May 2023 arXiv papers — page 24

Yian Chen, Yuehaw Khoo, Ziang Yu

In this paper, we propose a general framework for solving high-dimensional partial differential equations with tensor networks. Our approach uses Monte-Carlo simulations to update the solution and re-estimates the new solution from samples as a tensor-network using a recently proposed tensor train sketching technique. We showcase the versatility and flexibil

Andres S. Chavez Armijos, Anni Li, Christos G. Cassandras

This paper addresses cooperative lane-changing maneuvers in mixed traffic, aiming to minimize traffic flow disruptions while accounting for uncooperative vehicles. The proposed approach adopts controllers combining Optimal control with Control Barrier Functions (OCBF controllers) which guarantee spatio-temporal constraints through the use of fixed-time conve

Yixin Liu, Kaize Ding, Jianling Wang, Vincent Lee

Graph Neural Networks (GNNs) have exhibited impressive performance in many graph learning tasks. Nevertheless, the performance of GNNs can deteriorate when the input graph data suffer from weak information, i.e., incomplete structure, incomplete features, and insufficient labels. Most prior studies, which attempt to learn from the graph data with a specific

Hussain Ibdah

This is the second in a series of papers where we analyze the incompressible Navier-Stokes equations in H\"older spaces. We obtain, to our knowledge, the very first genuinely super-critical regularity criterion for this system of equations in any dimension $d\geq3$ and in the absence of physical boundaries. For \emph{any} $\beta\in(0,1)$, we show that $L_t^1

Yi Huang, Wei Zhu, Duan Li, Shushang Zhu

Following the idea of Bayesian learning via Gaussian mixture model, we organically combine the backward-looking information contained in the historical data and the forward-looking information implied by the market portfolio, which is affected by heterogeneous expectations and noisy trading behavior. The proposed combined estimation adaptively harmonizes the

Weiwei Wu, Huaping Zhang, Hong Wang, Chao Chang

Topologically protected spin textures, such as skyrmions1,2 and vortices3,4, are robust against perturbations, serving as the building blocks for a range of topological devices5-9. In order to implement these topological devices, it is necessary to find ultra-small topological spin textures at room temperature, because small size implies the higher topologic

Junren Qin, Shanxiang Lyu, Fan Yang, Jiarui Deng

Static deep neural network (DNN) watermarking techniques typically employ irreversible methods to embed watermarks into the DNN model weights. However, this approach causes permanent damage to the watermarked model and fails to meet the requirements of integrity authentication. Reversible data hiding (RDH) methods offer a potential solution, but existing app

Leonard Tang, Gavin Uberti, Tom Shlomi

We consider the emerging problem of identifying the presence and use of watermarking schemes in widely used, publicly hosted, closed source large language models (LLMs). We introduce a suite of baseline algorithms for identifying watermarks in LLMs that rely on analyzing distributions of output tokens and logits generated by watermarked and unmarked LLMs. No

Weijian Luo, Tianyang Hu, Shifeng Zhang, Jiacheng Sun

Due to the ease of training, ability to scale, and high sample quality, diffusion models (DMs) have become the preferred option for generative modeling, with numerous pre-trained models available for a wide variety of datasets. Containing intricate information about data distributions, pre-trained DMs are valuable assets for downstream applications. In this

Qiang Zhang, Jason Naradowsky, Yusuke Miyao

Existing dialogue models may encounter scenarios which are not well-represented in the training data, and as a result generate responses that are unnatural, inappropriate, or unhelpful. We propose the "Ask an Expert" framework in which the model is trained with access to an "expert" which it can consult at each turn. Advice is solicited via a structured dial

Stephen M. Watt

It is shown how to compute quotients efficiently in non-commutative univariate polynomial rings. This extends earlier work where efficient generic quotients were studied with a primary focus on commutative domains. Fast algorithms are given for left and right quotients of polynomials where the variable commutes with coefficients. These algorithms are based o

Maho Nakata, Toshiyuki Maeda

This article presents the "PubChemQC B3LYP/6-31G*//PM6" dataset, containing electronic properties of 85,938,443 molecules. It includes orbitals, orbital energies, total energies, dipole moments, and other relevant properties. The dataset encompasses a wide range of molecules, from essential compounds to biomolecules up to 1000 molecular weight, covering 94.0

Zolnamar Dorjsembe, Hsing-Kuo Pao, Sodtavilan Odonchimed, Furen Xiao

Artificial intelligence (AI) in healthcare, especially in medical imaging, faces challenges due to data scarcity and privacy concerns. Addressing these, we introduce Med-DDPM, a diffusion model designed for 3D semantic brain MRI synthesis. This model effectively tackles data scarcity and privacy issues by integrating semantic conditioning. This involves the

Forrest Mozer, Stuart Bale, Paul Kellogg, Orlando Romeo

Triggered ion-acoustic waves are a pair of coupled waves observed in the previously unexplored plasma regime near the Sun. They may be capable of producing important effects on the solar wind. Because this wave mode has not been observed or studied previously and it is not fully understood, the issue of whether it has a natural origin or is an instrumental a

Ethan Pronovost, Kai Wang, Nick Roy

In this paper we describe a learned method of traffic scene generation designed to simulate the output of the perception system of a self-driving car. In our "Scene Diffusion" system, inspired by latent diffusion, we use a novel combination of diffusion and object detection to directly create realistic and physically plausible arrangements of discrete boundi

Namkyeong Lee, Kanghoon Yoon, Gyoung S. Na, Sein Kim

Recently, molecular relational learning, whose goal is to predict the interaction behavior between molecular pairs, got a surge of interest in molecular sciences due to its wide range of applications. In this work, we propose CMRL that is robust to the distributional shift in molecular relational learning by detecting the core substructure that is causally r

Souvik Naskar, Karu Chongsiripinyo, Anikesh Pal, Akshay Jananan

A three-dimensional finite-difference solver has been developed and implemented for Boussinesq convection in a spherical shell. The solver transforms any complex curvilinear domain into an equivalent Cartesian domain using Jacobi transformation and solves the governing equations in the latter. This feature enables the solver to account for the effects of the

Qin Xie, Qinghua Zhang, Shuyin Xia, Fan Zhao

Granular ball computing (GBC), as an efficient, robust, and scalable learning method, has become a popular research topic of granular computing. GBC includes two stages: granular ball generation (GBG) and multi-granularity learning based on the granular ball (GB). However, the stability and efficiency of existing GBG methods need to be further improved due t

Stefano Soatto, Paulo Tabuada, Pratik Chaudhari, Tian Yu Liu

We tackle the question of whether an agent can, by suitable choice of prompts, control an AI bot to any state. To that end, we first introduce a formal definition of ``meaning'' that is amenable to analysis. Then, we characterize ``meaningful data'' on which large language models (LLMs) are ostensibly trained, and ``well-trained LLMs'' through conditions tha

Ali Haisam Muhammad Rafid, Adrian Sandu

Regularization techniques such as $\mathcal{L}_1$ and $\mathcal{L}_2$ regularizers are effective in sparsifying neural networks (NNs). However, to remove a certain neuron or channel in NNs, all weight elements related to that neuron or channel need to be prunable, which is not guaranteed by traditional regularization. This paper proposes a simple new approac

Krishna Pillutla, Galen Andrew, Peter Kairouz, H. Brendan McMahan

We present a rigorous methodology for auditing differentially private machine learning algorithms by adding multiple carefully designed examples called canaries. We take a first principles approach based on three key components. First, we introduce Lifted Differential Privacy (LiDP) that expands the definition of differential privacy to handle randomized dat

Kuan-Yu Chen, Ping-Han Chiang, Hsin-Rung Chou, Ting-Wei Chen

Tabular data is arguably one of the most commonly used data structures in various practical domains, including finance, healthcare and e-commerce. The inherent heterogeneity allows tabular data to store rich information. However, based on a recently published tabular benchmark, we can see deep neural networks still fall behind tree-based models on tabular da

Linshuang Zhang, Manyi Yang, Shiwei Zhang, Haiyang Niu

Cadmium selenide (CdSe) is an inorganic semiconductor with unique optical and electronic properties that made it useful in various applications, including solar cells, light-emitting diodes, and biofluorescent tagging. In order to synthesize high-quality crystals and subsequently integrate them into devices, it is crucial to understand the atomic scale cryst

He Wen

Digital technologies have dramatically accelerated the digital transformation in process industries, boosted new industrial applications, upgraded the production system, and enhanced operational efficiency. In contrast, the challenges and gaps between human and artificial intelligence (AI) have become more and more prominent, whereas the digital divide in pr

Atoosa Parsa, Sven Witthaus, Nidhi Pashine, Corey S. O'Hern

Unconventional computing devices are increasingly of interest as they can operate in environments hostile to silicon-based electronics, or compute in ways that traditional electronics cannot. Mechanical computers, wherein information processing is a material property emerging from the interaction of components with the environment, are one such class of devi

Sunitha Basodi, Krishna Pusuluri, Xueli Xiao, Yi Pan

Deep learning models offer superior performance compared to other machine learning techniques for a variety of tasks and domains, but pose their own challenges. In particular, deep learning models require larger training times as the depth of a model increases, and suffer from vanishing gradients. Several solutions address these problems independently, but t

Yijun Yang, Tianyi Zhou, Jing Jiang, Guodong Long

How to train a generalizable meta-policy by continually learning a sequence of tasks? It is a natural human skill yet challenging to achieve by current reinforcement learning: the agent is expected to quickly adapt to new tasks (plasticity) meanwhile retaining the common knowledge from previous tasks (stability). We address it by "Continual Task Allocation v

Jiafei Lyu, Le Wan, Zongqing Lu, Xiu Li

Sample efficiency is one of the most critical issues for online reinforcement learning (RL). Existing methods achieve higher sample efficiency by adopting model-based methods, Q-ensemble, or better exploration mechanisms. We, instead, propose to train an off-policy RL agent via updating on a fixed sampled batch multiple times, thus reusing these samples and

Zifan Chen, Jiazheng Li, Jie Zhao, Yiting Liu

**Background:** Accurate 3D CT scan segmentation of gastric tumors is pivotal for diagnosis and treatment. The challenges lie in the irregular shapes, blurred boundaries of tumors, and the inefficiency of existing methods. **Purpose:** We conducted a study to introduce a model, utilizing human-guided knowledge and unique modules, to address the challenges of

Tomoya Kato, Akihiko Miyachi, Naohito Tomita

We consider some bilinear Fourier multiplier operators and give a bilinear version of Seeger, Sogge, and Stein's result for Fourier integral operators. Our results improve, for the case of Fourier multiplier operators, Rodr\'iguez-L\'opez, Rule, and Staubach's result for bilinear Fourier integral operators. The sharpness of the results is also considered.

Yu Wang, Fengjuan Gao, Linzhang Wang, Tingting Yu

Interrupt-driven programs are widely deployed in safety-critical embedded systems to perform hardware and resource dependent data operation tasks. The frequent use of interrupts in these systems can cause race conditions to occur due to interactions between application tasks and interrupt handlers (or two interrupt handlers). Numerous program analysis and te

Kang Yang, Kunhao Lai

Deep neural network (DNN) models have become a critical asset of the model owner as training them requires a large amount of resource (i.e. labeled data). Therefore, many fingerprinting schemes have been proposed to safeguard the intellectual property (IP) of the model owner against model extraction and illegal redistribution. However, previous schemes adopt

A. Sajid, F. Nilsson, S. Manti, F. Bertoldo

We employ a first-principles computational workflow to screen for optically accessible, high-spin point defects in wide band gap two-dimensional (2D) crystals. Starting from an initial set of 5388 point defects, comprising both intrinsic and extrinsic, single and double defects in ten previously synthesised 2D host materials, we identify 596 defects with a t

Isuru Fernando, Andreas Klöckner

We demonstrate a new, hybrid symbolic-numerical method for the automatic synthesis of all families of translation operators required for the execution of the Fast Multipole Method (FMM). Our method is applicable in any dimensionality and to any translation-invariant kernel. The Fast Multipole Method, of course, is the leading approach for attaining linear co

Jingjin Liu, Hankz Hankui Zhuo, Kebing Jin, Jiamin Yuan

Traditional Chinese Medicine (TCM) has a rich history of utilizing natural herbs to treat a diversity of illnesses. In practice, TCM diagnosis and treatment are highly personalized and organically holistic, requiring comprehensive consideration of the patient's state and symptoms over time. However, existing TCM recommendation approaches overlook the changes

Dianchao Lin, Li Li

With the rapid development of Connected and Automated Vehicle (CAV) technology, limited self-driving vehicles have been commercially available in certain leading intelligent transportation system countries. When formulating the car-following model for CAVs, safety is usually the basic constraint. Safety-oriented car-following models seek to specify a safe fo

Eve Y. Y. Yang

In 2007, Andrews and Paule introduced the broken $k$-diamond partition function $\Delta_{k}(n)$, which has received a lot of researches on the arithmetic propertises. In this paper, we will prove the broken $k$-diamond partition function satisfies the Laguerre inequalities of order $2$ and the determinantal inequalities of order $3$ for $k=1$ or $2$. Moreove

Raula Gaikovina Kula, Katsuro Inoue, Christoph Treude

The use of third-party packages is becoming increasingly popular and has led to the emergence of large software package ecosystems with a maze of inter-dependencies. Since the reliance on these ecosystems enables developers to reduce development effort and increase productivity, it has attracted the interest of researchers: understanding the infrastructure a

Tao Wang, Kaihao Zhang, Ziqian Shao, Wenhan Luo

Image restoration in adverse weather conditions is a difficult task in computer vision. In this paper, we propose a novel transformer-based framework called GridFormer which serves as a backbone for image restoration under adverse weather conditions. GridFormer is designed in a grid structure using a residual dense transformer block, and it introduces two co

Yucheng Liao, Yuanyu Wan, Chang Yao, Mingli Song

We investigate the problem of online learning with monotone and continuous DR-submodular reward functions, which has received great attention recently. To efficiently handle this problem, especially in the case with complicated decision sets, previous studies have proposed an efficient projection-free algorithm called Mono-Frank-Wolfe (Mono-FW) using $O(T)$

Hailong Liu, Yang Li, Zhe Zeng, Hao Cheng

Autonomous Personal Mobility Vehicle (APMV) is a miniaturized autonomous vehicle designed to provide short-distance mobility to everyone in pedestrian-rich environments. By the characteristic of the open design, passengers on the APMV are exposed to the communication between the eHMI deployed on APMVs and pedestrians. Therefore, to ensure an optimal passenge

Huan Ren, Wenfei Yang, Tianzhu Zhang, Yongdong Zhang

Weakly-supervised temporal action localization aims to localize and recognize actions in untrimmed videos with only video-level category labels during training. Without instance-level annotations, most existing methods follow the Segment-based Multiple Instance Learning (S-MIL) framework, where the predictions of segments are supervised by the labels of vide

Haoyu Lu, Nan Li, Tongtong Song, Longbiao Wang

In recent years, the joint training of speech enhancement front-end and automatic speech recognition (ASR) back-end has been widely used to improve the robustness of ASR systems. Traditional joint training methods only use enhanced speech as input for the backend. However, it is difficult for speech enhancement systems to directly separate speech from input

Hoang Hai Ha, Ky Ho

Using variational methods, we obtain several multiplicity results for double phase problems that involve variable exponents and a new type of critical growth. This new critical growth is better suited for double phase problems when compared to previous works on the subject. In order to overcome the lack of compactness caused by the critical exponents, we est

Yisu Zhang, Jianke Zhu, Lixiang Lin

Despite the promising results of multi-view reconstruction, the recent neural rendering-based methods, such as implicit surface rendering (IDR) and volume rendering (NeuS), not only incur a heavy computational burden on training but also have the difficulties in disentangling the geometric and appearance. Although having achieved faster training speed than i

Semyon Dyatlov

In [arXiv:2305.05022], Cohen proved a higher dimensional fractal uncertainty principle for line porous sets. The purpose of this expository note is to provide a different point of view on some parts of Cohen's proof, particularly suited to readers familiar with the theory of distributions. It is meant to be complementary to Cohen's paper.

Mohamed A. Kassem, Abdulaziz Abu El-Fadl, Ahmed M. Nashaat, Hiroyuki Nakamura

Spinel chromites ACr$_2$O$_4$ with inherent magnetic geometrical frustration usually exhibit a noncollinear ferrimagnetic ground state when A are magnetic ions, with possibly crystallite-size dependent intriguing magnetic features. Here, we report single-domain magnetic properties of ACr$_2$O$_4$ (A = Ni, Co, and Mn) nanocrystals, with an average crystallite

Yu-Hsiang Tseng, Mao-Chang Ku, Wei-Ling Chen, Yu-Lin Chang

Contextualized embeddings are proven to be powerful tools in multiple NLP tasks. Nonetheless, challenges regarding their interpretability and capability to represent lexical semantics still remain. In this paper, we propose that the task of definition modeling, which aims to generate the human-readable definition of the word, provides a route to evaluate or

Zhen Zhang, Mengting Hu, Shiwan Zhao, Minlie Huang

Most named entity recognition (NER) systems focus on improving model performance, ignoring the need to quantify model uncertainty, which is critical to the reliability of NER systems in open environments. Evidential deep learning (EDL) has recently been proposed as a promising solution to explicitly model predictive uncertainty for classification tasks. Howe

Rui Ye, Yanyan He, Guangzhen Li, Luojia Wang

Non-Hermitian topological photonics is of great interest in bridging topological matter with gain/dissipation engineering in optics. A key problem in this direction is the interplay between the effective gauge potential and the non-Hermiticity. Here we tackle this problem in a synthetic non-Hermitian Hall ladder and experimentally observe antichiral edge cur

Ryuhei Hamaguchi, Yasutaka Furukawa, Masaki Onishi, Ken Sakurada

This paper proposes a low latency neural network architecture for event-based dense prediction tasks. Conventional architectures encode entire scene contents at a fixed rate regardless of their temporal characteristics. Instead, the proposed network encodes contents at a proper temporal scale depending on its movement speed. We achieve this by constructing t

Amin Beheshti, Jian Yang, Quan Z. Sheng, Boualem Benatallah

Generative Pre-trained Transformer (GPT) is a state-of-the-art machine learning model capable of generating human-like text through natural language processing (NLP). GPT is trained on massive amounts of text data and uses deep learning techniques to learn patterns and relationships within the data, enabling it to generate coherent and contextually appropria

Mengdi Zhao, Kejie Fang

Recent developments in quantum light-matter coupled systems and quantum transducers have highlighted the need for cryogenic optical measurements. In this study, we present a mechanically-rigid fiber-optic coupler with a coupling efficiency of over 50% for telecom wavelength light at cryogenic temperatures. Our method enables sensitive photonic device measure

Sara Ratliff, Axel Schmidt

Measurements of deep inelastic scattering from nuclei have revealed that the partonic structure of bound nucleons differs from that of free nucleons. One hypothesis is that this structure modification primarily occurs in highly virtual nucleons participating in short-range correlations, although distinguishing this from other hypotheses is difficult with inc

Kazuo Murota, Akiyoshi Shioura

For a class of discrete quasi convex functions called semi-strictly quasi M$^\natural$-convex functions, we investigate fundamental issues relating to minimization, such as optimality condition by local optimality, minimizer cut property, geodesic property, and proximity property. Emphasis is put on comparisons with (usual) M$^\natural$-convex functions. The

Oliver Knill

A topological ring R, an escape set B in R and a family of maps z^d+c defines the degree d Mandelstuff as the set of parameters for which the closure of the orbit of 0 does not intersect R. If B is the complement of a ball of radius 2 in C or H it is the complex or quaternionic Mandelbrot set; in a vector space with polar decomposition x=|x| U(t) like R=R^m,

Xilin Jiang, Yinghao Aaron Li, Nima Mesgarani

Lifelong audio feature extraction involves learning new sound classes incrementally, which is essential for adapting to new data distributions over time. However, optimizing the model only on new data can lead to catastrophic forgetting of previously learned tasks, which undermines the model's ability to perform well over the long term. This paper introduces

Fumichika Takamizo

Let $\beta>1$. For $x \in [0,\infty)$, we have so-called the $\beta$-expansion of $x$ in base $\beta$ as follows: $$x= \sum_{j \leq k} x_{j}\beta^{j} = x_{k}\beta^{k}+ \cdots + x_{1}\beta+x_{0}+x_{-1}\beta^{-1} + x_{-2}\beta^{-2} + \cdots$$ where $k \in \mathbb{Z}$, $\beta^{k} \leq x < \beta^{k+1}$, $x_{j} \in \mathbb{Z} \cap [0,\beta)$ for all $j \leq k$ an

Marco Alberto Ayala-Torres, Lucina Gabriela Espinoza Beltrán, Luis A. Hernández-Cruz, Luis Manuel Montaño

The Multipurpose Detector (MPD) consists of a typical array of sub-detectors to study the nuclear matter originating from the collisions of beams provided by the Nuclotron-based Ion Collider fAcility (NICA). A beam monitoring detector~(BeBe) is proposed for stage 2 of MPD to increase the trigger capabilities. BeBe is constituted of two plastic scintillator d

Yui Sudo, Kazuya Hata, Kazuhiro Nakadai

End-to-end automatic speech recognition (E2E-ASR) has the potential to improve performance, but a specific issue that needs to be addressed is the difficulty it has in handling enharmonic words: named entities (NEs) with the same pronunciation and part of speech that are spelled differently. This often occurs with Japanese personal names that have the same p

Le Jiang, Sarah Ostadabbas

Animal pose estimation has become a crucial area of research, but the scarcity of annotated data is a significant challenge in developing accurate models. Synthetic data has emerged as a promising alternative, but it frequently exhibits domain discrepancies with real data. Style transfer algorithms have been proposed to address this issue, but they suffer fr

Qasim Ajao, Lanre Sadeeq

Efforts toward building a sustainable future have underscored the importance of collective responsibility among state and non-state actors, corporations, and individuals to achieve climate goals. International initiatives, including the Sustainable Development Goals and the Paris Agreement, emphasize the need for immediate action from all stakeholders. This

Tsuyoshi Idé, Naoki Abe

When the prediction of a black-box machine learning model deviates from the true observation, what can be said about the reason behind that deviation? This is a fundamental and ubiquitous question that the end user in a business or industrial AI application often asks. The deviation may be due to a sub-optimal black-box model, or it may be simply because the

Jinda Cui, Jiawei Xu, David Saldaña, Jeff Trinkle

Dexterous manipulation of objects through fine control of physical contacts is essential for many important tasks of daily living. A fundamental ability underlying fine contact control is compliant control, \textit{i.e.}, controlling the contact forces while moving. For robots, the most widely explored approaches heavily depend on models of manipulated objec

Zhenting Wang, Chen Chen, Yi Zeng, Lingjuan Lyu

Recently, there has been a growing attention in image generation models. However, concerns have emerged regarding potential misuse and intellectual property (IP) infringement associated with these models. Therefore, it is necessary to analyze the origin of images by inferring if a specific image was generated by a particular model, i.e., origin attribution.

Dongho Kang, Jin Cheng, Miguel Zamora, Fatemeh Zargarbashi

This paper presents a control framework that combines model-based optimal control and reinforcement learning (RL) to achieve versatile and robust legged locomotion. Our approach enhances the RL training process by incorporating on-demand reference motions generated through finite-horizon optimal control, covering a broad range of velocities and gaits. These

Michael Strickland, Sabin Thapa

We present potential non-relativistic quantum chromodynamics (pNRQCD) predictions for bottomonium suppression in sqrt(sNN) = 200 GeV, 2.76 TeV, and 5.02 TeV heavy-ion collisions using an open quantum systems (OQS) description of the reduced heavy-quark anti-quark density matrix. Compared to prior OQS+pNRQCD studies we include the rapidity dependence of botto

Y. Tokiwa, H. Sakai. S. Kambe, P. Opletal, E. Yamamoto

The vortex dynamics in the spin-triplet superconductor, UTe$_2$, are studied by measuring the DC electrical resistivity with currents along the $a$-axis under magnetic fields along the $b$-axis. Surprisingly, we have discovered an island region of low critical current deep inside the superconducting (SC) state, well below the SC upper critical field, attribu

J. A. Brown, T. A. Laplace, B. L. Goldblum, J. J. Manfredi

The absolute light yield of a scintillator, defined as the number of scintillation photons produced per unit energy deposited, is a useful quantity for scintillator development, research, and applications. Yet, literature data on the absolute light yield of organic scintillators are limited. The goal of this work is to assess the suitability of the EJ-204 pl

Patrick Draper, Benjamin Lillard, Carissa Skye

Theories with compact extra dimensions can exhibit a vacuum instability known as a bubble of nothing. These decay modes can be obstructed if the internal manifold is stabilized by fluxes, or if it carries Wilson lines for background gauge fields, or if the instanton is incompatible with the spin structure. In each of these cases the decay can proceed by addi

Jiawei Xu, David Saldaña

Traditional aerial vehicles have limitations in their capabilities due to actuator constraints, such as motor saturation. The hardware components and their arrangement are designed to satisfy specific requirements and are difficult to modify during operation. To address this problem, we introduce a versatile modular multi-rotor vehicle that can change its ca

Zihao Li, Zhuoran Yang, Mengdi Wang

In this paper, we study offline Reinforcement Learning with Human Feedback (RLHF) where we aim to learn the human's underlying reward and the MDP's optimal policy from a set of trajectories induced by human choices. RLHF is challenging for multiple reasons: large state space but limited human feedback, the bounded rationality of human decisions, and the off-

Shahriar Talebi, Amirhossein Taghvaei, Mehran Mesbahi

This paper examines learning the optimal filtering policy, known as the Kalman gain, for a linear system with unknown noise covariance matrices using noisy output data. The learning problem is formulated as a stochastic policy optimization problem, aiming to minimize the output prediction error. This formulation provides a direct bridge between data-driven o

A. D. Alhaidari

Gauss quadrature integral approximation is extended to include integrals with a measure consisting of continuous as well as discrete components. That is, we give an approximation for the integral of a function plus its sum over a discrete weighted set.

Boris Kovalerchuk, Elijah McCoy

Building accurate and interpretable Machine Learning (ML) models for heterogeneous/mixed data is a long-standing challenge for algorithms designed for numeric data. This work focuses on developing numeric coding schemes for non-numeric attributes for ML algorithms to support accurate and explainable ML models, methods for lossless visualization of n-D non-nu

Yubo Zhuang, Xiaohui Chen, Yun Yang, Richard Y. Zhang

$K$-means clustering is a widely used machine learning method for identifying patterns in large datasets. Recently, semidefinite programming (SDP) relaxations have been proposed for solving the $K$-means optimization problem, which enjoy strong statistical optimality guarantees. However, the prohibitive cost of implementing an SDP solver renders these guaran

Tom Blau, Iadine Chades, Amir Dezfouli, Daniel Steinberg

Reinforcement learning can learn amortised design policies for designing sequences of experiments. However, current amortised methods rely on estimators of expected information gain (EIG) that require an exponential number of samples on the magnitude of the EIG to achieve an unbiased estimation. We propose the use of an alternative estimator based on the cro

Heinrich Dinkel, Zhiyong Yan, Yongqing Wang, Junbo Zhang

Transformers have emerged as a prominent model framework for audio tagging (AT), boasting state-of-the-art (SOTA) performance on the widely-used Audioset dataset. However, their impressive performance often comes at the cost of high memory usage, slow inference speed, and considerable model delay, rendering them impractical for real-world AT applications. In

Jingyi Liao, Xiao Fan Liu, Xiao-Ke Xu, Tao Zhou

Unfolding different gender roles is preceding the efforts to reduce gender inequality. This paper analyzes COVID-19 family clusters outside Hubei Province in mainland China during the 2020 outbreak, revealing significant differences in spreading patterns across gender and family roles. Results show that men are more likely to be the imported cases of a famil

Yujiro Tamura, Takahiro Wada, Hailong Liu

With the advancements in automated driving, there is concern that motion sickness will increase as non-driving-related tasks increase. Therefore, techniques to reduce motion sickness have drawn much attention. Research studies have attempted to estimate motion sickness using computational models for controlling it. Among them, a computational model for estim

Boris Kovalerchuk, Hoang Phan

This study explores a new methodology for machine learning classification tasks in 2-dimensional visualization space (2-D ML) using Visual knowledge Discovery in lossless General Line Coordinates. It is shown that this is a full machine learning approach that does not require processing n-dimensional data in an abstract n-dimensional space. It enables discov

Limei Dai, Jiguang Bao, Bo Wang

In this paper, we obtain the interior derivative estimates of solutions for elliptic and parabolic Hessian quotient equations. Then we establish the Bernstein theorem for parabolic Hessian quotient equations, that is, any parabolically convex solution $u=u(x,t)\in C^{4,2}(\mathbb{R}^n\times (-\infty,0])$ for $-u_t\frac{S_n(D^2u)}{S_l(D^2u)}=1$ in $\mathbb{R}

Mike Perkins, Jasper Roe, Darius Postma, James McGaughran

This study explores the robustness of university assessments against the use of Open AI&#39;s Generative Pre-Trained Transformer 4 (GPT-4) generated content and evaluates the ability of academic staff to detect its use when supported by the Turnitin Artificial Intelligence (AI) detection tool. The research involved twenty-two GPT-4 generated submissions bein

Md. Shafiqul Islam, Afroza Shirin

The aim of this paper is to find the numerical solutions of the second order linear and nonlinear differential equations with Dirichlet, Neumann and Robin boundary conditions. We use the Bernoulli polynomials as linear combination to the approximate solutions of 2nd order boundary value problems. Here the Bernoulli polynomials over the interval [0, 1] are ch

Yuanyuan Chang, Dena Firoozi, David Benatia

This paper presents a dynamic game framework to analyze the role of large banks in interbank markets. By extending existing models, we incorporate a large bank as a dynamic decision-maker interacting with multiple small banks. Using the mean-field game methodology and convex analysis, best-response trading strategies are derived, leading to an approximate eq

Dustin Hayes, Boris Kovalerchuk

This work uses visual knowledge discovery in parallel coordinates to advance methods of interpretable machine learning. The graphic data representation in parallel coordinates made the concepts of hypercubes and hyperblocks (HBs) simple to understand for end users. It is suggested to use mixed and pure hyperblocks in the proposed data classifier algorithm Hy

Zizhao Hu, Mohammad Rostami

Most existing cross-modal generative methods based on diffusion models use guidance to provide control over the latent space to enable conditional generation across different modalities. Such methods focus on providing guidance through separately-trained models, each for one modality. As a result, these methods suffer from cross-modal information loss and ar

Jiti Gao, Bin Peng, Yayi Yan

This paper considers a time-varying vector error-correction model that allows for different time series behaviours (e.g., unit-root and locally stationary processes) to interact with each other to co-exist. From practical perspectives, this framework can be used to estimate shifts in the predictability of non-stationary variables, test whether economic theor

Boris Kovalerchuk Andrew Dunn, Alex Worland, Sridevi Wagle

To increase the interpretability and prediction accuracy of the Machine Learning (ML) models, visualization of ML models is a key part of the ML process. Decision Trees (DTs) are essential in machine learning (ML) because they are used to understand many black box ML models including Deep Learning models. In this research, two new methods for creation and en

Raula Gaikovina Kula, Gregorio Robles

Software ecosystems have gained a lot of attention in recent times. Industry and developers gather around technologies and collaborate to their advancement; when the boundaries of such an effort go beyond certain amount of projects, we are witnessing the appearance of Free/Libre and Open Source Software (FLOSS) ecosystems. In this chapter, we explore two asp

Elizabeth A. Olson, Jana Pavlasek, Jasmine A. Berry, Odest Chadwicke Jenkins

Particle filtering is a common technique for six degrees of freedom (6D) pose estimation due to its ability to tractably represent belief over object pose. However, the particle filter is prone to particle deprivation due to the high-dimensional nature of 6D pose. When particle deprivation occurs, it can cause mode collapse of the underlying belief distribut

Nityasa Mishra, Louis E. Strigari

We examine solar neutrinos in dark matter detectors including the effects of flavor-dependent radiative corrections to the CE$\nu$NS cross section. Working within a full three-flavor framework, and including matter effects within the Sun and Earth, detectors with thresholds $\lesssim 1$ keV and exposures of $\sim 100$ ton-year could identify contributions to

Kai Mei, Zheng Li, Zhenting Wang, Yang Zhang

Prompt-based learning is vulnerable to backdoor attacks. Existing backdoor attacks against prompt-based models consider injecting backdoors into the entire embedding layers or word embedding vectors. Such attacks can be easily affected by retraining on downstream tasks and with different prompting strategies, limiting the transferability of backdoor attacks.

Kai Tan, Pierre C. Bellec

This paper investigates the asymptotic distribution of the maximum-likelihood estimate (MLE) in multinomial logistic models in the high-dimensional regime where dimension and sample size are of the same order. While classical large-sample theory provides asymptotic normality of the MLE under certain conditions, such classical results are expected to fail in

S Akshay, Paul Gastin, R Govind, Aniruddha R Joshi

In this paper, we consider a model of generalized timed automata (GTA) with two kinds of clocks, history and future, that can express many timed features succinctly, including timed automata, event-clock automata with and without diagonal constraints, and automata with timers. Our main contribution is a new simulation-based zone algorithm for checking reacha

E. R. Di Lascio

The magnetometric technique of First Order Reversal Curve (FORC) analysis, applicable to hysteretic systems, is introduced to the study of superconducting samples. Some typical superconducting structures in FORC diagram are identified, and the reversible and irreversible components are isolated, allowing the identification of typical magnetic features for su

Chun How Tan, Austin Chan, Malay Haldar, Jie Tang

At Airbnb, an online marketplace for stays and experiences, guests often spend weeks exploring and comparing multiple items before making a final reservation request. Each reservation request may then potentially be rejected or cancelled by the host prior to check-in. The long and exploratory nature of the search journey, as well as the need to balance both

Shengtong Zhang

For each uniformity $k \geq 3$, we construct $k$-uniform linear hypergraphs $G$ with arbitrarily large maximum degree $\Delta$ whose independence polynomial $Z_G$ has a root $\lambda$ with $\lvert\lambda\rvert = O\left(\frac{\log \Delta}{\Delta}\right)$. This disproves a recent conjecture of Galvin, McKinley, Perkins, Sarantis, and Tetali.

Liam Toran, Cory Van Der Walt, Alan Sammarone, Alex Keller

This paper aims to categorize bank transactions using weak supervision, natural language processing, and deep neural network techniques. Our approach minimizes the reliance on expensive and difficult-to-obtain manual annotations by leveraging heuristics and domain knowledge to train accurate transaction classifiers. We present an effective and scalable end-t

Fangchi Yan, Qingtian Zhang

We study the initial value problem of quasi-linear Hamiltonian mKdV equations. Our goal is to prove the global-in-time existence of a solution given sufficiently smooth, localized, and small initial data. To achieve this, we utilize the bootstrap argument, Sobolev energy estimates, and the dispersive estimate. This proof relies on the space-time resonance me