AI Blogs
![Clustering in the Absence of an Eigengap: A Study (arXiv:2308.15642v1 [cs.LG])](https://instadatanews.com/wp-content/uploads/2023/08/arxiv-logo-fb-400x250.png){kind=logo}
Clustering in the Absence of an Eigengap: A Study (arXiv:2308.15642v1 [cs.LG])
In our research, we focus on graph clustering in the Stochastic Block Model (SBM) where there are both large clusters and small, unrecoverable clusters. Previous methods for exact recovery either do not allow small clusters of size less than the square root of the...
Representation Learning Enables Calibrated Multiple-Output Quantile Regression
Calibrated Multiple-Output Quantile Regression with Representation Learning Authors: Shai Feldman, Stephen Bates, Yaniv Romano; Journal of Machine Learning Research, 24(24):1−48, 2023. Abstract We present a novel method for generating predictive regions that encompass...
Physics-Informed Neural Networks for Determining Constitutive Parameters in Complex Hyperelastic Solids (arXiv:2308.15640v1 [cond-mat.mtrl-sci])
The identification of constitutive parameters in engineering and biological materials, especially those with complex geometries and mechanical behaviors, has long been a challenge. The emergence of Physics-Informed Neural Networks (PINNs) has provided promising...
Quantization for Weakly Continuous Functions: Achieving Convergence and Near-Optimality
Q-Learning for MDPs with General Spaces: Convergence and Near Optimality via Quantization under Weak Continuity Authors: Ali Kara, Naci Saldi, Serdar Yüksel; Volume 24, Issue 199, Pages 1-34, 2023. Abstract This paper explores the applicability of reinforcement...
Hyperbolic CNNs: A Deep Learning Approach with Applications (arXiv:2308.15639v1 [cs.LG])
Artificial Intelligence has experienced a surge in interest in the last decade, largely due to the advancements in Deep Learning. Deep learning researchers have achieved great success in image processing through the use of Convolutional Neural Networks (CNNs)....
The Influence of Classification Difficulty on Weight Matrices Spectra in Deep Learning: A Study on Early Stopping Implementation
Impact of Classification Difficulty on the Spectra of Weight Matrices in Deep Learning and its Application to Early Stopping Xuran Meng, Jeff Yao; 24(28):1−40, 2023. Abstract Recent research has focused on understanding the success of deep learning. Random Matrix...
Rank-Aware Contextual Reasoning on Whole Slide Images for Weakly Supervised Skin Cancer Grading
[Submitted on 29 Aug 2023] Authors:Anirudh Choudhary, Angelina Hwang, Jacob Kechter, Krishnakant Saboo, Blake Bordeaux, Puneet Bhullar, Nneka Comfere, David DiCaudo, Steven Nelson, Emma Johnson, Leah Swanson, Dennis Murphree, Aaron Mangold, Ravishankar K. Iyer...
Causal Discovery for Zero-Inflated Count Data Using Model-Based Approach
Model-based Causal Discovery for Zero-Inflated Count Data Junsouk Choi, Yang Ni; 24(200):1−32, 2023. Abstract Zero-inflated count data are common in various scientific fields, including social science, biology, and genomics. However, few causal discovery approaches...
Enabling Differentiable Graph Attacks: Simultaneously Perturbing Everything.
Graph neural networks (GNNs) have been widely used in various applications such as social networks, recommendation systems, and online web services. However, GNNs are susceptible to adversarial attacks, which can significantly reduce their effectiveness. Previous...
A Geometric Approach to Sparse PCA
A Geometric Approach to Sparse PCA Dimitris Bertsimas, Driss Lahlou Kitane; 24(32):1−33, 2023. Abstract This paper presents a novel algorithm called GeoSPCA for solving the problem of maximizing the variance explained from a data matrix using orthogonal sparse...
Discrete Variable Mixed Variational Flows: A Study (arXiv:2308.15613v1 [stat.CO])
Variational flows have been successful in learning complex continuous distributions, but there is still a challenge in approximating discrete distributions. Current methods often involve embedding the discrete target in a continuous space, but this approach has...
Leveraging Amazon SageMaker Model Card Sharing for Enhanced Model Governance
With the increasing adoption of Artificial Intelligence (AI) and Machine Learning (ML) technologies in enterprises, it has become crucial to implement proper guardrails throughout the ML lifecycle. These guardrails ensure the security, privacy, and quality of the...
A Statistical Inverse Problems of Partial Differential Equations Approach with Variational Inverting Network
Variational Inverting Network for Statistical Inverse Problems of Partial Differential Equations Authors: Junxiong Jia, Yanni Wu, Peijun Li, Deyu Meng; 24(201):1−60, 2023. Abstract In order to address the uncertainties in inverse problems of partial differential...
InstaTune: Rapid Neural Architecture Search During Fine-Tuning. (arXiv:2308.15609v1 [cs.LG])
One-Shot Neural Architecture Search (NAS) algorithms often rely on training a super-network that is hardware agnostic for a specific task. These algorithms then extract optimal sub-networks from the trained super-network for different hardware platforms. However,...
Expanding Sample Space Alters Label Distribution in Learning
Label Distribution Changing Learning with Sample Space Expanding Authors: Chao Xu, Hong Tao, Jing Zhang, Dewen Hu, Chenping Hou; 24(36):1−48, 2023. Abstract As data collection methods continue to evolve, label ambiguity has become prevalent in various applications....
Benchmark for Detecting Measurement Tampering (arXiv:2308.15605v1 [cs.LG])
Training powerful AI systems to perform complex tasks can be challenging when it comes to providing robust training signals that are resistant to manipulation. One specific concern is measurement tampering, where the AI system alters multiple measurements to make it...
Learning in Decision-Dependent Games: Exploring Multiplayer Performative Prediction
Multiplayer Performative Prediction: Learning in Decision-Dependent Games Adhyyan Narang, Evan Faulkner, Dmitriy Drusvyatskiy, Maryam Fazel, Lillian J. Ratliff; 24(202):1−56, 2023. Abstract This paper introduces a new game theoretic framework called multi-player...
A Comparative Study on Partitioning Strategies for Training Distributed Graph Neural Networks. (arXiv:2308.15602v1 [cs.DC])
The emergence of graph neural networks (GNNs) as a popular area of deep learning has sparked interest in their ability to learn from graph-structured data. However, when dealing with large-scale graphs, the computational and memory requirements of training GNNs can...
Teaching Groups Independently: Avoiding Collusion
On Batch Teaching Without Collusion Authors: Shaun Fallat, David Kirkpatrick, Hans U. Simon, Abolghasem Soltani, Sandra Zilles; Volume 24, Issue 40, Pages 1-33, 2023. Abstract In order to prevent collusion in formal models of learning from teachers, certain criteria...
Exploring the Ability of Transformers to Learn the Greatest Common Divisor
arXivLabs is a platform that allows collaborators to create and share new features on our website. Both individuals and organizations who work with arXivLabs have fully embraced and supported our principles of openness, community, excellence, and user data privacy. We...
Examining FedAvg and FedProx: Non-parametric Perspectives Beyond Stationary Points
Beyond Stationary Points: A Non-parametric Perspective on FedAvg and FedProx Authors: Lili Su, Jiaming Xu, Pengkun Yang; Journal of Machine Learning Research (JMLR), 24(203):1−48, 2023. Abstract Federated Learning (FL) is a decentralized learning framework with...
Closing Set for Robust Open-set Semi-supervised Learning: A Prototype Fission Approach (arXiv:2308.15575v1 [cs.LG])
In large-scale unsupervised datasets, Semi-supervised Learning (SSL) has a vulnerability to out-of-distribution (OOD) samples. This is because it mistakenly labels OOD samples as in-distribution (ID) due to over-confidence in pseudo-labeling. The problem stems from...
Machine-Learned Advice Enhances the Robustness of Load Balancing
Robust Load Balancing with Machine Learned Advice Sara Ahmadian, Hossein Esfandiari, Vahab Mirrokni, Binghui Peng; 24(44):1−46, 2023. Abstract This study introduces and examines a theoretical model for load balancing of large databases, specifically commercial search...
Utilizing Task-based fMRI for Synthetic Data Augmentation: Learning Sequential Information
arXivLabs is a platform where collaborators can create and share new features on our website. We collaborate with individuals and organizations who share our values of openness, community, excellence, and user data privacy. We only work with partners who adhere to...
Byzantine Learning: Enhancing Robustness through Buffered Asynchronous SGD
Buffered Asynchronous SGD for Byzantine Learning Yi-Rui Yang, Wu-Jun Li; 24(204):1−62, 2023. Abstract Distributed learning has become a popular area of research due to its wide range of applications in cluster-based large-scale learning, federated learning, edge...
Glocal Perspectives on Soccer’s Expected Goal Models
Expected goal models have become popular in recent years, but their interpretability is often limited, particularly when trained using black-box methods. To address this issue, explainable artificial intelligence tools have been developed to enhance model transparency...
Convergence Analysis of Stochastic Gradient Descent Using Bandwidth-based Step Size
Convergence of Stochastic Gradient Descent with Bandwidth-based Step Size Xiaoyu Wang, Ya-xiang Yuan; 24(48):1−49, 2023. Abstract This paper introduces a novel step-size framework for the stochastic gradient descent (SGD) method, called bandwidth-based step sizes....
Cluster Analysis for Dimensionality Reduction through pseudo-Boolean Polynomials (arXiv:2308.15553v1 [cs.IR])
We present the utilization of a reduction property found in the penalty-based formulation of pseudo-Boolean polynomials as a means to reduce dimensionality in cluster analysis procedures. Through our experiments, we demonstrate that multidimensional datasets, such as...
A Flexible Solution for Sparse Learning with L0 Regularization
L0Learn: A Scalable Package for Sparse Learning using L0 Regularization Hussein Hazimeh, Rahul Mazumder, Tim Nonet; 24(205):1−8, 2023. Abstract This article introduces L0Learn, an open-source package designed for sparse linear regression and classification using L0...
Mediators’ Feedback on the Article “Pure Exploration” (arXiv:2308.15552v1 [cs.LG])
In this work, we introduce a new version of the best-arm identification problem called best-arm identification under mediators' feedback (BAI-MF). In traditional BAI problems, the goal is to find the arm with the highest expected reward. However, this framework does...
Conditions Required for Inverse Reinforcement Learning of Bayesian Stopping Time Problems
Necessary and Sufficient Conditions for Inverse Reinforcement Learning of Bayesian Stopping Time Problems Authors: Kunal Pattanayak, Vikram Krishnamurthy; Volume 24, Issue 52, Pages 1-64, 2023 Abstract This paper introduces a framework for inverse reinforcement...
Adversarial Style Transfer Enhances Robust Policy Optimization in Deep Reinforcement Learning
[Submitted on 29 Aug 2023] Click here to download a PDF of the paper titled "Adversarial Style Transfer for Robust Policy Optimization in Deep Reinforcement Learning" by Md Masudur Rahman and Yexiang Xue: Download PDF Abstract: This paper presents an algorithm that...
Online Learning with Memory and Non-stochastic Control in Non-stationary Environments
Non-stationary Online Learning with Memory and Non-stochastic Control Peng Zhao, Yu-Hu Yan, Yu-Xiang Wang, Zhi-Hua Zhou; 24(206):1−70, 2023. Abstract This paper investigates the problem of Online Convex Optimization (OCO) with memory, which allows loss functions to...
Enhancing perplexity tuning and computing sampling-based t-SNE embeddings
The analysis of high-dimensional data often relies on two-dimensional visualizations, commonly generated using t-distributed stochastic neighbor embedding (t-SNE). However, when dealing with large data sets, these visualizations may not be optimal due to unsuitable...
The Geometric Aspects of Stein Variational Gradient Descent
On the Geometry of Stein Variational Gradient Descent By Andrew Duncan, Nikolas Nüsken, Lukasz Szpruch; Published in 2023, Volume 24, Issue 56. Abstract Sampling or approximating high-dimensional probability distributions is a fundamental task in Bayesian inference...
Orthogonalizing Anatomy and Image-Characteristic Features in an Unsupervised Manner
arXivLabs is a platform that enables collaborators to create and distribute new features for arXiv directly on our website. Both individuals and organizations that engage with arXivLabs have embraced and embraced our principles of transparency, collaboration, quality,...
Generalized Hypergraph Cuts: Advancements in Augmented Sparsifiers
Augmented Sparsifiers for Generalized Hypergraph Cuts Nate Veldt, Austin R. Benson, Jon Kleinberg; 24(207):1−50, 2023. Abstract In this paper, we discuss the use of augmented sparsifiers for generalized hypergraph cuts. Hypergraph generalizations have been introduced...
Studying the Steganographic Capacity of Chosen Learning Models
The content is discussing the potential for machine learning and deep learning models to be used as vectors for various attack scenarios. Previous research has shown that malware can be hidden within these models, which can be seen as a form of steganography. The...
A Model-Free Algorithm for MDPs with Peak Constraints: Proven Sample-Efficiency
Provably Sample-Efficient Model-Free Algorithm for MDPs with Peak Constraints Qinbo Bai, Vaneet Aggarwal, Ather Gattami; 24(60):1−25, 2023. Abstract In the field of optimization for dynamic systems, it is common for variables to have constraints. These types of...
Identifying Dormant Cyberwarriors through Analysis of Online Forums. (arXiv:2308.15491v1 [cs.SI])
The rise of misinformation in the digital age has given birth to a new kind of warfare known as cyberwarfare. In this form of warfare, individuals known as cyberwarriors intentionally spread false information to defame their opponents or create unity among allies....
Minimizing Risk with 0-1 Loss: Exploring Minimax Risk Classifiers
Minimax Risk Classifiers with 0-1 Loss Authors: Santiago Mazuelas, Mauricio Romero, Peter Grunwald; 24(208):1−48, 2023. Abstract Supervised classification techniques utilize training samples to learn a classification rule that minimizes the expected 0-1 loss (error...
Investigating the Straggler Problem in Parameter Server on Iterative Convergent Distributed Machine Learning: An Empirical Study (arXiv:2308.15482v1 [cs.DC])
The aim of this study is to evaluate the effectiveness of existing techniques for reducing straggler delays in important iterative convergent machine learning algorithms such as Matrix Factorization (MF), Multinomial Logistic Regression (MLR), and Latent Dirichlet...
Limits and Algorithms for Sparse Linear Regression with Sublinear Sparsity
Fundamental Limits and Algorithms for Sparse Linear Regression with Sublinear Sparsity Lan V. Truong; 24(64):1−49, 2023. Abstract In this study, we investigate the normalized mutual information and minimum mean-square-error (MMSE) of sparse linear regression in the...
Predicting Online Job Failures in an HPC System Using an HPC System (arXiv:2308.15481v1 [cs.DC])
High Performance Computing (HPC) systems have become increasingly complex and have significant impacts on the economy and society. However, their high energy consumption is a critical issue in the face of environmental and energy crises. Therefore, it is crucial to...
Python Library for Deep Multi-Task Learning: A Comprehensive Toolkit
LibMTL: A Python Library for Deep Multi-Task Learning Authors: Baijiong Lin, Yu Zhang; Published in Journal of Machine Learning Research, 24(209):1−7, 2023. Abstract This article introduces LibMTL, a Python library based on PyTorch that offers a comprehensive,...
Predictive Inference of Individual Treatment Effects using Conformal Meta-learners
In this study, we address the challenge of using machine learning to predict individual treatment effects (ITEs). Previous research has focused on developing machine learning models that can estimate the conditional average treatment effect (CATE). These models...
Dealing with Large-scale Data: Distributed Nonparametric Regression Imputation for Missing Response Problems
Distributed Nonparametric Regression Imputation for Missing Response Problems with Large-scale Data Ruoyu Wang, Miaomiao Su, Qihua Wang; 24(68):1−52, 2023. Abstract Missing data analysis often employs nonparametric regression imputation, but this approach faces...
Combining Hard Negative Sampling with Supervised Contrastive Learning
Current image models typically use a two-stage approach: pre-training on large datasets and then fine-tuning using cross-entropy loss. However, studies have shown that cross-entropy loss may not provide optimal generalization and stability. Although supervised...
Foundational Principles of GFlowNet
GFlowNet Foundations Yoshua Bengio, Salem Lahlou, Tristan Deleu, Edward J. Hu, Mo Tiwari, Emmanuel Bengio; 24(210):1−55, 2023. Abstract This paper presents additional theoretical properties of Generative Flow Networks (GFlowNets), a method introduced for sampling...
Hierarchical Clustering for Document Scaling using Poisson Distribution
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...
Which Option Do You Prefer: Simultaneous or Repeated Greed?
Simultaneous or Repeated Greedy: How Do You Want Your Greedy? Moran Feldman, Christopher Harshaw, Amin Karbasi; 24(72):1−87, 2023. Abstract In this paper, we introduce SimultaneousGreedys, a deterministic algorithm for constrained submodular maximization. The...
Neural Adaptive Smoothing via Twisting: Introducing NAS-X (arXiv:2308.14864v1 [cs.LG])
Our paper introduces Neural Adaptive Smoothing via Twisting (NAS-X), a novel approach for learning and inference in sequential latent variable models using reweighted wake-sleep (RWS). NAS-X is designed to handle both discrete and continuous latent variables and...
Utilize the QnABot on AWS Solution with Amazon Lex, Amazon Kendra, and Large Language Models for Implementing Self-Service Question Answering Deployment
QnABot on AWS is an open-source chatbot solution powered by Amazon Lex. It is designed to provide conversational AI capabilities across multiple channels and languages, allowing businesses to deploy self-service chatbots in their contact centers, websites, and social...
Mean Field Optimization Problem: An Exploration of Entropic Fictitious Play
Entropic Fictitious Play for Mean Field Optimization Problem By Fan Chen, Zhenjie Ren, and Songbo Wang; Volume 24, Issue 211, Pages 1-36, 2023. Abstract This study focuses on the mean field limit of two-layer neural networks, where the number of neurons tends to...
Assessing Crucial Spatiotemporal Learners for Detecting Anomalies in Print Track through Melt Pool Image Streams
Recent advancements in machine learning applied to metal additive manufacturing (MAM) have shown great potential in overcoming the key challenges hindering the widespread adoption of MAM technology. Current research in this field highlights the importance of utilizing...
A Subspace-based Approach for Dimensionality Reduction and Variable Selection using Randomization
A New Approach for Dimensionality Reduction and Variable Selection Authors: Di Bo, Hoon Hwangbo, Vinit Sharma, Corey Arndt, Stephanie TerMaath; Published in Journal of Machine Learning Research (JMLR), 2023. Abstract High-dimensional data analysis provides a detailed...
Stream Clustering for Evolving Data Streams Utilizing Synthetic Minority Oversampling
arXivLabs is a platform where collaborators can create and share new features for arXiv directly on our website. Both individuals and organizations who work with arXivLabs have embraced our values of openness, community, excellence, and user data privacy. We are...
Leveraging AWS and generative AI to automatically generate impressions from radiology reports
Radiology reports are detailed documents that provide an interpretation of radiological imaging results. Typically, radiologists review and interpret the images, and then summarize the key findings. The summary, known as the impression, is crucial for clinicians and...
A Group Sparsity Leaky ReLU Neural Network Training Algorithm using an Inexact Augmented Lagrangian Approach
An Inexact Augmented Lagrangian Algorithm for Training Leaky ReLU Neural Network with Group Sparsity Authors: Wei Liu, Xin Liu, Xiaojun Chen; Journal: 24(212):1−43, 2023. Abstract The use of leaky ReLU networks with a group sparse regularization term has become...
User Neck Muscle Contraction Modeling and Prediction
arXivLabs is a platform that enables collaborators to create and share new features on our website. We welcome both individuals and organizations who embrace our core values of openness, community, excellence, and user data privacy. We are dedicated to working with...
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