Search

The main purpose of this paper is to present new and more uniform model-theoretic/combinatorial proofs of the theorems (in [5] and [4]): The randomization $T^{R}$ of a complete first-order theory $T$ with $NIP$/stability is a (complete) first-order continuous theory with $NIP$/stability. The proof method for both theorems is based on the significant use of a particular type of models of $T^{R}$, namely simple models, and certain indiscernible arrays. Using simple models of $T^R$ gives the advantage of re-proving these theorems in a simpler and quantitative manner. We finally turn our attention to $NSOP$ in randomization. We show that based on the definition of $NSOP$ given [11], $T^R$ is stable if and only if it is $NIP$ and $NSOP$., Comment: 21 pages. Comments welcome. k.khanaki @ gmail.com

Superconducting flip-chip interconnects are crucial for the three-dimensional integration of superconducting circuits in sensing and quantum technology applications. We demonstrate a simplified approach for a superconducting flip-chip device using commercially available indium microspheres and an in-house-built transfer stage for bonding two chips patterned with superconducting thin films. We use a gold-passivated niobium or niobium nitride layer as an under-bump metallization (UBM) layer between an aluminum-based superconducting wiring layer and the indium interconnect. At millikelvin temperatures, our flip-chip assembly can transport a supercurrent with tens of milliamperes, limited by the smallest geometric feature size and critical current density of the UBM layer and not by the indium interconnect. We show that the pressed indium interconnect itself can carry a supercurrent exceeding 1A due to its large size of about 500 micrometer diameter. Our flip-chip assembly does not require electroplating nor patterning of indium. The assembly process does not need a flip-chip bonder and can be realized with a transfer stage using a top chip with transparency or through-vias for alignment. These flip-chip devices can be utilized in applications that require few superconducting interconnects carrying large currents at millikelvin temperatures., Comment: 12 pages, 8 figures incl supplemental material

It is known from the work of Koch that the two-dimensional incompressible Euler equations propagate Dini modulus of continuity for the vorticity. In this work, we consider the two-dimensional Euler equations with a modulus of continuity for vorticity rougher than Dini continuous. We first show that the two-dimensional Euler equations propagate an explicit family of moduli of continuity for the vorticity that are rougher than Dini continuity. The main goal of this work is to address the following question: Given a modulus of continuity for the 2D Euler equations, can we always propagate it? The answer to this question is \textit{No}. We construct a family of moduli of continuity for the 2D Euler equations that are \textit{not} propagated.

In Gasket Assembly, a deformable gasket must be aligned and pressed into a narrow channel. This task is common for sealing surfaces in the manufacturing of automobiles, appliances, electronics, and other products. Gasket Assembly is a long-horizon, high-precision task and the gasket must align with the channel and be fully pressed in to achieve a secure fit. To compare approaches, we present 4 methods for Gasket Assembly: one policy from deep imitation learning and three procedural algorithms. We evaluate these methods with 100 physical trials. Results suggest that the Binary+ algorithm succeeds in 10/10 on the straight channel whereas the learned policy based on 250 human teleoperated demonstrations succeeds in 8/10 trials and is significantly slower. Code, CAD models, videos, and data can be found at https://berkeleyautomation.github.io/robot-gasket/, Comment: Content without Appendix accepted for IEEE CASE 2024

The research was conducted at the College of Agricultural Sciences Engineering/University of Sulaimani/ Kurdistan Region-Iraqi to investigate effects of different concentrations of IBA (0, 3000, 4000 and 5000 ppm) and soaking in water for 24 hours on propagation black mulberry (Morus nigra L.) by hardwood cuttings. In this research the parameters of rooting percentage, root number, root length, sprout bud number, shoot length and shoot diameter were measured. Effect of individual factors showed that the highest rooting percentage (15%) was achieved in cuttings soaked in water for 24 hours, as well as improving other traits. Also, the best (23.33%) rooting was found in cuttings dipped in 4000 ppm IBA. Interaction effects of the two factors showed that cuttings treated with 4000 ppm IBA and soaked in water for 24 hours gave the highest (40%) rooting, and the highest other root and shoot traits were achieved in the same interaction as well.

The transition matrix, frequently abbreviated as T-matrix, contains the complete information in a linear approximation of how a spatially localized object scatters an incident field. The T-matrix is used to study the scattering response of an isolated object and describes the optical response of complex photonic materials made from ensembles of individual objects. T-matrices of certain common structures, potentially, have been repeatedly calculated all over the world again and again. This is not necessary and constitutes a major challenge for various reasons. First, the resources spent on their computation represent an unsustainable financial and ecological burden. Second, with the onset of machine learning, data is the gold of our era, and it should be freely available to everybody to address novel scientific challenges. Finally, the possibility of reproducing simulations could tremendously improve if the considered T-matrices could be shared. To address these challenges, we found it important to agree on a common data format for T-matrices and to enable their collection from different sources and distribution. This document aims to develop the specifications for storing T-matrices and associated metadata. The specifications should allow maximum freedom to accommodate as many use cases as possible without introducing any ambiguity in the stored data. The common format will assist in setting up a public database of T-matrices., Comment: This is a revised version of the article as submitted to the Journal of Quantitative Spectroscopy and Radiative Transfer that was finally published there

Social media platforms continue to change our digital relationships nowadays. Therefore, recognizing the complex consequences of infinite scrolling is essential. This paper explores two distinct angles of social media engagement: mindless scrolling and mindful scrolling. This extensive study dives into numerous aspects of social media user behavior and satisfaction via the perspective of multiple surveys. We investigate the psychological exploit of infinite scrolling design to keep users engaged, illuminating its effect on users' emotional well-being. Furthermore, we explore its diverse effects on various groups, such as teenagers, professional people, and pregnant women, to better understand how digital activity differs throughout life phases. Furthermore, our study reveals the psychological consequences of being exposed to unfavorable news material. In the context of nutritional objectives, we examine the problems users confront as well as the significance of scrolling in dietary achievement. By taking into account the demographic effect, we can determine how factors like age, gender, and socioeconomic position affect user behavior. This study presents a comprehensive knowledge of the complicated connection of infinite scrolling with user satisfaction and psychological well-being through a variety of surveys, opening the door for well-informed conversations on online engagement., Comment: under review

Cross-lingual summarization (CLS) is a sophisticated branch in Natural Language Processing that demands models to accurately translate and summarize articles from different source languages. Despite the improvement of the subsequent studies, This area still needs data-efficient solutions along with effective training methodologies. To the best of our knowledge, there is no feasible solution for CLS when there is no available high-quality CLS data. In this paper, we propose a novel data-efficient approach, ConVerSum, for CLS leveraging the power of contrastive learning, generating versatile candidate summaries in different languages based on the given source document and contrasting these summaries with reference summaries concerning the given documents. After that, we train the model with a contrastive ranking loss. Then, we rigorously evaluate the proposed approach against current methodologies and compare it to powerful Large Language Models (LLMs)- Gemini, GPT 3.5, and GPT 4o proving our model performs better for low-resource languages' CLS. These findings represent a substantial improvement in the area, opening the door to more efficient and accurate cross-lingual summarizing techniques.

The recent monkeypox outbreak has raised significant public health concerns due to its rapid spread across multiple countries. Monkeypox can be difficult to distinguish from chickenpox and measles in the early stages because the symptoms of all three diseases are similar. Modern deep learning algorithms can be used to identify diseases, including COVID-19, by analyzing images of the affected areas. In this study, we introduce a lightweight model that merges two pre-trained architectures, EfficientNetV2B3 and ResNet151V2, to classify human monkeypox disease. We have also incorporated the squeeze-and-excitation attention network module to focus on the important parts of the feature maps for classifying the monkeypox images. This attention module provides channels and spatial attention to highlight significant areas within feature maps. We evaluated the effectiveness of our model by extensively testing it on a publicly available Monkeypox Skin Lesions Dataset using a four-fold cross-validation approach. The evaluation metrics of our model were compared with the existing others. Our model achieves a mean validation accuracy of 96.52%, with precision, recall, and F1-score values of 96.58%, 96.52%, and 96.51%, respectively., Comment: 6 pages with 6 figures

Mosquito-related diseases pose a significant threat to global public health, necessitating efficient and accurate mosquito classification for effective surveillance and control. This work presents an innovative approach to mosquito classification by leveraging state-of-the-art vision transformers and open-set learning techniques. A novel framework has been introduced that integrates Transformer-based deep learning models with comprehensive data augmentation and preprocessing methods, enabling robust and precise identification of ten mosquito species. The Swin Transformer model achieves the best performance for traditional closed-set learning with 99.80% accuracy and 0.998 F1 score. The lightweight MobileViT technique attains an almost similar accuracy of 98.90% with significantly reduced parameters and model complexities. Next, the applied deep learning models' adaptability and generalizability in a static environment have been enhanced by using new classes of data samples during the inference stage that have not been included in the training set. The proposed framework's ability to handle unseen classes like insects similar to mosquitoes, even humans, through open-set learning further enhances its practical applicability by employing the OpenMax technique and Weibull distribution. The traditional CNN model, Xception, outperforms the latest transformer with higher accuracy and F1 score for open-set learning. The study's findings highlight the transformative potential of advanced deep-learning architectures in entomology, providing a strong groundwork for future research and development in mosquito surveillance and vector control. The implications of this work extend beyond mosquito classification, offering valuable insights for broader ecological and environmental monitoring applications., Comment: 23 pages, 15 figures

Vulnerability Detection (VD) using machine learning faces a significant challenge: the vast diversity of vulnerability types. Each Common Weakness Enumeration (CWE) represents a unique category of vulnerabilities with distinct characteristics, code semantics, and patterns. Treating all vulnerabilities as a single label with a binary classification approach may oversimplify the problem, as it fails to capture the nuances and context-specific to each CWE. As a result, a single binary classifier might merely rely on superficial text patterns rather than understanding the intricacies of each vulnerability type. Recent reports showed that even the state-of-the-art Large Language Model (LLM) with hundreds of billions of parameters struggles to generalize well to detect vulnerabilities. Our work investigates a different approach that leverages CWE-specific classifiers to address the heterogeneity of vulnerability types. We hypothesize that training separate classifiers for each CWE will enable the models to capture the unique characteristics and code semantics associated with each vulnerability category. To confirm this, we conduct an ablation study by training individual classifiers for each CWE and evaluating their performance independently. Our results demonstrate that CWE-specific classifiers outperform a single binary classifier trained on all vulnerabilities. Building upon this, we explore strategies to combine them into a unified vulnerability detection system using a multiclass approach. Even if the lack of large and high-quality datasets for vulnerability detection is still a major obstacle, our results show that multiclass detection can be a better path toward practical vulnerability detection in the future. All our models and code to produce our results are open-sourced.

This research focused on enhancing post-incident malware forensic investigation using reinforcement learning RL. We proposed an advanced MDP post incident malware forensics investigation model and framework to expedite post incident forensics. We then implement our RL Malware Investigation Model based on structured MDP within the proposed framework. To identify malware artefacts, the RL agent acquires and examines forensics evidence files, iteratively improving its capabilities using Q Table and temporal difference learning. The Q learning algorithm significantly improved the agent ability to identify malware. An epsilon greedy exploration strategy and Q learning updates enabled efficient learning and decision making. Our experimental testing revealed that optimal learning rates depend on the MDP environment complexity, with simpler environments benefiting from higher rates for quicker convergence and complex ones requiring lower rates for stability. Our model performance in identifying and classifying malware reduced malware analysis time compared to human experts, demonstrating robustness and adaptability. The study highlighted the significance of hyper parameter tuning and suggested adaptive strategies for complex environments. Our RL based approach produced promising results and is validated as an alternative to traditional methods notably by offering continuous learning and adaptation to new and evolving malware threats which ultimately enhance the post incident forensics investigations., Comment: 21 pages

Virtual interventions enable the physics-based simulation of device deployment within coronary arteries. This framework allows for counterfactual reasoning by deploying the same device in different arterial anatomies. However, current methods to create such counterfactual arteries face a trade-off between controllability and realism. In this study, we investigate how Latent Diffusion Models (LDMs) can custom synthesize coronary anatomy for virtual intervention studies based on mid-level anatomic constraints such as topological validity, local morphological shape, and global skeletal structure. We also extend diffusion model guidance strategies to the context of morpho-skeletal conditioning and propose a novel guidance method for continuous attributes that adaptively updates the negative guiding condition throughout sampling. Our framework enables the generation and editing of coronary anatomy in a controllable manner, allowing device designers to derive mechanistic insights regarding anatomic variation and simulated device deployment., Comment: Accepted to ECCV 2024

Insulating antiferromagnets are anticipated as the main protagonists of ultrafast spintronics, with their intrinsic terahertz dynamics and their abililty to transport spin information over long distances. However, direct transfer of spin angular momentum to an antiferromagnetic insulator at picosecond time scales remains to be demonstrated. Here, studying the ultrafast behaviour of ferromagnetic metal/antiferromagnetic insulator bilayers, we evidence the generation of coherent excitations in the antiferromagnet combined with a modulation of the demagnetization behavior of the ferromagnet. This confirms that magnetic information can indeed be propagated into antiferromagnetic spin waves at picosecond timescales, thereby opening an avenue towards ultrafast manipulation of magnetic information.

This research examines whether sentiments conveyed in the State Bank of Pakistan's (SBP) communications impact financial market expectations and can act as a monetary policy tool. To achieve our goal, we first use sentiment analysis techniques to quantify the tone of SBP monetary policy documents and second, we use short time window, high frequency methodology to approximate the impact of tone on stock market returns. Our results show that positive (negative) change in the tone positively (negatively) impacts stock returns in Karachi Stock Exchange. Further extension shows that the communication of SBP still has a statistically significant impact on stock returns when controlling for different variables and monetary policy tool. Also, the communication of SBP does not have a long term constant effect on stock market.

Machine learning applications on signals such as computer vision or biomedical data often face significant challenges due to the variability that exists across hardware devices or session recordings. This variability poses a Domain Adaptation (DA) problem, as training and testing data distributions often differ. In this work, we propose Spatio-Temporal Monge Alignment (STMA) to mitigate these variabilities. This Optimal Transport (OT) based method adapts the cross-power spectrum density (cross-PSD) of multivariate signals by mapping them to the Wasserstein barycenter of source domains (multi-source DA). Predictions for new domains can be done with a filtering without the need for retraining a model with source data (test-time DA). We also study and discuss two special cases of the method, Temporal Monge Alignment (TMA) and Spatial Monge Alignment (SMA). Non-asymptotic concentration bounds are derived for the mappings estimation, which reveals a bias-plus-variance error structure with a variance decay rate of $\mathcal{O}(n_\ell^{-1/2})$ with $n_\ell$ the signal length. This theoretical guarantee demonstrates the efficiency of the proposed computational schema. Numerical experiments on multivariate biosignals and image data show that STMA leads to significant and consistent performance gains between datasets acquired with very different settings. Notably, STMA is a pre-processing step complementary to state-of-the-art deep learning methods.

In recent years, there has been a growing focus on scrutinizing the security of cellular networks, often attributing security vulnerabilities to issues in the underlying protocol design descriptions. These protocol design specifications, typically extensive documents that are thousands of pages long, can harbor inaccuracies, underspecifications, implicit assumptions, and internal inconsistencies. In light of the evolving landscape, we introduce CellularLint--a semi-automatic framework for inconsistency detection within the standards of 4G and 5G, capitalizing on a suite of natural language processing techniques. Our proposed method uses a revamped few-shot learning mechanism on domain-adapted large language models. Pre-trained on a vast corpus of cellular network protocols, this method enables CellularLint to simultaneously detect inconsistencies at various levels of semantics and practical use cases. In doing so, CellularLint significantly advances the automated analysis of protocol specifications in a scalable fashion. In our investigation, we focused on the Non-Access Stratum (NAS) and the security specifications of 4G and 5G networks, ultimately uncovering 157 inconsistencies with 82.67% accuracy. After verification of these inconsistencies on open-source implementations and 17 commercial devices, we confirm that they indeed have a substantial impact on design decisions, potentially leading to concerns related to privacy, integrity, availability, and interoperability., Comment: Accepted at USENIX Security 24

Semantic Textual Relatedness holds significant relevance in Natural Language Processing, finding applications across various domains. Traditionally, approaches to STR have relied on knowledge-based and statistical methods. However, with the emergence of Large Language Models, there has been a paradigm shift, ushering in new methodologies. In this paper, we delve into the investigation of sentence-level STR within Track A (Supervised) by leveraging fine-tuning techniques on the RoBERTa transformer. Our study focuses on assessing the efficacy of this approach across different languages. Notably, our findings indicate promising advancements in STR performance, particularly in Latin languages. Specifically, our results demonstrate notable improvements in English, achieving a correlation of 0.82 and securing a commendable 19th rank. Similarly, in Spanish, we achieved a correlation of 0.67, securing the 15th position. However, our approach encounters challenges in languages like Arabic, where we observed a correlation of only 0.38, resulting in a 20th rank., Comment: 10 pages, 9 figures, 4 tables

Deep learning holds immense promise for aiding radiologists in breast cancer detection. However, achieving optimal model performance is hampered by limitations in availability and sharing of data commonly associated to patient privacy concerns. Such concerns are further exacerbated, as traditional deep learning models can inadvertently leak sensitive training information. This work addresses these challenges exploring and quantifying the utility of privacy-preserving deep learning techniques, concretely, (i) differentially private stochastic gradient descent (DP-SGD) and (ii) fully synthetic training data generated by our proposed malignancy-conditioned generative adversarial network. We assess these methods via downstream malignancy classification of mammography masses using a transformer model. Our experimental results depict that synthetic data augmentation can improve privacy-utility tradeoffs in differentially private model training. Further, model pretraining on synthetic data achieves remarkable performance, which can be further increased with DP-SGD fine-tuning across all privacy guarantees. With this first in-depth exploration of privacy-preserving deep learning in breast imaging, we address current and emerging clinical privacy requirements and pave the way towards the adoption of private high-utility deep diagnostic models. Our reproducible codebase is publicly available at https://github.com/RichardObi/mammo_dp., Comment: Early Accept at MICCAI 2024 Deep-Breath Workshop

Recent works of the authors have demonstrated the usefulness of considering moduli spaces of Artinian reductions of a given ring when studying standard graded rings and their Lefschetz properties. This paper illuminates a key aspect of these works, the behaviour of the canonical module under deformations in this moduli space. We demonstrate that even when there is no natural geometry around, we can give a viewpoint that behaves like it, effectively constructing geometry out of nothing, giving interpretation to intersection numbers without cycles. Moreover, we explore some properties of this normalization., Comment: 30 pages

Detecting Machine-Generated Text (MGT) has emerged as a significant area of study within Natural Language Processing. While language models generate text, they often leave discernible traces, which can be scrutinized using either traditional feature-based methods or more advanced neural language models. In this research, we explore the effectiveness of fine-tuning a RoBERTa-base transformer, a powerful neural architecture, to address MGT detection as a binary classification task. Focusing specifically on Subtask A (Monolingual-English) within the SemEval-2024 competition framework, our proposed system achieves an accuracy of 78.9% on the test dataset, positioning us at 57th among participants. Our study addresses this challenge while considering the limited hardware resources, resulting in a system that excels at identifying human-written texts but encounters challenges in accurately discerning MGTs., Comment: 8 pages, 3 figures, 2 tables. Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)

We present an efficient method for adapting a monolingual Large Language Model (LLM) to another language, addressing challenges of catastrophic forgetting and tokenizer limitations. We focus this study on adapting Llama 2 to Arabic. Our two-stage approach begins with expanding the vocabulary and training only the embeddings matrix, followed by full model continual pre-training on a bilingual corpus. By continually pre-training on a mix of Arabic and English corpora, the model retains its proficiency in English while acquiring capabilities in Arabic. Our approach results in significant improvements in Arabic and slight enhancements in English, demonstrating cost-effective cross-lingual transfer. We perform ablations on embedding initialization techniques, data mix ratios, and learning rates and release a detailed training recipe. To demonstrate generalizability of this approach we also adapted Llama 3 8B to Arabic and Llama 2 13B to Hindi.

Recent studies have revealed the vulnerability of deep neural networks (DNNs) to various backdoor attacks, where the behavior of DNNs can be compromised by utilizing certain types of triggers or poisoning mechanisms. State-of-the-art (SOTA) defenses employ too-sophisticated mechanisms that require either a computationally expensive adversarial search module for reverse-engineering the trigger distribution or an over-sensitive hyper-parameter selection module. Moreover, they offer sub-par performance in challenging scenarios, e.g., limited validation data and strong attacks. In this paper, we propose Neural mask Fine-Tuning (NFT) with an aim to optimally re-organize the neuron activities in a way that the effect of the backdoor is removed. Utilizing a simple data augmentation like MixUp, NFT relaxes the trigger synthesis process and eliminates the requirement of the adversarial search module. Our study further reveals that direct weight fine-tuning under limited validation data results in poor post-purification clean test accuracy, primarily due to overfitting issue. To overcome this, we propose to fine-tune neural masks instead of model weights. In addition, a mask regularizer has been devised to further mitigate the model drift during the purification process. The distinct characteristics of NFT render it highly efficient in both runtime and sample usage, as it can remove the backdoor even when a single sample is available from each class. We validate the effectiveness of NFT through extensive experiments covering the tasks of image classification, object detection, video action recognition, 3D point cloud, and natural language processing. We evaluate our method against 14 different attacks (LIRA, WaNet, etc.) on 11 benchmark data sets such as ImageNet, UCF101, Pascal VOC, ModelNet, OpenSubtitles2012, etc., Comment: Accepted to ECCV 2024

The support of artificial intelligence (AI) based decision-making is a key element in future 6G networks, where the concept of native AI will be introduced. Moreover, AI is widely employed in different critical applications such as autonomous driving and medical diagnosis. In such applications, using AI as black-box models is risky and challenging. Hence, it is crucial to understand and trust the decisions taken by these models. Tackling this issue can be achieved by developing explainable AI (XAI) schemes that aim to explain the logic behind the black-box model behavior, and thus, ensure its efficient and safe deployment. Recently, we proposed a novel perturbation-based XAI-CHEST framework that is oriented toward channel estimation in wireless communications. The core idea of the XAI-CHEST framework is to identify the relevant model inputs by inducing high noise on the irrelevant ones. This manuscript provides the detailed theoretical foundations of the XAI-CHEST framework. In particular, we derive the analytical expressions of the XAI-CHEST loss functions and the noise threshold fine-tuning optimization problem. Hence the designed XAI-CHEST delivers a smart input feature selection methodology that can further improve the overall performance while optimizing the architecture of the employed model. Simulation results show that the XAI-CHEST framework provides valid interpretations, where it offers an improved bit error rate performance while reducing the required computational complexity in comparison to the classical DL-based channel estimation., Comment: This paper has been submitted to the IEEE Transactions on Vehicular Technology (TVT) as a regular paper on 27 June 2024

There are many extensions of the Standard Model with a dark matter (DM) candidate obtained via the freeze-out mechanism. It can happen that after all experimental and theoretical constraints are taken into account, all parameter points have a relic density below the experimentally measured value. This means that the models solve only partially the DM problem, and at least one more candidate is needed. In this work we show that it is possible to further extend the model with a DM candidate obtained via the freeze-in mechanism to be in agreement with the relic density experimental measurement. Once the relic density problem is solved with this addition, new questions are raised. This new model with at least two DM candidates could have a freeze-out undetectable DM particle both in direct and indirect detection. This could happen if the freeze-out DM particle would have a very low density. Hence, a collider DM hint via excess in the missing energy with no correspondence in direct and indirect detection experiments, could signal the existence of a Feebly Interacting Massive Particle (FIMP). Conversely, if a DM particle is found and a particular model can explain all observables except the correct relic density, an extension with an extra FIMP would solve the problem. The freeze-in DM candidate, due to the small portal couplings, will not change the remaining phenomenology.

Under a natural assumption on the dynamical degrees, we prove that the Green currents associated to any H\'enon-like map in any dimension have H\"older continuous super-potentials, i.e., give H\"older continuous linear functionals on suitable spaces of forms and currents. As a consequence, the unique measure of maximal entropy is the Monge-Amp\`ere of a H\"older continuous plurisubharmonic function and has strictly positive Hausdorff dimension. Under the same assumptions, we also prove that the Green currents are woven. When they are of bidegree $(1,1)$, they are laminar. In particular, our results generalize results known until now only in algebraic settings, or in dimension 2.

We introduce NCP (Neural Conditional Probability), a novel operator-theoretic approach for learning conditional distributions with a particular focus on inference tasks. NCP can be used to build conditional confidence regions and extract important statistics like conditional quantiles, mean, and covariance. It offers streamlined learning through a single unconditional training phase, facilitating efficient inference without the need for retraining even when conditioning changes. By tapping into the powerful approximation capabilities of neural networks, our method efficiently handles a wide variety of complex probability distributions, effectively dealing with nonlinear relationships between input and output variables. Theoretical guarantees ensure both optimization consistency and statistical accuracy of the NCP method. Our experiments show that our approach matches or beats leading methods using a simple Multi-Layer Perceptron (MLP) with two hidden layers and GELU activations. This demonstrates that a minimalistic architecture with a theoretically grounded loss function can achieve competitive results without sacrificing performance, even in the face of more complex architectures.