Search

Organizing and managing cryptocurrency portfolios and decision-making on transactions is crucial in this market. Optimal selection of assets is one of the main challenges that requires accurate prediction of the price of cryptocurrencies. In this work, we categorize the financial time series into several similar subseries to increase prediction accuracy by learning each subseries category with similar behavior. For each category of the subseries, we create a deep learning model based on the attention mechanism to predict the next step of each subseries. Due to the limited amount of cryptocurrency data for training models, if the number of categories increases, the amount of training data for each model will decrease, and some complex models will not be trained well due to the large number of parameters. To overcome this challenge, we propose to combine the time series data of other cryptocurrencies to increase the amount of data for each category, hence increasing the accuracy of the models corresponding to each category.

JavaScript has been consistently among the most popular programming languages in the past decade. However, its dynamic, weakly-typed, and asynchronous nature can make it challenging to write maintainable code for developers without in-depth knowledge of the language. Consequently, many JavaScript applications tend to contain code smells that adversely influence program comprehension, maintenance, and debugging. Due to the widespread usage of JavaScript, code security is an important matter. While JavaScript code smells and detection techniques have been studied in the past, current work on security smells for JavaScript is scarce. Security code smells are coding patterns indicative of potential vulnerabilities or security weaknesses. Identifying security code smells can help developers to focus on areas where additional security measures may be needed. We present a set of 24 JavaScript security code smells, map them to a possible security awareness defined by Common Weakness Enumeration (CWE), explain possible refactoring, and explain our detection mechanism. We implement our security code smell detection on top of an existing open source tool that was proposed to detect general code smells in JavaScript., Comment: 9 pages

Record matching, the task of identifying records that correspond to the same real-world entities across databases, is critical for data integration in domains like healthcare, finance, and e-commerce. While traditional record matching models focus on optimizing accuracy, fairness issues, such as demographic disparities in model performance, have attracted increasing attention. Biased outcomes in record matching can result in unequal error rates across demographic groups, raising ethical and legal concerns. Existing research primarily addresses fairness at specific decision thresholds, using bias metrics like Demographic Parity (DP), Equal Opportunity (EO), and Equalized Odds (EOD) differences. However, threshold-specific metrics may overlook cumulative biases across varying thresholds. In this paper, we adapt fairness metrics traditionally applied in regression models to evaluate cumulative bias across all thresholds in record matching. We propose a novel post-processing calibration method, leveraging optimal transport theory and Wasserstein barycenters, to balance matching scores across demographic groups. This approach treats any matching model as a black box, making it applicable to a wide range of models without access to their training data. Our experiments demonstrate the effectiveness of the calibration method in reducing demographic parity difference in matching scores. To address limitations in reducing EOD and EO differences, we introduce a conditional calibration method, which empirically achieves fairness across widely used benchmarks and state-of-the-art matching methods. This work provides a comprehensive framework for fairness-aware record matching, setting the foundation for more equitable data integration processes.

The rise of large language models (LLMs) has significantly impacted various domains, including natural language processing (NLP) and image generation, by making complex computational tasks more accessible. While LLMs demonstrate impressive generative capabilities, there is an ongoing debate about their level of "understanding," particularly in structured domains like SQL. In this paper, we evaluate the extent to which LLMs "understand" SQL by testing them on a series of key SQL tasks. These tasks, such as syntax error detection, missing token identification, query performance prediction, query equivalence checking, and query explanation, assess the models' proficiency in recognition, context awareness, semantics, and coherence, which are essential skills for SQL understanding. We generate labeled datasets from well-known workloads, and evaluate the latest LLMs, focusing on how query complexity and syntactic features influence performance. Our results indicate that while GPT4 excels at tasks requiring recognition and context, all models struggle with deeper semantic understanding and coherence, especially in query equivalence and performance estimation, revealing the limitations of current LLMs in achieving full SQL comprehension., Comment: 12 pages conference submission

The success of learning-based coding techniques and the development of learning-based image coding standards, such as JPEG-AI, point towards the adoption of such solutions in different fields, including the storage of biometric data, like fingerprints. However, the peculiar nature of learning-based compression artifacts poses several issues concerning their impact and effectiveness on extracting biometric features and landmarks, e.g., minutiae. This problem is utterly stressed by the fact that most models are trained on natural color images, whose characteristics are very different from usual biometric images, e.g, fingerprint or iris pictures. As a matter of fact, these issues are deemed to be accurately questioned and investigated, being such analysis still largely unexplored. This study represents the first investigation about the adaptability of learning-based image codecs in the storage of fingerprint images by measuring its impact on the extraction and characterization of minutiae. Experimental results show that at a fixed rate point, learned solutions considerably outperform previous fingerprint coding standards, like JPEG2000, both in terms of distortion and minutiae preservation. Indeed, experimental results prove that the peculiarities of learned compression artifacts do not prevent automatic fingerprint identification (since minutiae types and locations are not significantly altered), nor do compromise image quality for human visual inspection (as they gain in terms of BD rate and PSNR of 47.8% and +3.97dB respectively)., Comment: Accepted ad Wifs 2024

Entity Matching (EM) is crucial for identifying equivalent data entities across different sources, a task that becomes increasingly challenging with the growth and heterogeneity of data. Blocking techniques, which reduce the computational complexity of EM, play a vital role in making this process scalable. Despite advancements in blocking methods, the issue of fairness; where blocking may inadvertently favor certain demographic groups; has been largely overlooked. This study extends traditional blocking metrics to incorporate fairness, providing a framework for assessing bias in blocking techniques. Through experimental analysis, we evaluate the effectiveness and fairness of various blocking methods, offering insights into their potential biases. Our findings highlight the importance of considering fairness in EM, particularly in the blocking phase, to ensure equitable outcomes in data integration tasks.

In this paper, I consider a $f(R, G, T)$ modified gravity model where $R$ represents the Ricci scalar, $G$ denotes the Gauss-Bonnet invariant, and $T$ signifies the trace of the stress-energy tensor. This model is coupled with two distinct types of scalar fields. In the flat Friedmann-Lema\^{\i}tre-Robertson-Walker (FLRW) universe, the necessary conditions for a successful bounce are achieved. Under these circumstances, it is demonstrated that the equation of state (EoS) parameter cannot cross the phantom divider when only the inflaton scalar field is considered. Appropriate conditions to preserve the conservation of energy law are obtained. The absence of radiation domination is confirmed by referencing one of the collections of the Planck 2018 report. Moreover, it has been demonstrated that this is a general model, encompassing other models such as Weyl conformal geometry and the inflation epoch. Numerical calculations and graphs are used to confirm the results., Comment: 32 pages, 13 figures

With security threats increasing in frequency and severity, it is critical that we consider the important role of threat hunters. These highly-trained security professionals learn to see, identify, and intercept security threats. Many recent works and existing tools in cybersecurity are focused on automating the threat hunting process, often overlooking the critical human element. Our study shifts this paradigm by emphasizing a human-centered approach to understanding the lived experiences of threat hunters. By observing threat hunters during hunting sessions and analyzing the rich insights they provide, we seek to advance the understanding of their cognitive processes and the tool support they need. Through an in-depth observational study of threat hunters, we introduce a model of how they build and refine their mental models during threat hunting sessions. We also present 23 themes that provide a foundation to better understand threat hunter needs and five actionable design propositions to enhance the tools that support them. Through these contributions, our work enriches the theoretical understanding of threat hunting and provides practical insights for designing more effective, human-centered cybersecurity tools., Comment: 17 Pages; 4 Figures; 4 Tables

Investigating the genetic architecture of complex diseases is challenging due to the highly polygenic and interactive landscape of genetic and environmental factors. Although genome-wide association studies (GWAS) have identified thousands of variants for multiple complex phenotypes, conventional statistical approaches can be limited by simplified assumptions such as linearity and lack of epistasis models. In this work, we trained artificial neural networks for predicting complex traits using both simulated and real genotype/phenotype datasets. We extracted feature importance scores via different post hoc interpretability methods to identify potentially associated loci (PAL) for the target phenotype. Simulations we performed with various parameters demonstrated that associated loci can be detected with good precision using strict selection criteria, but downstream analyses are required for fine-mapping the exact variants due to linkage disequilibrium, similarly to conventional GWAS. By applying our approach to the schizophrenia cohort in the Estonian Biobank, we were able to detect multiple PAL related to this highly polygenic and heritable disorder. We also performed enrichment analyses with PAL in genic regions, which predominantly identified terms associated with brain morphology. With further improvements in model optimization and confidence measures, artificial neural networks can enhance the identification of genomic loci associated with complex diseases, providing a more comprehensive approach for GWAS and serving as initial screening tools for subsequent functional studies. Keywords: Deep learning, interpretability, genome-wide association studies, complex diseases

Shaping thermoplastic sheets into three-dimensional products is challenging since overheating results in failed manufactured parts and wasted material. To this end, we propose an indirect data-driven predictive control approach using Model Predictive Control (MPC) capable of handling temperature constraints and heating-power saturation while delivering enhanced precision, overshoot control, and settling times compared to state-of-the-art methods. We employ a Non-linear Auto-Regressive with Exogenous inputs (NARX) model to define a linear control-oriented model at each operating point. Using a high-fidelity simulator, several simulation studies have been conducted to evaluate the proposed method's robustness and performance under parametric uncertainty, indicating overshoot and average steady-state error less than $2^\circ \mathrm{C}$ and $0.7^\circ \mathrm{C}$ ($7^\circ \mathrm{C}$ and $2^\circ \mathrm{C}$) for the nominal (worst-case) scenario. Finally, we applied the proposed method to a lab-scale thermoforming platform, resulting in a close response to the simulation analysis with overshoot and average steady-state error metrics less than $5.3^\circ \mathrm{C}$ and $1^\circ \mathrm{C}$, respectively.

Recent advances in reinforcement learning (RL) have predominantly leveraged neural network-based policies for decision-making, yet these models often lack interpretability, posing challenges for stakeholder comprehension and trust. Concept bottleneck models offer an interpretable alternative by integrating human-understandable concepts into neural networks. However, a significant limitation in prior work is the assumption that human annotations for these concepts are readily available during training, necessitating continuous real-time input from human annotators. To overcome this limitation, we introduce a novel training scheme that enables RL algorithms to efficiently learn a concept-based policy by only querying humans to label a small set of data, or in the extreme case, without any human labels. Our algorithm, LICORICE, involves three main contributions: interleaving concept learning and RL training, using a concept ensembles to actively select informative data points for labeling, and decorrelating the concept data with a simple strategy. We show how LICORICE reduces manual labeling efforts to to 500 or fewer concept labels in three environments. Finally, we present an initial study to explore how we can use powerful vision-language models to infer concepts from raw visual inputs without explicit labels at minimal cost to performance., Comment: 23 pages, 6 figures, 9 tables

High contrast imaging of extrasolar planets and circumstellar disks requires extreme wavefront stability. Such stability can be achieved with active wavefront control (WFC). The next generation of ground- and space-based telescopes will require a robust form of WFC in order to image planets at small inner working angles and extreme flux ratios with respect to the host star. WFC algorithms such as implicit Electric Field Conjugation (iEFC) reduce stellar leakage by minimizing the electric field within a given region of an image, creating a dark hole. iEFC utilizes an empirical approach to sense and remove speckles in the focal plane. While iEFC is empirically calibrated and can handle optical model errors, there are still model assumptions made during the calibration. The performance of iEFC will degrade if the system changes due to slow, optomechanical drifts. In this work, we assess the iEFC performance impacts of pupil misalignments on the deformable mirror and focal plane misalignments on the detector. We base our analysis on the MagAO-X instrument, an extreme AO system installed on the Magellan-Clay telescope, to develop iEFC misalignment tolerancing requirements for both ground- and space-based missions. We present end-to-end physical optics simulations of the MagAO-X instrument, demonstrating iEFC alignment tolerance., Comment: 8 pages, 6 figures, SPIE Astronomical Telescopes + Instrumentation 2024

Understanding the mechanisms behind decisions taken by large foundation models in sequential decision making tasks is critical to ensuring that such systems operate transparently and safely. In this work, we perform exploratory analysis on the Video PreTraining (VPT) Minecraft playing agent, one of the largest open-source vision-based agents. We aim to illuminate its reasoning mechanisms by applying various interpretability techniques. First, we analyze the attention mechanism while the agent solves its training task - crafting a diamond pickaxe. The agent pays attention to the last four frames and several key-frames further back in its six-second memory. This is a possible mechanism for maintaining coherence in a task that takes 3-10 minutes, despite the short memory span. Secondly, we perform various interventions, which help us uncover a worrying case of goal misgeneralization: VPT mistakenly identifies a villager wearing brown clothes as a tree trunk when the villager is positioned stationary under green tree leaves, and punches it to death., Comment: Mechanistic Interpretability Workshop at ICML 2024

The exploitation of certification tools by end users represents a fundamental aspect of the development of quantum technologies as the hardware scales up beyond the regime of classical simulatability. Certifying quantum networks becomes even more crucial when the privacy of their users is exposed to malicious quantum nodes or servers as in the case of multi-client distributed blind quantum computing, where several clients delegate a joint private computation to remote quantum servers, such as federated quantum machine learning. In such protocols, security must be provided not only by keeping data hidden but also by verifying that the server is correctly performing the requested computation while minimizing the hardware assumptions on the employed devices. Notably, standard verification techniques fail in scenarios where the clients receive quantum states from untrusted sources such as, for example, in a recently demonstrated linear quantum network performing multi-client blind quantum computation. However, recent theoretical results provide techniques to verify blind quantum computations even in the case of untrusted state preparation. Equipped with such theoretical tools, in this work, we provide the first experimental implementation of a two-client verifiable blind quantum computing protocol in a distributed architecture. The obtained results represent novel perspectives for the verification of multi-tenant distributed quantum computation in large-scale networks., Comment: Minor changes in the description of the experimental setup

Developing a reliable vision system is a fundamental challenge for robotic technologies (e.g., indoor service robots and outdoor autonomous robots) which can ensure reliable navigation even in challenging environments such as adverse weather conditions (e.g., fog, rain), poor lighting conditions (e.g., over/under exposure), or sensor degradation (e.g., blurring, noise), and can guarantee high performance in safety-critical functions. Current solutions proposed to improve model robustness usually rely on generic data augmentation techniques or employ costly test-time adaptation methods. In addition, most approaches focus on addressing a single vision task (typically, image recognition) utilising synthetic data. In this paper, we introduce Per-corruption Adaptation of Normalization statistics (PAN) to enhance the model robustness of vision systems. Our approach entails three key components: (i) a corruption type identification module, (ii) dynamic adjustment of normalization layer statistics based on identified corruption type, and (iii) real-time update of these statistics according to input data. PAN can integrate seamlessly with any convolutional model for enhanced accuracy in several robot vision tasks. In our experiments, PAN obtains robust performance improvement on challenging real-world corrupted image datasets (e.g., OpenLoris, ExDark, ACDC), where most of the current solutions tend to fail. Moreover, PAN outperforms the baseline models by 20-30% on synthetic benchmarks in object recognition tasks.

Antibodies are widely used in life-sciences and medical therapy. Yet, broadly applicable methods are missing to determine, in the biological system of choice, antibody specificity and its quantitative contribution to e.g. immunofluorescence stainings. Thereby, antibody-based data often needs to be seen with caution. Here, we present a simple-to-use approach to characterize and quantify antibody binding properties directly in the system of choice. We determine an epitope accessibility distribution in the system of interest based on a computational analysis of antibody-dilution immunofluorescence stainings. This allows the selection of specific antibodies, the choice of a dilution to maximize signal-specificity, and an improvement of signal quantification. It further expands the scope of antibody-based imaging to detect changes of the subcellular nano-environment and allows for antibody multiplexing.

Magnetic Resonance Imaging (MRI) is a powerful technique employed for non-invasive in vivo visualization of internal structures. Sparsity is often deployed to accelerate the signal acquisition or overcome the presence of motion artifacts, improving the quality of image reconstruction. Image reconstruction algorithms use TV-regularized LASSO (Total Variation-regularized LASSO) to retrieve the missing information of undersampled signals, by cleaning the data of noise and while optimizing sparsity. A tuning parameter moderates the balance between these two aspects; its choice affecting the quality of the reconstructions. Currently, there is a lack of general deterministic techniques to choose these parameters, which are oftentimes manually selected and thus hinder the reliability of the reconstructions. Here, we present ALMA (Algorithm for Lagrange Multipliers Approximation), an iterative mathematics-inspired technique that computes tuning parameters for generalized LASSO problems during MRI reconstruction. We analyze quantitatively the performance of these parameters for imaging reconstructions via TV-LASSO in an MRI context on phantoms. Although our study concentrates on TV-LASSO, the techniques developed here hold significant promise for a wide array of applications. ALMA is not only adaptable to more generalized LASSO problems but is also robust to accommodate other forms of regularization beyond total variation. Moreover, it extends effectively to handle non-Cartesian sampling trajectories, broadening its utility in complex data reconstruction scenarios. More generally, ALMA provides a powerful tool for numerically solving constrained optimization problems across various disciplines, offering a versatile and impactful solution for advanced computational challenges.

The Space Coronagraph Optical Bench (SCoOB) is a high-contrast imaging testbed built to demonstrate starlight suppression techniques at visible wavelengths in a space-like vacuum environment. The testbed is designed to achieve ${<}10^{-8}$ contrast from $3-10\lambda/D$ in a one-sided dark hole using a liquid crystal vector vortex waveplate and a 952-actuator Kilo-C deformable mirror (DM) from Boston Micromachines (BMC). We have recently expanded the testbed to include a field stop for mitigation of stray/scattered light, a precision-fabricated pinhole in the source simulator, a Minus K passive vibration isolation table for jitter reduction, and a low-noise vacuum-compatible CMOS sensor. We report the latest contrast performance achieved using implicit electric field conjugation (iEFC) at a vacuum of ${\sim}10^{-6}$ Torr and over a range of bandpasses with central wavelengths from 500 to 650nm and bandwidths (BW) from $\ll 1\%$ to 15\%. Our jitter in vacuum is $<3\times10^{-3} \lambda/D$, and the best contrast performance to-date in a half-sided D-shaped dark hole is $2.2\times10^{-9}$ in a $\ll 1 \%$ BW, $4\times10^{-9}$ in a 2\% BW, and $2.5\times10^{-8}$ in a 15\% BW., Comment: 16 pages, 12 figures, SPIE Astronomical Telescopes and Instrumentation 2024

The correction of quasi-static wavefront errors within a coronagraphic optical system will be a key challenge to overcome in order to directly image exoplanets in reflected light. These quasi-static errors are caused by mid to high-order surface errors on the optical elements as a result of manufacturing processes. Using high-order wavefront sensing and control (HOWFSC) techniques that do not introduce non-common path aberrations, the quasi-static errors can be corrected within the desired region of interest designated as the dark hole. For the future Habitable Worlds Observatory (HWO), HOWFSC algorithms will be key to attaining the desired contrasts. To simulate the performance of HOWFSC with space rated processors, optical models for a 6 m class space-borne observatory and a coronagraph have been developed. Phenomena such as the Talbot effect and beamwalk are included in the simulations using combinations of ray-based modeling and end-to-end propagation techniques. After integrating the optical models with the embedded processors, simulations with realistic computation times can be performed to understand the computational hardware performance that will be needed to maintain the desired contrasts. Here, the details of the optical models are presented along with the HOWFSC methods utilized. Initial results of the HOWFSC methods are also included as a demonstration of how system drifts will degrade the contrast and require dark hole maintenance., Comment: 10 pages, 8 Figures, SPIE Astronomical Telescopes and Instrumentation 2024

Generative models are gaining significant attention as potential catalysts for a novel industrial revolution. Since automated sample generation can be useful to solve privacy and data scarcity issues that usually affect learned biometric models, such technologies became widely spread in this field. In this paper, we assess the vulnerabilities of generative machine learning models concerning identity protection by designing and testing an identity inference attack on fingerprint datasets created by means of a generative adversarial network. Experimental results show that the proposed solution proves to be effective under different configurations and easily extendable to other biometric measurements., Comment: Paper submitted at "Pattern Recognition Letters", 9 pages, 6 images

Reinforcement learning (RL) has recently shown promise in predicting Alzheimer's disease (AD) progression due to its unique ability to model domain knowledge. However, it is not clear which RL algorithms are well-suited for this task. Furthermore, these methods are not inherently explainable, limiting their applicability in real-world clinical scenarios. Our work addresses these two important questions. Using a causal, interpretable model of AD, we first compare the performance of four contemporary RL algorithms in predicting brain cognition over 10 years using only baseline (year 0) data. We then apply SHAP (SHapley Additive exPlanations) to explain the decisions made by each algorithm in the model. Our approach combines interpretability with explainability to provide insights into the key factors influencing AD progression, offering both global and individual, patient-level analysis. Our findings show that only one of the RL methods is able to satisfactorily model disease progression, but the post-hoc explanations indicate that all methods fail to properly capture the importance of amyloid accumulation, one of the pathological hallmarks of Alzheimer's disease. Our work aims to merge predictive accuracy with transparency, assisting clinicians and researchers in enhancing disease progression modeling for informed healthcare decisions. Code is available at https://github.com/rfali/xrlad., Comment: Previous versions accepted to NeurIPS 2023's XAIA and AAAI 2024's XAI4DRL workshops

Entity Matching (EM) is a critical task in numerous fields, such as healthcare, finance, and public administration, as it identifies records that refer to the same entity within or across different databases. EM faces considerable challenges, particularly with false positives and negatives. These are typically addressed by generating matching scores and apply thresholds to balance false positives and negatives in various contexts. However, adjusting these thresholds can affect the fairness of the outcomes, a critical factor that remains largely overlooked in current fair EM research. The existing body of research on fair EM tends to concentrate on static thresholds, neglecting their critical impact on fairness. To address this, we introduce a new approach in EM using recent metrics for evaluating biases in score based binary classification, particularly through the lens of distributional parity. This approach enables the application of various bias metrics like equalized odds, equal opportunity, and demographic parity without depending on threshold settings. Our experiments with leading matching methods reveal potential biases, and by applying a calibration technique for EM scores using Wasserstein barycenters, we not only mitigate these biases but also preserve accuracy across real world datasets. This paper contributes to the field of fairness in data cleaning, especially within EM, which is a central task in data cleaning, by promoting a method for generating matching scores that reduce biases across different thresholds.

Forecasts and future beliefs play a critical role in the harvest labor hiring planning, especially when errors in them entails fixing previous made decisions, which can carry extra costs or losses. In this article, we study the effect that errors in the forecast/belief can have in the wine grape harvest planning process and the losses of the product. Errors are reflected in the prediction of yields and in the estimation of rain transition probabilities have on the value and losses of product. Also, using a multi-stage stochastic optimization model we can study the effect that second stage decisions have on the ability fix the planning decisions, reduce product losses and generate value. In a first step, we develop a multi-stage stochastic model which considers grape growth uncertainty given a belief in future events. The model decisions variables are: hiring, firing and maintaining harvest labor through periods, and also the harvested quantities in each period and block. Once the model defines the plan for the coming epoch, some decisions are implemented and a deviation in the forecast is revealed and the decision maker can adjust future decisions and beliefs. Results indicate that the effect of the errors in yield determination is not symmetrical; underestimations of the yields have a more significant negative effect on the objective function, while overestimation does not. Flexibility to revise hiring decisions does not make a significant difference if the yields are overestimated. The model significantly reduces losses of the better-quality grapes, since they correspond to a significant proportion of the income and account for the largest portion of income loss. Last, grapes that have an early improvement of their quality give the decision-maker an extra level of flexibility to adjust the harvesting plan.

Mental illness remains one of the most critical public health issues. Despite its importance, many mental health professionals highlight a disconnect between their training and actual real-world patient practice. To help bridge this gap, we propose PATIENT-{\Psi}, a novel patient simulation framework for cognitive behavior therapy (CBT) training. To build PATIENT-{\Psi}, we construct diverse patient cognitive models based on CBT principles and use large language models (LLMs) programmed with these cognitive models to act as a simulated therapy patient. We propose an interactive training scheme, PATIENT-{\Psi}-TRAINER, for mental health trainees to practice a key skill in CBT -- formulating the cognitive model of the patient -- through role-playing a therapy session with PATIENT-{\Psi}. To evaluate PATIENT-{\Psi}, we conducted a comprehensive user study of 13 mental health trainees and 20 experts. The results demonstrate that practice using PATIENT-{\Psi}-TRAINER enhances the perceived skill acquisition and confidence of the trainees beyond existing forms of training such as textbooks, videos, and role-play with non-patients. Based on the experts' perceptions, PATIENT-{\Psi} is perceived to be closer to real patient interactions than GPT-4, and PATIENT-{\Psi}-TRAINER holds strong promise to improve trainee competencies. Our code and data are released at \url{https://github.com/ruiyiw/patient-psi}., Comment: EMNLP 2024 Main, 9 pages, 5 figures

High-order wavefront sensing and control (HOWFSC) is key to create a dark hole region within the coronagraphic image plane where high contrasts are achieved. The Roman Coronagraph is expected to perform its HOWFSC with a ground-in-the-loop scheme due to the computational complexity of the Electric Field Conjugation (EFC) algorithm. This scheme provides the flexibility to alter the HOWFSC algorithm for given science objectives. The baseline HOWFSC scheme involves running EFC while observing a bright star such as {\zeta} Puppis to create the initial dark hole followed by a slew to the science target. The new implicit EFC (iEFC) algorithm removes the optical diffraction model from the controller, making the final contrast independent of model accuracy. While previously demonstrated with a single DM, iEFC is extended to two deformable mirror systems in order to create annular dark holes. The algorithm is then applied to the Wide-Field-of-View Shaped Pupil Coronagraph (SPC-WFOV) mode designed for the Roman Space Telescope using end-to-end physical optics models. Initial monochromatic simulations demonstrate the efficacy of iEFC as well as the optimal choice of modes for the SPC-WFOV instrument. Further simulations with a 3.6% wavefront control bandpass and a broader 10% bandpass then demonstrate that iEFC can be used in broadband scenarios to achieve contrasts below 1E-8 with Roman. Finally, an EMCCD model is implemented to estimate calibration times and predict the controller's performance. Here, 1E-8 contrasts are achieved with a calibration time of about 6.8 hours assuming the reference star is {\zeta} Puppis. The results here indicate that iEFC can be a valid HOWFSC method that can mitigate the risk of model errors associated with space-borne coronagraphs, but to maximize iEFC performance, lengthy calibration times will be required to mitigate the noise accumulated during calibration., Comment: 20 pages, 15 figures