AI Blogs
The Utilization of Successor Representation for Temporal Abstraction in Reinforcement Learning
Temporal Abstraction in Reinforcement Learning with the Successor Representation Authors: Marlos C. Machado, Andre Barreto, Doina Precup, Michael Bowling; Volume 24, Issue 80, Pages 1-69, 2023. Abstract Intelligence often involves reasoning at multiple levels of...
![Addressing Imbalanced Classification for Diverse Minorities (arXiv:2308.14838v1 [cs.LG])](https://instadatanews.com/wp-content/uploads/2023/08/arxiv-logo-fb-400x250.png){kind=logo}
Addressing Imbalanced Classification for Diverse Minorities (arXiv:2308.14838v1 [cs.LG])
In various real-world applications, imbalanced datasets pose significant challenges when training classifiers. This issue becomes even more difficult when working with large datasets. To address this problem, over-sampling techniques have been developed to interpolate...
Applications of Polynomial-Time Algorithms for Counting and Sampling Markov Equivalent Directed Acyclic Graphs
Polynomial-Time Algorithms for Counting and Sampling Markov Equivalent DAGs with Applications Marcel Wienöbst, Max Bannach, Maciej Liśkiewicz; 24(213):1−45, 2023. Abstract Counting and sampling directed acyclic graphs from a Markov equivalence class are essential...
Exploration of Efficient Model Updates: Dynamic Sparse Training for Continual Learning
Continual learning (CL) is the ability of an intelligent system to acquire and retain knowledge from a stream of data with minimal computational overhead. Various approaches, such as regularization, replay, architecture, and parameter isolation, have been introduced...
Optimizing Online Operations on Riemannian Manifolds
Online Optimization over Riemannian Manifolds Authors: Xi Wang, Zhipeng Tu, Yiguang Hong, Yingyi Wu, Guodong Shi; Volume 24, Issue 84, Pages 1-67, 2023. Abstract In recent years, there has been a significant increase in research on online optimization. This paper...
Examining the Impact of Pre-training on Lifelong Learning: An Empirical Study
Investigating the Role of Pre-training in Lifelong Learning: An Empirical Study Sanket Vaibhav Mehta, Darshan Patil, Sarath Chandar, Emma Strubell; 24(214):1−50, 2023. Abstract The lifelong learning paradigm in machine learning is an appealing alternative to isolated...
Statistical Verification with Imprecise Neural Networks: An Approach for Distributional Robustness
The arXivLabs framework enables collaborators to develop and share new features directly on our website. Both individuals and organizations that collaborate with arXivLabs uphold our values of openness, community, excellence, and user data privacy. We are dedicated to...
Dimension-Based Mixed Membership Models for Multivariate Categorical Data
Dimension-Grouped Mixed Membership Models for Multivariate Categorical Data Authors: Yuqi Gu, Elena E. Erosheva, Gongjun Xu, David B. Dunson; Volume 24, Issue 88, Pages 1-49, 2023. Abstract Mixed Membership Models (MMMs) are widely used latent structure models for...
Neural Operators for Scattering Analysis
arXivLabs is a platform where collaborators can create and share new features for our website. Both individuals and organizations who collaborate with arXivLabs share our values of openness, community, excellence, and user data privacy. We only work with partners who...
Distributed Data and its Application in Least Squares Model Averaging
Least Squares Model Averaging for Distributed Data Authors: Haili Zhang, Zhaobo Liu, Guohua Zou; Journal of Machine Learning Research 24(215):1−59, 2023. Abstract The divide and conquer algorithm is commonly used in big data analysis. However, the theory of model...
A fuzzy cluster validity index with secondary options detector based on correlation
[Submitted on 28 Aug 2023] Download a PDF of the paper titled A correlation-based fuzzy cluster validity index with secondary options detector, by Nathakhun Wiroonsri and Onthada Preedasawakul Download PDF Abstract: The problem of determining the optimal number of...
Robust Statistical Learning with Non-Asymptotic Guarantees in the Presence of Infinite Variance
Non-Asymptotic Guarantees for Robust Statistical Learning under Infinite Variance Assumption Lihu Xu, Fang Yao, Qiuran Yao, Huiming Zhang; 24(92):1−46, 2023. Abstract The field of statistics and machine learning has seen a growing interest in developing robust...
Generating tabular datasets with differential privacy
arXivLabs is a platform where collaborators can create and share new features for arXiv directly on our website. Both individuals and organizations that collaborate with arXivLabs share our core values of openness, community, excellence, and user data privacy. We are...
Change Point Detection using Random Forests
Random Forests for Change Point Detection Authors: Malte Londschien, Peter Bühlmann, Solt Kovács; Published in 2023. Abstract This study introduces a new method for detecting multiple change points using classifiers in a multivariate nonparametric setting. The method...
Improving Imbalanced Data Learning on a General Tree Network using Distributed Dual Coordinate Ascent
arXivLabs is a platform where collaborators can create and share new features for the arXiv website. Both individuals and organizations that work with arXivLabs share our values of openness, community, excellence, and user data privacy. We only collaborate with...
The Impact of Limited Initialization, Measurement Noise, and Over-parameterization
Global Convergence of Sub-gradient Method for Robust Matrix Recovery: Small Initialization, Noisy Measurements, and Over-parameterization Jianhao Ma, Salar Fattahi; 24(96):1−84, 2023. Abstract This study examines the performance of the sub-gradient method (SubGM) on a...
Active Automata Learning with Conflict Awareness (arXiv:2308.14781v1 [cs.LG])
Active automata learning algorithms face challenges when dealing with conflicting information in observation data, making them less effective in scenarios with noise or system mutations. To address this, we propose the Conflict-Aware Active Automata Learning (C3AL)...
GANs: Gradient Flows Leading to Convergence
GANs as Converging Gradient Flows Authors: Yu-Jui Huang, Yuchong Zhang; Published in 2023; Journal of Machine Learning Research, 24(217):1−40. Abstract This study addresses the problem of unsupervised learning using gradient descent in the space of probability density...
A Versatile Framework for Federated Learning
FedLab: A Versatile Framework for Federated Learning Dun Zeng, Siqi Liang, Xiangjing Hu, Hui Wang, Zenglin Xu; 24(100):1−7, 2023. Abstract FedLab is an open-source framework that offers a lightweight and flexible solution for simulating federated learning. The main...
A Systematic Approach to Efficiently Analyze Hyperspectral Images for Plastic Characterization
[Submitted on 28 Aug 2023] Download a PDF of the paper titled "Systematic reduction of Hyperspectral Images for high-throughput Plastic Characterization" by Mahdiyeh Ghaffari and 5 other authors. Download PDF Abstract: Hyperspectral Imaging (HSI) combines microscopy...
Enhanced Model-based Policy Optimization through Adaptation
Adaptation Augmented Model-based Policy Optimization Jian Shen, Hang Lai, Minghuan Liu, Han Zhao, Yong Yu, Weinan Zhang; 24(218):1−35, 2023. Abstract Model-based reinforcement learning (RL) is often more sample efficient compared to model-free RL as it utilizes a...
XVir: A Transformer-Based Approach for Detecting Viral Reads in Cancer Samples.
Approximately 15% of cancers worldwide are believed to be caused by viral infections. Some of the viruses that can increase the risk of cancer include human papillomavirus, hepatitis B and C viruses, Epstein-Barr virus, and human immunodeficiency virus. Recent...
Probabilistic Metrics for Intrinsic Gaussian Processes on Uncharted Manifolds
Intrinsic Gaussian Process on Unknown Manifolds with Probabilistic Metrics Mu Niu, Zhenwen Dai, Pokman Cheung, Yizhu Wang; 24(104):1−42, 2023. Abstract This article presents a new approach for constructing Intrinsic Gaussian Processes for regression on unknown...
A Revised Approach to Concept Editing in Diffusion Models (arXiv:2308.14761v1 [cs.CV])
Text-to-image models face several safety concerns that may hinder their applicability for deployment. Traditionally, these concerns, including bias, copyright infringement, and offensive content, have been addressed separately. However, in real-world scenarios, all...
A Revised Approach to Functional Generalized Linear Models with Massive Data: Functional L-Optimality Subsampling
Functional L-Optimality Subsampling for Functional Generalized Linear Models with Massive Data Authors: Hua Liu, Jinhong You, Jiguo Cao; Published in Journal of Machine Learning Research, 24(219):1−41, 2023. Abstract When dealing with massive data, memory and...
Unified Force-Centric Pre-Training for 3D Molecular Conformations: Harnessing the Force, May the Force be with You (arXiv:2308.14759v1 [physics.chem-ph])
Recent research has demonstrated the potential of utilizing pre-trained models for 3D molecular representation. However, these existing models primarily focus on equilibrium data and neglect off-equilibrium conformations. The main challenge lies in extending these...
Using Physics-Informed Priors for Bayesian Calibration of Imperfect Computer Models
Bayesian Calibration of Imperfect Computer Models using Physics-Informed Priors Michail Spitieris, Ingelin Steinsland; 24(108):1−39, 2023. Abstract In this paper, we present a computationally efficient data-driven framework for quantifying uncertainty in physical...
An Integrated Approach for Decomposing Distributional Value Functions in Multi-Agent Reinforcement Learning
A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning Wei-Fang Sun, Cheng-Kuang Lee, Simon See, Chun-Yi Lee; 24(220):1−32, 2023. Abstract In fully cooperative multi-agent reinforcement learning (MARL) settings, the...
Stochastic Configuration Machines: Enabling Industrial Artificial Intelligence (arXiv:2308.13570v1 [cs.LG])
Real-time predictive modeling is highly anticipated in the field of industrial artificial intelligence (IAI), where neural networks play a crucial role. To effectively model and save data size for industrial applications, this paper introduces a new randomized learner...
Modularity as a Distance: Exploring Community Detection through Hyperspherical Geometry
The Hyperspherical Geometry of Community Detection: Modularity as a Distance Martijn Gösgens, Remco van der Hofstad, Nelly Litvak; 24(112):1−36, 2023. Abstract This article presents a metric space of clusterings, where clusterings are represented by a binary vector...
Completion of Block-wise Overlapping Noisy Matrices for Multi-source Learning
Multi-source Learning via Completion of Block-wise Overlapping Noisy Matrices Doudou Zhou, Tianxi Cai, Junwei Lu; 24(221):1−43, 2023. Abstract Electronic healthcare records (EHR) serve as a valuable resource for healthcare research. One challenge in effectively...
DB and AI Integration: A Versatile Toolkit for Extensibility
SQLFlow: A Flexible Toolkit for Integrating Databases and AI Authors: Jun Zhou, Ke Zhang, Lin Wang, Hua Wu, Yi Wang, ChaoChao Chen; Published in 2023, 24(116):1−9. Abstract The integration of AI algorithms into databases is an ongoing endeavor in both academia and...
Using Topic Modeling to Identify Mental Health Research Topics
The content can be rewritten as follows: arXivLabs is a platform where collaborators can create and share new features for arXiv directly on our website. We are proud to have individuals and organizations who share our values of openness, community, excellence, and...
Convergence-Guaranteed Actor-Critic Method for Solving the Linear Quadratic Regulator in a Single Timescale
Single Timescale Actor-Critic Method for Solving the Linear Quadratic Regulator with Convergence Guarantees Mo Zhou, Jianfeng Lu; 24(222):1−34, 2023. Abstract We propose a single timescale actor-critic algorithm for solving the linear quadratic regulator (LQR)...
A Diffusion Model for Accurate PPG-to-ECG Translation with Region Disentanglement.
The increasing prevalence of cardiovascular diseases (CVDs) highlights the need for affordable and easily accessible tools for continuous cardiac monitoring. While Electrocardiography (ECG) is considered the standard, continuous monitoring remains a challenge. As a...
The Ill-Posed Nature of Maximum Likelihood Estimation in Gaussian Process Regression
Ill-Posedness of Maximum Likelihood Estimation in Gaussian Process Regression Toni Karvonen, Chris J. Oates; 24(120):1−47, 2023. Abstract Gaussian process regression is widely used in machine learning and statistics, and maximum likelihood estimation is commonly...
An Iterative Refinement Approach for MLLM: Introducing MLLM-DataEngine (arXiv:2308.13566v1 [cs.LG])
In this paper, we introduce MLLM-DataEngine, a novel closed-loop system that connects data generation, model training, and evaluation. Despite the advancements in Multimodal Large Language Models (MLLMs) in instruction dataset building and benchmarking, the current...
Neural Network-Based Estimation of Conditional Distribution Function for Censored and Uncensored Data
Conditional Distribution Function Estimation Using Neural Networks for Censored and Uncensored Data Authors: Bingqing Hu, Bin Nan; Volume 24, Issue 223, Pages 1-26, 2023. Abstract The majority of research on neural networks focuses on estimating the conditional mean...
Quantifying Uncertainty in Online Learning and Stochastic Approximation
HiGrad: Uncertainty Quantification for Online Learning and Stochastic Approximation Weijie J. Su, Yuancheng Zhu; 24(124):1−53, 2023. Abstract Stochastic gradient descent (SGD) is a widely used method for online learning in cases where data is received in a continuous...
Stochastic Approximation to Generalized Method of Moments: An Overview (arXiv:2308.13564v1 [econ.EM])
We present a new set of algorithms called Stochastic Generalized Method of Moments (SGMM) for estimating and inferring on moment restriction models that are overidentified. Our SGMM algorithm is a novel alternative to the widely used offline GMM algorithm proposed by...
Using Amazon SageMaker, HashiCorp Terraform, and GitLab CI/CD for MLOps: Batch Inference, Model Monitoring, and Retraining
Maintaining machine learning (ML) workflows in production can be challenging due to the various tasks involved, such as creating CI/CD pipelines, model versioning, monitoring for data drift, model retraining, and manual approval processes. To address these challenges,...
Segmentation: A Reliable Framework Based on Ranking
RankSEG: A Consistent Ranking-based Framework for Segmentation Authors: Ben Dai, Chunlin Li; Published in Journal of Machine Learning Research, 24(224):1−50, 2023. Abstract Segmentation is an important field in computer vision and natural language processing, where...
A Comparative Study of ChatGPT, BARD, and GPT-4: Analyzing Crash Narratives Using Large Language Models
Extracting information from crash narratives using text analysis is a common practice in traffic safety research. With the recent advancements in large language models (LLM), it is important to understand how popular LLM interfaces perform in classifying or extracting...
A Model for Dynamic Multilayer Networks: Eigenmodel Approach
An Eigenmodel for Dynamic Multilayer Networks Authors: Joshua Daniel Loyal, Yuguo Chen; Published in 2023, Volume 24(128), Pages 1-69 Abstract Dynamic multilayer networks often represent the structure of multiple co-evolving relations. However, statistical models for...
Causal Inference through Machine Unlearning (arXiv:2308.13559v1 [cs.LG])
Machine learning models are widely used for making predictions and deriving insights from data. However, to ensure user privacy, it is essential to enable these models to forget some of the information they have learned about a specific user. This process, known as...
The Boundaries of Dense Simplicial Complexes
Limits of Dense Simplicial Complexes By T. Mitchell Roddenberry and Santiago Segarra; 24(225):1−42, 2023. Abstract In this paper, we present a theory on the limits of sequences of dense abstract simplicial complexes. Convergence of a sequence is determined by the...
Quantifying Bias in GAN-Augmented Data: A Comprehensive Study
arXivLabs is a platform where collaborators can develop and share new features for arXiv directly on our website. We are proud to work with both individuals and organizations who share our values of openness, community, excellence, and user data privacy. We are...
Deep Learning AutoML: A Comprehensive Library
AutoKeras: A Deep Learning AutoML Library Authors: Haifeng Jin, François Chollet, Qingquan Song, Xia Hu; Published in 2023; Volume 24, Issue 6, Pages 1-6. Abstract Deep learning requires expertise in software tools like TensorFlow and Keras, as well as knowledge of...
Time Series Machine Learning: A Comprehensive Approach from Start to Finish
Merlion: End-to-End Machine Learning for Time Series Aadyot Bhatnagar, Paul Kassianik, Chenghao Liu, Tian Lan, Wenzhuo Yang, Rowan Cassius, Doyen Sahoo, Devansh Arpit, Sri Subramanian, Gerald Woo, Amrita Saha, Arun Kumar Jagota, Gokulakrishnan Gopalakrishnan, Manpreet...
LiNGAM-Based Python Package for Causal Discovery
Python package for causal discovery based on LiNGAM Takashi Ikeuchi, Mayumi Ide, Yan Zeng, Takashi Nicholas Maeda, Shohei Shimizu; 24(14):1−8, 2023. Abstract This article presents an open-source Python package that focuses on causal discovery using LiNGAM (Linear...
Generating ENA Visualizations for Asynchronous Online Discussion Using a Combination of Automatic Coding and Instructor Input (arXiv:2308.13549v1 [cs.HC])
Asynchronous online discussions are commonly used in hybrid and online courses to facilitate social interaction. However, evaluating these discussions can be a daunting task for instructors. This paper proposes a solution using Latent Dirichlet Analysis (LDA) and the...
Autoregressive Networks: An Overview
Autoregressive Networks Binyan Jiang, Jialiang Li, Qiwei Yao; 24(227):1−69, 2023. Abstract This study introduces a first-order autoregressive (AR(1)) model to represent dynamic network processes, where edges change over time while nodes remain unchanged. The model...
Functional Graph Contrastive Learning in Hyperscanning EEG Exposes Emotional Contagion Induced by Stressors Based on Stereotypes. (arXiv:2308.13546v1 [eess.SP])
This study explores the complexities of emotional contagion and its influence on performance in collaborative interactions. Specifically, it focuses on the impact of stereotype-based stress (SBS) on female pairs during problem-solving tasks. The research aims to...
Accelerated Algorithms and Lower Bounds for Bilevel Optimization
Lower Bounds and Accelerated Algorithms for Bilevel Optimization Kaiyi ji, Yingbin Liang; 24(22):1−56, 2023. Abstract Bilevel optimization has recently gained increased attention due to its wide range of applications in modern machine learning problems. While the...
The Effectiveness of Nuclear-norm-based Matrix Completion for Smooth Non-linear Structured Problems
On the Optimality of Nuclear-norm-based Matrix Completion for Problems with Smooth Non-linear Structure Yunhua Xiang, Tianyu Zhang, Xu Wang, Ali Shojaie, Noah Simon; 24(228):1−38, 2023. Abstract Originally developed for imputing missing entries in low rank or...
Mitigating Attacks on Federated Learning Defense Systems
Attacks against Federated Learning Defense Systems and their Mitigation Cody Lewis, Vijay Varadharajan, Nasimul Noman; 24(30):1−50, 2023. Abstract Federated learning (FL) defense systems have been developed to protect against attacks from untrustworthy endpoints....
Creating Comprehensible and Equitable Boolean Rule Sets through Column Generation
Interpretable and Fair Boolean Rule Sets via Column Generation Authors: Connor Lawless, Sanjeeb Dash, Oktay Gunluk, Dennis Wei; Volume 24, Issue 229, Pages 1-50, 2023. Abstract This research focuses on the learning of Boolean rules in disjunctive normal form (DNF),...
Nonlinear Generalized Nash Equilibrium Problems: First-Order Algorithm Approaches
First-Order Algorithms for Nonlinear Generalized Nash Equilibrium Problems Authors: Michael I. Jordan, Tianyi Lin, Manolis Zampetakis; Volume 24, Issue 38, Pages 1-46, 2023. Abstract This paper focuses on the computation of equilibria in a class of nonlinear...
Feature Extraction for Bangla Text Classification Using Deep Generative Models on a Comprehensive Dataset
[Submitted on 21 Aug 2023] Click here to download a PDF of the paper titled "Feature Extraction Using Deep Generative Models for Bangla Text Classification on a New Comprehensive Dataset" by Md. Rafi-Ur-Rashid and 2 other authors Download PDF Abstract: The task of...
Sample Complexity for Distributionally Robust Learning with chi-square Divergence
Sample Complexity for Distributionally Robust Learning under chi-square divergence Zhengyu Zhou, Weiwei Liu; 24(230):1−27, 2023. Abstract This paper explores the sample complexity of learning a distributionally robust predictor when facing a specific distributional...
Lets Make Something Amazing Together
Get in Touch
info@instadatahelpainews.com
+91 9903726517
InstaDataHelp Analytics Services, 2nd Main, Basapura Main Road, Electronic City Post, Bengaluru 560100, Karnataka, India