prove that, in a discontinuous PDE setting, output space methods can result in failure to appropriately minimize the unobserved error with the correct coefficient field. Consequently, we propose Function Space Backward-Consistent Sampling (FunBCS), an input space optimization approach for solving PDE problems which aims to find the best input such that the denoiser reconstruction is physics-consistent. We then prove that FunBCS appropriately minimizes the unobserved error, unlike output space optimization methods. Per our theoretical analysis, we also provide insights on how to dynamically allocate the number of input space optimization steps used throughout the sampling process. Our evaluations, across four PDE inverse problems (including the discontinuous Darcy flow), demonstrate that FunBCS reduces the reconstruction error by $27$-$64\%$ while running $1.4$-$2.1\times$ faster when compared to the current state-of-the-art.

arXiv:2610.04044v3cs.CV

Dynamic Quadtree Tokenization and Transformer for Adaptive Mesh PDE Forecasting

The quadratic attention cost of Vision Transformers (ViTs) forces a trade-off between spatial resolution and rollout horizon, particularly for fine-scale PDEs where shocks, reaction fronts, and material interfaces occupy small, evolving regions of the domain. Conventional neural surrogates also lack mechanisms to adapt resolution dynamically. We propose WAMRViT, a ViT that tokenizes inputs as balanced quadtrees using a wavelet-inspired refinement criterion, jointly encodes position and refinement level with 3D rotary positional embeddings, and regrids in cell space during inference for stable long-horizon rollouts. A multi-scale variant retains each leaf at its native source resolution and lets the model learn across resolution levels. Unlike fixed-budget adaptive-tokenization methods, WAMRViT imposes no predetermined token count and supports fully adaptive topology throughout autoregressive rollout. To our knowledge, it is the first machine-learning surrogate to natively tokenize multi-level Adaptive Mesh Refinement (AMR) data. On uniform-grid benchmarks, uniform-patch WAMRViT improves finest-level region-of-interest VRMSE over a finest-patch uniform ViT while using substantially fewer tokens. The multi-scale variant achieves the lowest first-step full-field RMSE and VRMSE on both benchmarks and improves rollout-averaged full-field and refined-region accuracy at long horizons. With parallelized regridding, its end-to-end rollout cost lies between finest-patch and approximately token-matched coarser-patch ViTs. On a complex AMR combustion problem whose finest features cannot be represented natively by the evaluated uniform-grid baselines, WAMRViT operates on adaptive cells built from the simulator hierarchy and substantially reduces finest-level error at matched transformer capacity. Code: https://github.com/tonyzyl/wamrvit

arXiv:2610.03792v3cs.CV

What Do Verifiable Rewards Teach Video-Language Models About Time? A Controlled Multi-Model Study

Reinforcement learning from verifiable rewards (RLVR) has produced large reasoning gains in language models, and verifiable video benchmarks make the recipe directly applicable to causal-temporal video question answering. We present a controlled study of what RLVR actually teaches video-language models about temporal structure. We fine-tune four open models with group relative policy optimization (GRPO) under three data recipes using annotated synthetic questions, self-supervised real-video pretext tasks, and a one-to-one mixture, plus a targeted real-video augmentation arm. We evaluate the model-recipe grid on 105 CLEVRER questions with one correct option and on two real-video transfer sets. The 8B ordered gain is 4.8 points (95% video-bootstrap CI [-5.6, 15.1]), while blind accuracy increases 10.5 points ([0.9, 20.6]). The 4B model gains an accuracy advantage for ordered over shuffled frames. On the real-video sets, the 8B synthetic-only checkpoint loses 26.7 and 25.2 points, with smaller regressions under mixed and augmented recipes. In a separate scene-disjoint, single-gold Qwen3-VL-8B experiment, supervised fine-tuning (SFT) and GRPO each complete 1,200 updates at three fixed seeds. GRPO minus SFT is -3.89 points in ordered accuracy (nominal 97.5% video-bootstrap CI [-7.36, -0.45]) and -2.78 points in ordered-minus-shuffled accuracy ([-6.60, 0.87]). Transfer differences are sensitive to parseability. Intervals quantify test-video uncertainty conditional on the fitted runs. The results show why benchmark accuracy, transfer, and presented-order sensitivity need to be evaluated separately.

arXiv:2610.03303v2cs.LG

S$^{2}$-PINN: Stochastic Separable Physics-Informed Neural Networks

Uncertainty quantification (UQ) for random partial differential equations (PDEs) is ubiquitous in computational science and engineering. However, classical spectral solvers for this class of problems face the curse of dimensionality, and existing neural solvers often ignore the stochastic structure that makes moments and calibration tractable. We introduce a stochastic separable physics-informed neural network, dubbed S$^{2}$-PINN, that represents the solution $u(t,\mathbf{x},\mathbf{Z})$ of a random PDE with a learnable Gaussian spatial dictionary, Fourier temporal features, and a generalized polynomial chaos (gPC) stochastic basis, coupled by a low-rank Canonical Polyadic (CP) tensor decomposition core. The method is trained with a hybrid strong-form and gPC-projected residual loss. Our theoretical analysis establishes that the separable class is dense in $L^2$ under mild conditions, and the projected residual corresponds exactly to a stochastic Galerkin constraint. Furthermore, we show that mini-batch projection coefficients are logarithmically dependent on the number of gPC modes, and that the orthogonality penalty controls the conditioning of the learned spatial dictionary. Using four manufactured random PDE benchmarks, we show that S$^{2}$-PINN outperforms nine baselines in terms of mean and variance accuracy, as well as calibration, while using significantly fewer parameters. Further evaluations on non-manufactured Poisson and Darcy problems, a stochastic Navier--Stokes problem, a diffusion scaling study of higher random dimensions, and two stochastic inverse problems reveal the generalization capabilities of the proposed structure. Together, these results support stochastic separability as an effective design principle for physics-informed neural UQ. The code for the experiments can be found in https://github.com/DMax1314/s2pinn

arXiv:2609.39640v2cs.CL

Zero-Compute Cross-Lingual Transferability Estimation Using Typological Feature Proxies

Cross-lingual transfer describes how knowledge in a source language benefits a target language. Measuring it quantitatively requires broad multilingual pre-training, as prior work has done with cross-lingual transfer matrices. We ask whether transfer is predictable from freely available typological features, and whether the prominence of high-resource source languages reflects typology or data quality and quantity. We show that typological databases contain cheap and dense signals about cross-lingual transfer. Our typology-only random forest on a 24-language prior-work transfer matrix scores leave-one-language-out $\rho{=}0.705$ and $R^2{=}0.49$, against $\rho{=}0.62$ for a tuned non-typological control, an increment that a paired bootstrap cannot separate at this scale. When both languages of a held-out pair are unseen, performance degrades to $\rho{\approx}0.41$, so the model interpolates a ground-truth matrix more reliably than it predicts new languages. The signal survives leave-one-script-out and leave-one-family-out protocols, so script and family confounding do not explain the effect. By decomposing the transfer into a typology term and a resource-and-script bias term, we find the best-source ranking sensitive to this bias. Typological features never observe this bias, which makes them a zero-compute screening tool that replaces hundreds of training runs with a model fit. Our code is available \href{https://github.com/dharmsen/typo-x-ling-transfer}{here}.

arXiv:2609.37969v2cs.CV

SoL-Refiner: Speed-of-Light One-Step Refinement for High-Resolution Video

High-resolution video generation is expensive, as its cost grows rapidly with the number of spatiotemporal tokens. A practical alternative first generates a lower-resolution video and then applies a refiner, but conventional multi-step refinement introduces a second sampling bottleneck. We present SoL-Refiner, a one-step video refiner that transforms low-resolution model outputs into 4K videos with a single denoising step. Our three-stage recipe combines high-resolution continual training, reinforcement learning (RL) post-training, and a final one-step distillation. We introduce Refiner-Bench, a video refinement benchmark constructed from the outputs of different video generators, and use a shared-input protocol to compare refiners at approximately 2K output resolution. With LTX-2.3 Refiner as the base model, the one-step SoL-Refiner outperforms all external refiners at 2K on the VBench and UniPercept averages, while at $3840\!\times\!2176$ it improves both metrics over the three-step LTX-2.3 Refiner. With the complete acceleration stack, SoL-Refiner achieves an $8.91\times$ speedup in refinement latency over the same baseline in our 2K latency setting. With MiniMax H3 as the base model, SoL-Refiner produces 2K videos in three refinement steps and is preferred over the official MiniMax H3 2K API in 87% of user-study judgments.

arXiv:2609.34639v2cs.LG

Uniform Race: Parameter-Free Approximate Rejection Sampling

Consider the approximate sampling problem: given $N$ independent samples from a proposal distribution $\mu$, the goal is to select one whose distribution is close to a target $\pi$ specified only up to a normalizing constant. The seminal work of Block & Polyanskiy (2023) provides a total variation (TV) error bound for approximate rejection sampling (RS) as a function of the algorithm's acceptance threshold $M$. The ideal threshold $M$ that minimizes the bound, however, depends on properties of $(\pi, \mu)$ that are typically unavailable from the observed sample. This raises a natural question: Can one attain the best RS guarantee without taking the best $M$ as input? We answer this question affirmatively by proposing a parameter-free sampling algorithm called uniform race (UR). UR computes a score for each sample $y$ that is the importance weight $\pi(y)/\mu(y)$ divided by an independent uniform random variable and then returns the one with the highest score. We prove that UR attains the best $M$-tuned TV error bound for RS. That is, UR, without knowing the best $M$, achieves the same performance guarantee as RS that takes the best $M$ as input. We also prove that UR has no larger TV error than the budget-calibrated version of the rejection sampler of Rohatgi et al. (2025) and sampling importance resampling (SIR). In particular, we identify instances where UR's error is exponentially smaller in $N$ than that of these two baselines. Furthermore, we establish conditions under which attaining this RS guarantee for every $(\pi, \mu)$ uniquely determines the selection probabilities as those of UR. Finally, test-time scaling experiments on LLM reasoning tasks corroborate the theoretical comparisons and demonstrate that UR remains competitive without requiring threshold selection.

arXiv:2609.34458v2stat.ML

Understanding Generalization Requires Universal Induction

Classical statistical theory is insufficient to explain the successes of general-purpose AI models, because it depends on handcrafted inductive biases that it cannot justify. No Free Lunch (NFL) theorems force any learner that beats chance on some environments to underperform on others. We might hope that past experience informs which environments to expect, but NFL applies equally to meta-learning. Thus, any method that makes meaningful predictions necessarily begins with an inductive bias external to the data. Choosing to bias toward short programs yields Solomonoff induction (SI), whose performance is competitive against all computable learners - albeit up to "constants" that become large when comparing against specialized methods that exploit background information. We therefore relativize SI to an information vantage point, biasing toward short programs with access to all preexisting information. This reframes the inductive bias: instead of seeking some absolute notion of simplicity, we favour accessibility with respect to our vantage point. An algorithm can only outpredict the relativized SI to the extent that its code contains additional information about the data, and no algorithm can generate such information. While SI is incomputable and hence not a practical algorithm, it provides a formal optimum for inference in the limit of infinite compute, and there is evidence to suggest that frontier AI systems roughly approximate it. Thus, the only known answer to meta-NFL is rooted in algorithmic information theory, which we should expect to play a fundamental role in explaining the generalization behaviour of modern (and future) AI systems.

arXiv:2609.34378v2cs.CV

Marathoner: Ultra-Long-Horizon Autonomous Intelligence

Humans naturally possess the ability to work persistently toward long-term goals. Given a challenging task, humans can continuously work for months or even years to accomplish a specific objective. In this paper, we propose Marathoner, an autonomous agentic model possessing the ability of ultra-long-horizon execution. Specifically, we propose a comprehensive post-training pipeline to instill this critical capability into base model. For Ultra-Long-Horizon Task Synthesis, we leverage major release PRs containing 1000+ lines of new code from diverse GitHub repositories as the primary source for synthesizing challenging task-level data. Additionally, we introduce Multi-Task Chaining, which chains multiple generated tasks into a single more challenging task, enabling the synthesis of tasks with frontier-level difficulty. For rejection sampling finetuning, we combine strong teacher model with diverse harnesses to generate trajectories on our synthesized tasks and conduct supervised finetuning on base model with rejection sampled trajectories. For reinforcement learning, cold-started model performs real-world execution through harnesses in independent sandboxes during rollout process, effectively facilitating the acquisition of genuine ultra-long-horizon execution capability. We further propose a novel reward strategy, Later Stage Bonus Reward, which explicitly encourages model to perform meaningful maneuvers during later stages of execution. Through extensive evaluation on 5 benchmarks containing ultra-long-horizon tasks, Marathoner achieves consistent and substantial performance improvements over base model and even surpasses performance of strong proprietary model. Further analysis shows that Marathoner can consistently work for 10+ hours and conduct 1000+ tool calls on highly challenging tasks.

arXiv:2609.33387v2cs.LG

From Grey-Box to Green-Box: When can Physics-Informed Machine Learning Reduce Carbon Footprints in Structural Health Monitoring?

Machine learning plays an increasingly vital role in engineering, but the corresponding increase in compute time is not without environmental cost. Physics-informed machine learning or "grey-box" models have been developed to overcome some of the limitations of traditional black-box learners, utilising the physical insight that an engineer would have about the structure they are modelling and have shown promising results in the structural engineering field among many others. This work explores whether an additional advantage could be a reduced environmental impact, considering the relationship between training data quantity and training time, linking this duration to carbon emissions from computing. In a structural health monitoring context, four physics-informed machine learning approaches - spanning Gaussian processes and neural networks - are evaluated: residual modelling, input augmentation, hybrid modelling, and constrained learning. The emissions for training each of the models to reach a given error threshold is compared, and in most examples, shown to be lower for the physics-informed models (with input augmented models being an exception). This reduction in training emissions further compounds the environmental savings achieved by collecting and storing less data. Although promising results, we cannot expect a silver bullet and the case studies demonstrate that a trade-off is needed between the increased complexity that comes from introducing physics into a machine learner, against the gain from reduced training data requirements.

arXiv:2609.32991v2cs.LG

What Should Data Teach? Moving Bottlenecks Across Circuit, Store, and Use

What should data teach a language model at a particular point in training? A circuit view reveals three distinct bottlenecks: forming a computation, making its required content available, and selecting among available routes. A shared diagnosis-to-data principle connects them: localize the missing operation, preserve its causal relation, vary shortcut-bearing context, and re-audit the residual. Formation-sensitive selection and prerequisite ordering accelerate a binding-matching-transport path; a brief early prefix from the same training multiset retains a validation advantage through 100B tokens. Availability counterfactuals then distinguish writing content from invoking available memory, while paired supervision and context-opportunity ranking improve matched route decisions and long-context answer likelihood. A continuous 350M-model experiment connects the three interventions on the same facts: early circuit training improves subsequent learning, and the complete sequence outperforms stage-replacement controls on facts withheld from Use teaching. Independent query surfaces and opposed-source decisions expose conditional arbitration as the remaining frontier. Together, these results show why a change in the limiting operation calls for a change in supervision, not merely a new ranking of difficult examples.

arXiv:2609.31016v2cs.LG

Robust Successor Features

Generalization in Reinforcement Learning (RL) refers to the ability to execute close-to-optimal policies in unseen tasks after the agent has been trained on a different set of tasks. Building on the seminal work of the successor representation and further adaptations with function approximation, Transfer in RL has traditionally focused on generalizing to tasks that only differ in the reward function. A decade after the introduction of the successor representation, Robust RL emerged simultaneously from several articles in the field of operations research. In Robust RL, the transition kernel is unknown, and the goal is to maximize the expected reward under this uncertainty. Our work unifies these two paradigms through robust successor features, which generalize across both the reward function and the transition kernel, under the assumption that tasks are linear Markov Decision Processes. We derive a bound on Generalized Policy Improvement (GPI) that explicitly quantifies how performance degrades with the mismatch between transition kernels, recovering existing successor-feature guarantees when dynamics are shared. Finally, the generalization capabilities of robust successor features are validated on several grid-based benchmarks and compared to previous alternatives that focus solely on either the reward or the transition kernel.

arXiv:2609.30809v2math.NA

Deep-Learning Solvers and Surrogates for Infinity and p-Laplace Problems

We investigate the use of neural network solvers for infinity and $p$-Laplace problems, which are fundamental in nonlinear analysis and have practical applications. Our approach employs Physics-Informed Neural Networks (PINNs) and Deep Operator Networks (DeepONets) to address computational challenges associated with large $p$ values, ranging from $2$ to $1000$, on various 2D and 3D domains. Our method offers advantages over traditional physics-based solvers, especially in three dimensions where mesh-based solvers become very costly for these problems. We also establish conditional convergence results for PINN approximations of both problems and a universal approximation result for DeepONet on the parametric $p$-Poisson problem. We demonstrate the effectiveness of these neural network solvers through numerical experiments and compare their performance with conventional methods.

arXiv:2609.30698v2cs.CV

MM-VeriAgent: Learning to Use Extensive Tools to Verify Multimodal Misinformation with Reinforcement Learning

Real-world multimodal misinformation often involves mixed forgery sources, requiring sample-specific detection strategies. Existing tool-augmented methods rely on predefined workflows or inference-time planning, limiting adaptability or increasing inference cost. To address this issue, we introduce \textbf{MM-VeriAgent}, which learns to verify mixed-source multimodal misinformation with tools. We first build \textbf{MM-VeriTools}, a specialized toolkit for misinformation detection agents. By benchmarking various candidate models and methods on the sub-tasks required by mixed-source detection, we select the strongest for textual, visual, and cross-modal forgery analysis and encapsulate them as callable tools with a unified interface. On top of this toolkit, we train the LVLM agent with reinforcement learning to teach it how to use these tools to better solve mixed-source detection. Since many of the tools are specialized models whose online execution at every rollout severely limits RL efficiency, we further introduce \textbf{Tool-Execution Cache}, which pre-executes candidate tool calls and reuses their cached outputs during training. This preserves multi-step rollouts while reducing online tool execution, largely improving the training efficiency.Experiments on MMFakeBench demonstrate substantial accuracy gains over the base model without explicit tool search at inference time. Ablation and efficiency analyses further validate the learned tool-use policy and show that Tool-Execution Cache reduces online tool executions during training.

arXiv:2609.29711v2cs.LG

Decoupling Knowledge and Privacy: Post-Task Self-Distillation Replay for LLM Continual Learning

Privacy-preserving continual learning (PPCL) must reduce the reproduction of sensitive content while retaining useful knowledge across sequential tasks. Formal privacy guarantees characterize randomized mechanisms, whereas operational output control concerns whether a trained model selectively reduces the likelihood of sensitive content in its outputs. In this work, we investigate the latter together with continual-learning utility under realistic task evolution. Retention and privacy correction operate at different granularities: task acquisition requires broad preservation of current- and old-task behavior, whereas privacy correction targets sparse annotated positions. Joint optimization leaves the current-task preservation target continually changing. We propose SPARK, a retention-correction decomposition that first freezes the learned post-task distribution and then applies selective correction around this stable reference. Self-Distillation Replay learns the current task while distilling behavior from previous tasks, and Post-Task Privacy Correction reduces annotated-PII likelihood while anchoring current- and old-task non-PII behavior to the resulting checkpoint. Extensive evaluations demonstrate that SPARK achieves effective selective PII suppression while preserving strong continual-learning utility and knowledge retention across diverse settings. Code and data will be released upon publication.

arXiv:2609.27262v2cs.CL

Can One Adapted Model Do It All? Fine-Tuning Strategy Selection for Customer Support LLMs

Production customer-support systems often require LLMs to support multiple skills, such as intent classification, question answering, summarization, or tool-use decisions. A central deployment question is whether these skills should be handled by separate task-specialist models or by a single model trained through multi-task training, sequential updates, or model merging. We study this question using thirteen models spanning five families (Qwen3, Qwen3.5, Gemma-3, Llama-3.1, and Mistral) from 0.6B to 32B parameters across eight customer-support datasets, spanning four public and four proprietary datasets with approximately 74.5k training and 8.7k evaluation samples. Under a fixed training protocol, we train more than 200 checkpoints. Our experiments reveal that multi-task full fine-tuning is the strongest operational default at every model size we test. Specialist models are strong on their target tasks but often degrade sharply off-task, making reliable routing important. Sequential Low-Rank Adaptation (LoRA) preserves earlier skills better than sequential full fine-tuning, while merging a specialist with its base model improves off-task robustness with limited same-task loss for larger models. We conclude with practical guidelines for selecting fine-tuning strategies in real-world settings.

arXiv:2609.27179v2math.ST

Optimal distribution-free sequential change detection with conformal martingales

We study the challenging problem of distribution-free sequential changepoint detection for independent observations with unknown and \emph{completely unrestricted} pre- and post-change laws. For over two decades, the primary existing solution for this problem has employed Vovk's conformal test martingales and associated e-detectors, which control the probability of false alarm (PFA) and the average run length (ARL) respectively. The majority of these works focus on validity, with statistical efficiency usually left for simulations. We develop a comprehensive theory of how conformal p-values behave under non-exchangeable data with a changepoint at an unknown time $T$. We use this to analyze the post-change growth and resulting detection delays and find that the standard existing methods are provably suboptimal for PFA and ARL control, and can lead to delays that are $\Omega(T)$ and $\Omega(\sqrt{\text{ARL}})$ respectively. We construct new conformal e-processes and e-detectors with learned scores and a fixed, distribution-independent betting dictionary. For any distribution pair with positive finite KL divergence, our methods asymptotically achieve $\log T/\mathrm{KL}$ delay for PFA control and $\log\mathrm{ARL}/\mathrm{KL}$ delay (with a sharp leading constant of 1), which are both proven to be minimax optimal in a suitable double-array framework. Simulations illustrate the large empirical benefits of our new approach.