Forskningsradar

Science Journals

Peer-reviewade publikationer — 51240 artiklar

arXiv (fysik & CS) Preprint 2026-05-19
Agents for Experiments, Experiments for Agents: A Design Grammar for AI-Enabled Experimental Science
arXiv:2605.17746v1 Announce Type: new Abstract: AI systems are becoming active participants in organizational and knowledge work. They increasingly interact with humans, coordinate workflows, and operate in multi-agent arrangements. Understanding their effects therefore requires more than measuring output accuracy; it requires evidence about mechanisms, delegation, feedback, and control. Experiments remain central to this task, but they also face a recursive challenge: we need experiments for agents to study these arrangements, and we may need agents for experiments to help search the expanding space of possible designs. Yet experimental conditions for human-AI and agentic workflows are still largely specified in prose, making them difficult to compare, reuse, or audit. We frame this as a problem of workflow representation, traceability, and governance in AI-enabled knowledge production. We introduce SEED (Structural Encoding for Experimental Discovery), a framework that represents experimental conditions as typed actor-flow graphs. SEED supports three design functions: describing conditions as interaction structures, evaluating structural novelty relative to encoded prior designs, and generating candidate designs under feasibility and governance constraints. We report a lightweight empirical feasibility test that compares graph-blind and SEEDguided generation in a medical-triage design task. In this diagnostic contrast, SEED-guided candidate designs show clearer actor-flow changes, assumptions, and governance checks, supporting the feasibility of the grammar as a design aid. The commentary closes by identifying governance tensions around novelty, replication, validity, diversity of inquiry, and accountability.
arXiv (fysik & CS) Preprint 2026-05-19
End-to-End Formalization of Quantum Error Correction
arXiv:2605.16523v1 Announce Type: cross Abstract: Quantum error-correcting codes (QECCs) sit between noisy quantum hardware and reliable computation, so the code parameters used in practice must be trustworthy. The single number that summarizes a code's strength is its distance, yet certifying a distance lower bound is NP-hard in general, placing it beyond the reach of pen-and-paper proofs as well as direct proof-assistant scripting. As a result, distance values in the literature come either from non-scaling hand proofs, or from unverified solvers that leave a trust gap exactly where the code is supposed to provide a guarantee. We present Lean-QEC, the first Lean 4 formalization of stabilizer-code theory that delivers end-to-end, machine-checked distance certificates at industrial code sizes. Lean-QEC formalizes the linear algebra of qubit states, the Pauli group, stabilizer codes, the binary symplectic representation, classical coding theory, and the CSS and Bivariate Bicycle families. To break the combinatorial barrier, Lean-QEC translates the distance condition into a Boolean satisfiability formula through a verified reduction. The pipeline scales through a BitVec-flattened encoding that replaces Lean's Matrix representation, and an error-location encoding that reduces the variable count from $n$ to $k\lceil \log_2 n\rceil$. With these, we obtain automatically-generated Lean-checked distance proofs for a large range of industrially viable qLDPC codes within the Bivariate Bicycle and Generalized Bicycle families, including [[90, 8, 10]] and [[70, 6, 9]] BB codes, with the formulation scaling up to 144 qubits when performed outside the Lean kernel. The resulting library is reusable and is designed to plug into broader Lean-based efforts toward end-to-end verification of fault-tolerant quantum computation.
arXiv (fysik & CS) Preprint 2026-05-19
Fast Rates in $\alpha$-Potential Games via Regularized Mirror Descent
arXiv:2605.00268v2 Announce Type: replace Abstract: An $\alpha$-potential game is a multi-player non-cooperative interaction in which a global potential function approximates individual player rewards up to a structural bias $\alpha$. While identifying a Nash Equilibrium (NE) in generic general-sum games is known to be computationally intractable, the potential game structure enables tractable NE identification. In this paper, we study the offline learning of NE in $\alpha$-potential games using KL regularization. To analyze this process, we propose a novel Reference-Anchored offline data coverage framework--a verifiable condition that anchors data requirements to a known reference policy rather than an unknown optimum. Building on this, we propose Offline Potential Mirror Descent (OPMD), a decentralized algorithm that achieves an accelerated $\widetilde{\mathcal{O}}(1/n)$ statistical rate, surpassing the standard $\widetilde{\mathcal{O}}(1/\sqrt{n})$ rate typical of offline multi-agent learning. This work characterizes the first fast-rate offline learning approach for $\alpha$-potential games.
arXiv (fysik & CS) Preprint 2026-05-19
What Does the AI Doctor Value? Auditing Pluralism in the Clinical Ethics of Language Models
arXiv:2605.18738v1 Announce Type: new Abstract: Medicine is inherently pluralistic. Principles such as autonomy, beneficence, nonmaleficence, and justice routinely conflict, and such ethical dilemmas often sharply divide reasonable physicians. Good clinical practice navigates these tensions in concert with each patient's values rather than imposing a single ethical stance. The ethical values that large language models bring to medical advice, however, have not been systematically examined. We present a framework for auditing value pluralism in medical AI, comprising a benchmark of clinician-verified dilemmas and an attribution method that recovers value priorities directly from decisions. The ecosystem of frontier models spans physician-level value heterogeneity, and models discuss competing values in their reasoning (Overton pluralism) before committing to a decision. However, individual model decisions are near-deterministic across repeated sampling and semantic variations, failing to reproduce the distributional pluralism of the physician panel. Across benchmark cases, these consistent decisions reflect committed, systematic value preferences. While most model priorities fall within the natural range of inter-physician variation, some significantly underweight patient autonomy. A single LLM deployed without regard for its value priorities could amplify those priorities at scale to every patient it serves. Without explicit efforts to balance ethical perspectives with one or multiple models, these tools risk replacing clinical pluralism with a deployment monoculture.
arXiv (fysik & CS) Preprint 2026-05-19
UST-Hand: An Uncertainty-aware Spatiotemporal Point Cloud Interaction Network for 3D Self-supervised Hand Pose Estimation
arXiv:2605.17742v1 Announce Type: new Abstract: Manually annotating accurate 3D hand poses is extremely time-consuming and labor-intensive. Existing self-supervised hand pose estimation methods leverage the discrepancy between input images and rendered outputs, or multi-view consistency constraints, as the driving force to optimize networks and progressively refine pose accuracy. However, these methods are highly susceptible to noisy pseudo-labels and overlook the importance of fully exploiting fine-grained spatial correlations, which undermines the stability of model training. To address these issues, we propose UST-Hand, a self-supervised learning framework that estimates uncertainty distribution of hand pose and constructs a probabilistic point cloud feature space, which enables the complex spatiotemporal relationship modeling. UST-Hand employs a conditional normalizing flow model to capture hand pose distributions and samples diverse hypotheses, facilitating robust learning under noisy pseudo-labels supervision with enhanced stability. These multi-hypothesis are mapped to a unified probabilistic 3D point cloud space for multi-view and temporal feature interaction, comprehensively exploring hand motion patterns and fine-grained spatial correlations. Extensive experiments on three challenging datasets demonstrate that UST-Hand achieves state-of-the-art performance, outperforming existing self-supervised methods by up to 37.8% in Mean Per Vertex Position Error (MPVPE).
arXiv (fysik & CS) Preprint 2026-05-19
VISAFF: Speaker-Centered Visual Affective Feature Learning for Emotion Recognition in Conversation
arXiv:2605.18547v1 Announce Type: new Abstract: Emotion Recognition in Conversation (ERC) is essential for effective human-machine interaction, aiming to identify speakers' emotional states in multi-turn dialogues. Early text-based methods struggle with complex scenarios like sarcasm because they inherently neglect vital non-verbal information. While recent Vision-Language Models (VLMs) address this by analyzing video directly, they are not inherently tailored for ERC and often focus on emotionally irrelevant background regions or passive listeners rather than the active speaker. Furthermore, fine-tuning these large models incurs prohibitive computational costs. Additionally, isolated visual signals are frequently ambiguous or technically compromised without the context of linguistic content and vocal prosody. To address these challenges, we propose VISAFF, a speaker-centered VISual AFFective feature learning framework for ERC. VISAFF consists of two stages: Speaker-Centered Affective Grounding and Reliability-Guided Affective Complementation. VISAFF utilizes a tuning-free approach to unlock the reasoning capabilities of frozen VLMs, efficiently steering them to focus on the active speaker's emotional visual cues without heavy training overheads. In the second stage, we introduce a reliability-guided affective complementation mechanism that dynamically leverages textual and acoustic modalities to compensate for visual uncertainty. Experiments on two real-world datasets demonstrate that VISAFF achieves highly competitive performance compared to state-of-the-art methods in a tuning-free setting, significantly enhancing computational efficiency by eliminating the need for expensive fine-tuning of large VLMs. The source code is available at https://anonymous.4open.science/r/speaker-2365/.
arXiv (fysik & CS) Preprint 2026-05-19
InFeR: Informed Failure Resilience in Learned Visual Navigation Control
arXiv:2510.24680v2 Announce Type: replace Abstract: While imitation learning (IL) has enabled successful visual navigation in many common environments, IL policies are prone to unpredictable failures under out-of-distribution (OOD) scenarios. This necessitates failure-resilient policies, which not only detect failures, but also recognise their sources and recover from them autonomously. We propose InFeR, a general framework for building IL policies with informed failure resilience without failure or recovery demonstrations. InFeR retrains an IL policy with a Variational Information Bottleneck (VIB) loss to structure its latent space for OOD failure detection. It applies a visual explainability technique, Grad-CAM, to localise an image region as the source of failure and inform a heuristic policy for recovery. All these are achieved without requiring additional training data. Real-world experiments show that InFeR enables informed failure recovery across two different policy architectures, yielding robust long-range navigation in complex environments.
arXiv (fysik & CS) Preprint 2026-05-19
Emergent Thiemann coherent states in the near-kernel sector of quantum reduced loop gravity
arXiv:2605.18625v1 Announce Type: cross Abstract: We study the near-kernel sector of the Hamiltonian constraint operator in the one-vertex model of quantum reduced loop gravity using variational Monte Carlo methods with neural quantum states. The analysis is based on the symmetric Hamiltonian containing both Euclidean and Lorentzian contributions, and on the variational minimization of the positive quadratic operator $\hat{\mathcal Q}=\hat C \hat C^\dagger$ in truncated Hilbert spaces with spin cutoff up to $j_{\mathrm{max}}=1001$. The resulting near-kernel states are found to organize into three qualitatively distinct classes. At low cutoffs, we find solutions that do not factorize across the three edge degrees of freedom. At larger cutoffs, we find two different factorized branches, both described to very high accuracy by products of one-edge wavefunctions but localized in different spin regimes. One of these branches is matched with near-unit fidelity by reduced Thiemann coherent states, providing evidence for an emergent semiclassical organization of the near-kernel sector. The other is likewise strongly factorized, but its one-edge factors are not well described by the same coherent-state family.
arXiv (fysik & CS) Preprint 2026-05-19
Harmonious Colorings: bounds, heuristics and integer-linear formulations
arXiv:2605.18634v1 Announce Type: cross Abstract: A proper coloring $c$ of a simple graph $G$ is harmonious if, for every pair of distinct edges $uv,xy\in E(G)$, we have that $\{c(u),c(v)\}\neq \{c(x),c(y)\}$. The harmonious chromatic number of $G$, denoted by $h(G)$, is the least positive integer $k$ such that $G$ has a harmonious coloring with $k$ colors. In this work, we extend an idea presented in [Kolay, et al. Harmonious coloring: Parameterized algorithms and upper bounds. Theor. Comp. Sci. 772 (2019), 132-142] to compare the harmonious chromatic numbers of two graphs $G$ and $H$, with $H$ being obtained from $G$ by identifying vertices at distance at least three. Furthermore, by fixing a proof presented in the same work, we manage to improve one of its upper bounds. We also introduce and study the first, to the best of our knowledge, integer-linear programming formulations for this problem in the literature, along with some heuristics. We provide some preliminary tests on random instances and instances from the second DIMACS Implementation Challenge.
arXiv (fysik & CS) Preprint 2026-05-19
Statistical Limits and Efficient Algorithms for Differentially Private Federated Learning
arXiv:2605.18656v1 Announce Type: cross Abstract: Federated Learning is a leading framework for training ML and AI models collaboratively across numerous user devices or databases. We study the trade-offs among estimation accuracy, privacy constraints, and communication cost for differentially private (DP) federated M estimation. The two standard methods in the literature are FedAvg, which may suffer from high federation bias, and FedSGD, which can incur high communication cost. Aimed at improving accuracy at a reduced communication cost, we propose FedHybrid, which uses FedSGD starting with an improved initialization by the FedAvg estimator. We propose FedNewton, which averages local Newton iterations to reduce bias in FedAvg, achieving an estimation accuracy comparable to FedSGD with much fewer communication rounds when the number of clients grows sufficiently slowly. We establish finite sample upper bounds on the mean-squared error rates of the DP versions of these estimators as functions of the number of clients, local sample sizes, privacy budget, and number of iterations. We further derive a minimax lower bound on the MSE of any iterative private federated procedure that provides a benchmark to assess the optimality gap of these methods. We numerically evaluate our methods for training a logistic regression and a neural network on the computer vision datasets MNIST and CIFAR-10.
arXiv (fysik & CS) Preprint 2026-05-19
Optimising CSRNet with parameter-free attention mechanisms for crowd counting in public transport
arXiv:2605.18349v1 Announce Type: new Abstract: Occupancy estimation and crowd counting are critical tasks in designing smart and efficient public transport vehicles. Given that public transport loading can vary from sparse to crowded, classical models for occupancy estimation must be adapted to suit this purpose. Attention mechanisms have shown remarkable capability in enhancing the representational power of deep neural networks for crowd counting in congested scenes with occlusion, complex backgrounds, and perspective distortion. However, conventional approaches, often implemented as parameterized sub-networks within convolutional layers, inevitably increase model size and computational cost, limiting deployment on resource-constrained edge devices. This paper investigates the effectiveness of state-of-the-art parameter-free attention mechanisms for crowd counting and density map estimation in highly congested scenes. We evaluate channel-wise (PFCA), spatial-wise (SA), and 3-D (SimAM) modules and compare their performance with parameterized attention modules constrained to introduce no more than 1% additional parameters. Furthermore, we present a novel combination of attention mechanisms that combines the strengths of PFCA and SA (PFCASA) customized for analyzing video streams onboard public transport systems. Using CSRNet as the backbone, experiments on the ShanghaiTech dataset demonstrate that parameter-free attention mechanisms achieve comparable or superior accuracy without introducing additional model parameters. A detailed performance analysis further reveals that PFCASA outperforms other attention modules in scenes with fewer than 40 individuals, while PFCA shows greater effectiveness as crowd density increases, underscoring their potential applicability for integration into smart public transport modalities.
arXiv (fysik & CS) Preprint 2026-05-19
MEEDAV: A Synchronous Web Viewer for EEG, Eye-Tracking and Speech Data
arXiv:2605.18296v1 Announce Type: new Abstract: MEEDAV is an open-source web-based application for the synchronised visualisation of electroencephalography (EEG), eye-tracking, and audio data collected in psycholinguistic research. While originally developed for the Eyetracked Multi-Modal Translation (EMMT) corpus, which uses four-channel EEG data from the Muse 2 headband, MEEDAV also supports higher-density EEG setups thanks to its channel-agnostic processing pipeline. The system performs time alignment across all modalities and provides optional ICA-based EEG denoising. It features interactive Plotly visualisations, including unified EEG-audio-gaze timelines, gaze-intensity plots, event markers, and spatial heatmaps of fixation/saccade patterns. Researchers can filter by participant and stimulus, inspect raw versus cleaned signals, and compute cross-modal correlations. All processing is handled in real time, with a modular backend that supports local file access or GitHub-based streaming. Although initially tailored to the structure of the EMMT dataset, MEEDAV demonstrates a generalisable approach to multimodal data exploration and offers a lightweight, browser-accessible solution for cognitive neuroscience and translation studies.
arXiv (fysik & CS) Preprint 2026-05-19
A Hybrid Optimization Framework for Spatial Packaging of Interconnected Systems
arXiv:2605.17424v1 Announce Type: new Abstract: This paper presents an optimization framework for Spatial Packaging of Interconnected Systems with Physical Interactions (SPI2) that addresses the geometric challenges of three-dimensional component placement and routing. While SPI2 generally includes physical interactions, this study isolates the spatial optimization aspect to evaluate placement and routing performance independently. The framework integrates the Maximal Disjoint Ball Decomposition (MDBD) for geometric abstraction with a hybrid optimization strategy that combines stochastic initialization and gradient-based refinement with interior point optimization. It is formulated to handle the nonlinear, non-convex, and continuous characteristics of spatially coupled design problems. The proposed framework is evaluated against a use case from prior SPI2 research and tested with a newly introduced benchmark that enables verifiable assessment of optimization performance. Results indicate that the presented method achieves more than a 10% improvement over existing SPI2 implementations and converges to spatially analytical optima across various benchmark scenarios. Benchmark experiments show solution accuracy of 0.6-2% relative to the ground truth.
arXiv (fysik & CS) Preprint 2026-05-19
Universal Jaynes-Cummings Control of an Oscillator
arXiv:2605.18658v1 Announce Type: cross Abstract: The Jaynes-Cummings (JC) interaction-the coherent exchange of excitations between a two-level system and a harmonic oscillator-is one of the fundamental interactions of quantum optics, realized across platforms such as cavity quantum electrodynamics, trapped ions, mechanical resonators, and superconducting circuits. Although JC interactions and qubit rotations form a universal gate set for oscillator control, practical implementations have not been demonstrated. Here we develop and experimentally demonstrate universal JC-based oscillator control by compiling arbitrary unitary gates into sequences of JC interactions and qubit rotations. In our experiment, the oscillator is realized using a mode of a high quality factor microwave cavity and the ancilla qubit using a superconducting transmon circuit, with the JC interaction implemented by a sideband interaction enabled by the Josephson nonlinearity. The native gates are constructed to be closed below a chosen cutoff photon number, encoding a qudit with suppressed leakage errors, while ancilla relaxation errors are detectable. We further find that the dispersive shift serves as a compilation resource that reduces circuit depths. We demonstrate universal qudit control and implement a single-qutrit gate set with a mean post-selected process fidelity of 96%, as well as ququart and ququint shift gates. These results establish Jaynes-Cummings control as a practical route to universal oscillator control, enabling programmable bosonic processors across a variety of quantum platforms.
arXiv (fysik & CS) Preprint 2026-05-19
PIPER: Content-Based Table Search via profiling and LLM-Generated Pseudoqueries
arXiv:2605.18199v1 Announce Type: new Abstract: The rapid growth of tabular datasets in data lakes, data spaces, and open data portals makes effective dataset search essential for reuse and analysis. Existing search systems rely mainly on metadata, which is often incomplete or low quality, especially for tables whose meaning depends on both schema and cell values. Recent advances in Large Language Models (LLMs) enable richer, content-based representations of tables. However, prior LLM-based retrieval methods have focused on Table Question Answering, where the goal is to select a single table to answer a question, rather than retrieve and rank relevant datasets. We propose PIPER, a content-driven retrieval method for tabular datasets that uses table profiles and LLM-generated queries embedded for dense retrieval. Designed for dataset search in poor-metadata settings, PIPER outperforms both classical metadata-based baselines and strong TableQA retrieval methods, demonstrating the value of LLM-based content modeling for tabular dataset search.
arXiv (fysik & CS) Preprint 2026-05-19
ReBaR: Reference-Based Reasoning for Robust Pose Estimation from Monocular Images
arXiv:2303.11675v3 Announce Type: replace Abstract: R}easoning for Robust Human Pose and Shape Estimation), designed to estimate human body shape and pose from single-view images. ReBaR effectively addresses the challenges of occlusions and depth ambiguity by learning reference features for part regression reasoning. Our approach starts by extracting features from both body and part regions using an attention-guided mechanism. Subsequently, these features are used to encode additional part-body dependencies for individual part regression, with part features serving as queries and the body feature as a reference. This reference-based reasoning allows our network to infer the spatial relationships of occluded parts with the body, utilizing visible parts and body reference information. ReBaR outperforms contemporary methods on three benchmark datasets and still maintains competitive advantages among recent new approaches. Demonstrating significant improvement in handling depth ambiguity and occlusion. These results strongly support the effectiveness of our reference-based framework for estimating human body shape and pose from single-view images.
arXiv (fysik & CS) Preprint 2026-05-19
Usenix'23 Extended Version: Smart Learning to Find Dumb Contracts
arXiv:2304.10726v3 Announce Type: replace Abstract: We introduce the Deep Learning Vulnerability Analyzer (DLVA) for Ethereum smart contracts based on neural networks. We train DLVA to judge bytecode even though the supervising oracle can only judge source. DLVA's training algorithm is general: we extend a source code analysis to bytecode without any manual feature engineering, predefined patterns, or expert rules. DLVA's training algorithm is also robust: it overcame a 1.25% error rate mislabeled contracts, and--the student surpassing the teacher--found vulnerable contracts that Slither mislabeled. DLVA is much faster than other smart contract vulnerability detectors: DLVA checks contracts for 29 vulnerabilities in 0.2 seconds, a 10-1,000x speedup. DLVA has three key components. First, Smart Contract to Vector (SC2V) uses neural networks to map smart contract bytecode to a high-dimensional floating-point vector. We benchmark SC2V against 4 state-of-the-art graph neural networks and show that it improves model differentiation by 2.2%. Second, Sibling Detector (SD) classifies contracts when a target contract's vector is Euclidian-close to a labeled contract's vector in a training set; although only able to judge 55.7% of the contracts in our test set, it has a Slither-predictive accuracy of 97.4% with a false positive rate of only 0.1%. Third, Core Classifier (CC) uses neural networks to infer vulnerable contracts regardless of vector distance. We benchmark DLVA's CC with 10 ML techniques and show that the CC improves accuracy by 11.3%. Overall, DLVA predicts Slither's labels with an overall accuracy of 92.7% and associated false positive rate of 7.2%. Lastly, we benchmark DLVA against nine well-known smart contract analysis tools. Despite using much less analysis time, DLVA completed every query, leading the pack with an average accuracy of 99.7%, pleasingly balancing high true positive rates with low false positive rates.
arXiv (fysik & CS) Preprint 2026-05-19
Human-Flow Digital Twin for Predicting the Effects of Mobility Introduction on Visitor Circulation
arXiv:2605.17426v1 Announce Type: new Abstract: We propose a framework for predicting the effects of mobility introduction measures using a human-flow digital twin. This digital twin incorporates a multi-agent simulator that can represent how visitors choose destinations depending on factors such as their current location and the attractiveness of spots. We extract data on how visitors selected destinations with respect to measured pre-intervention human-flow data, inter-spot distances, spot attractiveness, and travel volumes, and use these data to train each agent's decision model of this simulator. The trained decision model is a function that takes a visitor's current state and surrounding environmental information as input and outputs which spot the visitor will move toward next. By expressing mobility introduction measures as changes to inter-point distances or to spot attractiveness, the framework can reproduce human flows with mobility introduction in the multi-agent simulator and thereby quantify effects such as changes in visitor counts and circulation. We evaluated the proposed method using human-flow data measured with and without introducing mobility within Wakayama Castle Park in Japan. When reproducing flows with mobility introduction using a multi-layer perceptron decision model, the cosine similarity of the spatial population distribution exceeded 0.7, confirming that the approach can replicate the flow changes caused by the mobility introduction.
arXiv (fysik & CS) Preprint 2026-05-19
SeamlessEdit: Background Noise Aware Zero-Shot Speech Editing with in-Context Enhancement
arXiv:2505.14066v3 Announce Type: replace-cross Abstract: With the fast development of zero-shot text-to-speech technologies, it is possible to generate high-quality speech signals that are indistinguishable from the real ones. Speech editing, including speech insertion and replacement, appeals to researchers due to its potential applications. However, existing studies only considered clean speech scenarios. In real-world applications, the existence of environmental noise could significantly degrade the quality of generation. In this study, we propose a noise-resilient speech editing framework, SeamlessEdit, for noisy speech editing. SeamlessEdit adopts a frequency-band-aware noise suppression module and an in-content refinement strategy. It can well address the scenario where the frequency bands of voice and background noise are not separated. The proposed SeamlessEdit framework outperforms state-of-the-art approaches in multiple quantitative and qualitative evaluations.
arXiv (fysik & CS) Preprint 2026-05-19
Revisiting Long-term Time Series Forecasting: An Investigation on Linear Mapping
arXiv:2305.10721v2 Announce Type: replace Abstract: Introduction: Long-term time series forecasting (LTSF) has gained significant attention in recent years. While various specialized designs exist for capturing temporal dependency, recent studies have shown that even a single linear layer can achieve competitive performance. This paper investigates the intrinsic effectiveness of recent LTSF approaches and reveals the critical role of affine mapping. Materials and methods: We conduct comprehensive experiments on both simulated and real-world datasets to analyze the components of state-of-the-art models. A theoretical analysis is provided to explain the working mechanisms of affine mapping in periodic signal forecasting. We evaluate the impact of reversible normalization and input horizon extension on model robustness. Results: We find that (1) affine mapping dominates forecasting performance across commonly utilized benchmarks, with models learning similar transition matrices from input to output; (2) affine mapping effectively captures periodic patterns but struggles with non-periodic signals or time series with varying periods across channels; (3) reversible normalization significantly enhances trend forecasting by transforming non-periodic trends into periodic-like patterns; (4) increasing input horizon improves performance on multi-channel data with different periods. Code is available at: \url{https://github.com/plumprc/RTSF}. Conclusions: Our findings provide theoretical and experimental insights into the working mechanisms of LTSF models, highlighting both the strengths and limitations of linear approaches. The results suggest that future model development should focus on handling cross-channel period variations and non-periodic components.
arXiv (fysik & CS) Preprint 2026-05-19
Corruptions of Supervised Learning Problems: Typology and Mitigations
arXiv:2307.08643v4 Announce Type: replace Abstract: Corruption is notoriously widespread in data collection. Despite extensive research, the existing literature predominantly focuses on specific settings and learning scenarios, lacking a unified view of corruption modelization and mitigation. In this work, we develop a general theory of corruption, which incorporates all modifications to a supervised learning problem, including changes in model class and loss. Focusing on changes to the underlying probability distributions via Markov kernels, our approach leads to three novel opportunities. First, it enables the construction of a novel, provably exhaustive corruption framework, distinguishing among different corruption types. This serves to unify existing models and establish a consistent nomenclature. Second, it facilitates a systematic analysis of corruption's consequences on learning tasks, by comparing Bayes risks in the clean and corrupted scenarios. Notably, while label corruptions affect only the loss function, attribute corruptions additionally influence the hypothesis class. Third, building upon these results, we investigate mitigations for various corruption types. We expand existing loss-correction methods for label corruption to handle dependent corruption types. Our findings highlight the necessity to generalize this classical corruption-corrected learning framework to a new paradigm with weaker requirements to encompass more corruption types. We provide such a paradigm as well as loss correction formulas in the attribute and joint corruption cases.
arXiv (fysik & CS) Preprint 2026-05-19
Progressive Generalization Augmentation with Deeply Coupled RND-PPO and Domain-Prioritized Noise Injection for Robust Crop Management Reinforcement Learning
arXiv:2605.17428v1 Announce Type: new Abstract: Our preliminary experiments on gym-DSSAT maize irrigation tasks revealed that +/-2 degrees C temperature noise causes an 11.9% reduction in economic returns for PPO policies trained under clean conditions - a systematic robustness deficit that existing research has not adequately addressed. This paper tackles three interconnected limitations impeding practical deployment of agricultural RL systems: the trade-off between early-stage learning efficiency and late-stage generalization capability; the naive additive combination of intrinsic and extrinsic rewards in exploration-augmented PPO; and uniform measurement noise injection strategies that disregard empirically validated differential sensitivity across agricultural state variables. We introduce three systematic innovations: Progressive Generalization Augmentation (PGA) implementing a three-phase curriculum (clean training 0-800 episodes, progressive 800-1200, full augmentation 1200-2000); a deeply coupled RND-PPO architecture with dual-channel GAE normalization, progress-decayed intrinsic coefficients, and semantic discretization; and domain-prioritized noise injection with hierarchical activation. Our experimental evaluation demonstrates: 8.43% yield improvement and 16.42% nitrogen use efficiency improvement over SOTA BERT-DQN in Florida; 5.61% yield improvement in Zaragoza (though 3.67% lower economic score due to challenging Mediterranean climate); and 94.4% vs 80.0% performance retention under combined perturbations. All experiments used 5 random seeds on NVIDIA A100 GPUs with 4.2+/-0.3 hours per run (2000 episodes, 2048-step buffer, 64 mini-batch size).
arXiv (fysik & CS) Preprint 2026-05-19
The Normal Distributions Indistinguishability Spectrum and its Application to Privacy-Preserving Machine Learning
arXiv:2309.01243v4 Announce Type: replace Abstract: We investigate the privacy of {\em any} algorithm whose outputs have Gaussian distribution. This work is motivated by the prevalence of such algorithms in several useful (ML) applications, and the comparatively little research that focuses on privacy-preserving learning outside of adding Gaussian noise to the data (such as DP-SGD). {\em What is the DP of any algorithm with multivariate Gaussian output?} We answer the above research question with a general lemma which we call {\em Normal Distributions Indistinguishability Spectrum} (NDIS), a closed-form analytic computation of the hockey-stick divergence $\delta$ between an arbitrary pair of multivariate Gaussians, parameterized by privacy parameter $\epsilon$. To show its practical implications, we prove several properties of our NDIS lemma. These properties form a {\em toolbox} of results which lead to potentially {\em easier} privacy proofs for any Gaussian-output algorithm. As an example application of our toolbox, we prove a tighter parametrisation of the privacy of {\em random projection (RP)}, and obtaining from it a more noise-frugal DP mechanism. Beyond random projection, NDIS can be used to lift {\em any} Gaussian-output algorithm with a `sensitivity' (which we define) to a Gaussian-output DP mechanism. The mechanism boosts the existing randomness in the algorithm, so that one can describe the mechanism's privacy as the IS between a single pair of Gaussians, which can then be analyzed via NDIS. Lastly, we leverage the connections between NDIS and the CDF of the generalized $\chi^2$ distribution (which have efficient empirical estimators) to present a tool for white-box auditing of Gaussian-output algorithms.
arXiv (fysik & CS) Preprint 2026-05-19
Lightweight CNN-Based DDoS Detection for Resource-Constrained Edge Networks
arXiv:2309.05646v2 Announce Type: replace Abstract: Distributed Denial of Service (DDoS) attacks remain a persistent threat to the availability of Internet services, edge networks, and cyber-physical infrastructure. Although recent AI-security work has increasingly focused on foundation models, autonomous agents, and adversarial robustness, many operational defense tasks still require low-latency classification close to the network edge, where cloud-scale analysis may be too slow or expensive. This paper presents a lightweight supervised deep learning approach for DDoS detection using a convolutional neural network (CNN) trained on packet-flow representations derived from the CIC-DDoS2019 benchmark dataset. The proposed pipeline extracts packet flows from PCAP traffic, normalizes them to fixed-length representations, and classifies each flow as benign or malicious using a compact CNN architecture with convolution, dropout, pooling, and sigmoid classification layers. On a held-out test set of previously unseen flows, the model achieves 0.9883 accuracy, 0.9864 precision, 0.9784 recall, and 0.9824 F1 score, while processing the evaluated test flows in 0.28 seconds. These results suggest that compact neural models can provide useful early-warning signals for edge-oriented DDoS detection. We further discuss deployment constraints, benchmark limitations, and future directions for cross-dataset evaluation, hardware-aware profiling, and integration with mitigation pipelines.
arXiv (fysik & CS) Preprint 2026-05-19
Achieving Linear Speedup with ProxSkip in Distributed Stochastic Optimization
arXiv:2310.07983v5 Announce Type: replace Abstract: The ProxSkip algorithm for distributed optimization is gaining increasing attention due to its effectiveness in reducing communication. However, existing analyses of ProxSkip are limited to the strongly convex setting and fail to achieve linear speedup with respect to the number of nodes. Key questions regarding its behavior in the non-convex setting and the achievability of linear speedup remain open. In this paper, we revisit decentralized ProxSkip and answer these questions affirmatively. We provide a unified convergence analysis for stochastic non-convex, convex, and strongly convex problems, revealing how gradient noise, local updates, network connectivity, and data heterogeneity jointly determine the convergence behavior. To the best of our knowledge, this is the first analysis showing that decentralized ProxSkip achieves linear speedup in the number of nodes under stochastic gradients. Moreover, our results demonstrate that local updates can effectively reduce communication frequency and improve communication efficiency.