AI Blogs
The Criterion of d-Separation in Categorical Probability
The d-Separation Criterion in Categorical Probability Tobias Fritz, Andreas Klingler; 24(46):1−49, 2023. Abstract The d-separation criterion is used to determine the compatibility of a joint probability distribution with a directed acyclic graph by examining certain...
Comparative User Test: Assessing the Influence of Geolocation Data on Usability of Augmented Reality
The paper titled "Impact of geolocation data on augmented reality usability: A comparative user test" was authored by Julien Mercier (Lab-Sticc_decide, Ubs, Hes-So, Hes-So, Heig-Vd), N. Chabloz (Hes-So, Heig-Vd, Hes-So), G. Dozot (Hes-So, Heig-Vd, Hes-So), C. Audrin,...
Generalized Stochastic Dominance: A Statistical Approach to Comparing Classifiers
Statistical Comparisons of Classifiers by Generalized Stochastic Dominance Authors: Christoph Jansen, Malte Nalenz, Georg Schollmeyer, Thomas Augustin; 24(231):1−37, 2023. Abstract Comparing classifiers across multiple data sets and criteria is a crucial question in...
Collaborative Filtering Unleashed: A Study on Adversarial Approaches (arXiv:2308.13541v1 [cs.IR])
Collaborative Filtering (CF) has been successfully utilized to assist users in discovering items of interest. However, existing CF methods are hindered by the issue of noisy data, which negatively affects the quality of recommendations. To address this problem,...
Sharp Thresholds and Contiguity in the Contextual Stochastic Block Model
Contextual Stochastic Block Model: Sharp Thresholds and Contiguity Chen Lu, Subhabrata Sen; 24(54):1−34, 2023. Abstract This study focuses on community detection in the "contextual stochastic block model" (Yan and Sarkar, 2020; Deshpande et al., 2018). Deshpande et...
Neural Network Training Enhanced with Lifted Bregman Algorithm
Lifted Bregman Training of Neural Networks Xiaoyu Wang, Martin Benning; 24(232):1−51, 2023. Abstract A new mathematical formulation is introduced for training feed-forward neural networks with potentially non-smooth proximal maps as activation functions. This...
Harnessing the Potential of Embeddings for Multi-task Recommendation in STEM Field
Multi-task learning (MTL) has become increasingly popular in recommendation systems as it allows for the simultaneous optimization of multiple objectives. However, a major challenge in MTL is negative transfer, where the performance of certain tasks deteriorates due...
Minimizing Monotonic Alpha-divergence for Variational Inference
Monotonic Alpha-divergence Minimisation for Variational Inference Kamélia Daudel, Randal Douc, François Roueff; 24(62):1−76, 2023. Abstract This paper presents a new family of iterative algorithms designed for minimizing alpha-divergence in the context of Variational...
The Unseen Whitening Effects of Linear Autoencoders for Recommendation
In recent research on recommendation systems, there has been a focus on exploring the use of linear regression (autoencoder) models to learn item similarity. This study aims to establish a connection between linear autoencoder models and ZCA whitening for...
Effective Transfer of Strategic Knowledge
Strategic Knowledge Transfer Max Olan Smith, Thomas Anthony, Michael P. Wellman; 24(233):1−96, 2023. Abstract When playing or solving a game, it is common to encounter a series of changing strategies used by other agents. These strategies often have overlapping...
Improving ROC Curve Optimization for Binary Classification and Changepoint Detection through Sort-Based Surrogate Loss
Optimizing ROC Curves with a Sort-Based Surrogate Loss for Binary Classification and Changepoint Detection Authors: Jonathan Hillman, Toby Dylan Hocking; Published in 24(70):1−24, 2023. Abstract Receiver Operating Characteristic (ROC) curves are valuable in evaluating...
A Toolkit for Multimodal Deep Learning with Standardized Features
MultiZoo and MultiBench: A Toolkit for Multimodal Deep Learning Authors: Paul Pu Liang, Yiwei Lyu, Xiang Fan, Arav Agarwal, Yun Cheng, Louis-Philippe Morency, Ruslan Salakhutdinov; Published in 2023, Volume 24(234), Pages 1-7. Abstract The process of learning...
Learning to Imitate from a Single Video Demonstration: A Step Towards Mastery
Towards Learning to Imitate from a Single Video Demonstration Glen Berseth, Florian Golemo, Christopher Pal; 24(78):1−26, 2023. Abstract Learning to imitate behaviors observed in videos, without having access to the internal state or action information of the observed...
Asynchronous Clustered Federated Learning with DAG-DLT Framework
Federated Learning (FL) is a technique that focuses on training a global model while ensuring the privacy of client data. However, FL encounters challenges due to the non-IID data distribution among clients. To address this, Clustered FL (CFL) has emerged as a...
Efficient and Highly Effective Adversarial Algorithms for Accurate Estimation in Contaminated Gaussian Models
Tractable and Near-Optimal Adversarial Algorithms for Robust Estimation in Contaminated Gaussian Models Ziyue Wang, Zhiqiang Tan; 24(235):1−112, 2023. Abstract This study focuses on the problem of simultaneous estimation of location and variance matrix under the...
A Survey on Federated Learning in IoT: Considering Resource Constraints (arXiv:2308.13157v1 [cs.LG])
This research paper discusses the integration of the Internet of Things (IoT) ecosystem with Federated Learning (FL), a decentralized machine learning technique. FL is commonly used to collect and train machine learning models from various distributed data sources....
Understanding Partial Differential Equations in Reproducing Kernel Hilbert Spaces
Learning Partial Differential Equations in Reproducing Kernel Hilbert Spaces George Stepaniants; 24(86):1−72, 2023. Abstract A new approach is proposed for learning the fundamental solutions (Green's functions) of various linear partial differential equations (PDEs)...
Improving Breast Cancer Classification with Lightweight Attention Mechanism in Transfer ResNet
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 values of openness, community, excellence, and user data privacy. We are...
Using Neural Q-Learning to Solve Partial Differential Equations
Neural Q-learning for solving PDEs Samuel N. Cohen, Deqing Jiang, Justin Sirignano; 24(236):1−49, 2023. Abstract Solving high-dimensional partial differential equations (PDEs) is a significant challenge in scientific computing. In this study, we propose a novel...
A Highly Efficient Framework for Matching Text-labels in Extreme Multi-label Text Classification
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 have embraced and embraced our values of openness, community, excellence, and user data...
The Reliable Shapley Interaction Index
Faith-Shap: The Faithful Shapley Interaction Index Che-Ping Tsai, Chih-Kuan Yeh, Pradeep Ravikumar; 24(94):1−42, 2023. Abstract Shapley values, originally designed to assign attributions to individual players in coalition games, are now commonly used in explainable...
OmniQuant: Achieving Omnidirectional Calibration in Large Language Models. (arXiv:2308.13137v1 [cs.LG])
Large language models (LLMs) have significantly transformed natural language processing tasks. However, their practical implementation is hindered by their extensive memory and computation requirements. While recent post-training quantization (PTQ) methods have proven...
AWS and Amazon SageMaker Studio Lab Partner with University of San Francisco for the 2023 Data Science Conference Datathon
AWS and the University of San Francisco's Data Institute collaborated to organize a datathon as part of the 2023 Data Science Conference (DSCO 23). The competition involved high school and undergraduate students working on a data science project focused on air quality...
Efficient Calculation of Causal Bounds at Scale
Scalable Computation of Causal Bounds Authors: Madhumitha Shridharan, Garud Iyengar; Journal: 24(237):1−35, 2023. Abstract This study focuses on the problem of computing bounds for causal queries on causal graphs with unobserved confounders and discrete-valued...
Making Reinforcement Learning Understandable: A Case Study on Surgical Recovery
[Submitted on 25 Aug 2023] Download a PDF of the paper titled "Nonparametric Additive Value Functions: Interpretable Reinforcement Learning with an Application to Surgical Recovery" by Patrick Emedom-Nnamdi and three other authors here. Abstract: We propose a...
Learning Optimal Individualized Treatment Rules with a Group-structured Approach and Numerous Treatments
Learning Optimal Group-structured Individualized Treatment Rules with Many Treatments Haixu Ma, Donglin Zeng, Yufeng Liu; 24(102):1−48, 2023. Abstract In recent years, there has been increased attention towards data-driven individualized decision making problems. One...
Forecasting Inventory Management with a Focus on Business Metrics
Business planning relies heavily on time-series forecasts. However, these forecasts often prioritize objectives that do not align with the goals of the business, resulting in forecasts that do not meet business preferences. In this study, we show that optimizing...
Efficient Calculation of Rankings using Pairwise Comparisons
Efficient Computation of Rankings from Pairwise Comparisons M. E. J. Newman; 24(238):1−25, 2023. Abstract This study focuses on the ranking of individuals, teams, or objects, based on pairwise comparisons between them, using the Bradley-Terry model. The estimation of...
Large Language Model Adaptation with Bayesian Low-Rank Approximation (arXiv:2308.13111v1 [cs.LG])
Parameter-efficient fine-tuning (PEFT) is a new approach that allows for cost-effective fine-tuning of large language models (LLMs). One popular choice for fine-tuning is low-rank adaptation (LoRA). However, a common issue with fine-tuned LLMs is that they often...
A Comprehensive Framework for Federated Optimization Considering Asynchronous and Heterogeneous Client Updates
A General Theory for Federated Optimization with Asynchronous and Heterogeneous Clients Updates Authors: Yann Fraboni, Richard Vidal, Laetitia Kameni, Marco Lorenzi; Published in 2023, Volume 24, Issue 110, Pages 1-43. Abstract This study presents a novel framework...
Survival Analysis in Electronic Health Records: Enhancing Temporal Distinctiveness through Contrastive Learning
Survival analysis is a critical component in healthcare decision-making, as it provides risk predictions for important events in a patient's medical journey. However, due to data censoring, existing survival analysis methods have limitations. This paper proposes a...
Introducing the Inaugural Margin-based Loss Function for Classification with Negative Divergence
Leaky Hockey Stick Loss: The First Negatively Divergent Margin-based Loss Function for Classification Authors: Oh-Ran Kwon, Hui Zou; Journal of Machine Learning Research, 24(239):1−40, 2023. Abstract Many modern classification algorithms are formulated using the...
Achieving Reinforcement Learning based Control for an Autonomous Formula SAE Car: A Rapid Racing Approach (arXiv:2308.13088v1 [cs.RO])
The increasing interest in autonomous navigation research has led to the introduction of a Driverless Vehicle category in Formula Student events. This study focuses on utilizing Deep Reinforcement Learning for the end-to-end control of an autonomous race car in these...
An Integrated Approach for Optimization-Driven Graph Coarsening
A Unified Framework for Optimization-Based Graph Coarsening Manoj Kumar, Anurag Sharma, Sandeep Kumar; 24(118):1−50, 2023. Abstract Graph coarsening is a commonly used technique for reducing the dimensionality of large-scale graph machine learning problems. The...
A Data Center Management Framework: Integrating Sustainable Hybrid Evolutionary Learning for Carbon, Wastewater, and Energy Efficiency
arXivLabs is a platform where collaborators can create and share new features for arXiv directly on our website. Both individuals and organizations that work with arXivLabs share our values of openness, community, excellence, and user data privacy. We are committed to...
Pathways: An Approach to Scaling Language Modeling
PaLM: Scaling Language Modeling with Pathways Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, Parker Schuh, Kensen Shi, Sasha Tsvyashchenko, Joshua Maynez,...
Reconsidering Multivariate Time Series Anomaly Detection: Advanced Algorithms and Inadequate Evaluation Methodology. (arXiv:2308.13068v1 [cs.LG])
The research topic of Multivariate Time Series (MVTS) anomaly detection has received significant attention from both industry and academia. However, upon careful examination of the literature, it becomes apparent that the community lacks organization compared to other...
Analysis of Generative Adversarial Networks Using Euler-Lagrange Method
Euler-Lagrange Analysis of Generative Adversarial Networks Siddarth Asokan, Chandra Sekhar Seelamantula; 24(126):1−100, 2023. Abstract This study focuses on Generative Adversarial Networks (GANs) and tackles the inherent functional optimization problem from a...
Enhancing Molecule Properties through Multi-Stage VAE: An Objective-Agnostic Approach (arXiv:2308.13066v1 [cs.LG])
The Variational Autoencoder (VAE) is a widely used technique in drug discovery. However, it has been observed that VAE approaches struggle to accurately represent low-dimensional data in a higher-dimensional space. This issue has not been extensively studied in the...
Enhanced Stochastic Optimization Algorithms with Power for Large-Scale Machine Learning
Improved Powered Stochastic Optimization Algorithms for Large-Scale Machine Learning Zhuang Yang; 24(241):1−29, 2023. Abstract Stochastic optimization, particularly stochastic gradient descent (SGD), has become the most commonly used method for solving machine...
ZeroLeak: Leveraging LLMs to Scale and Optimize Side-Channel Patching for Cost Efficiency (arXiv:2308.13062v1 [cs.CR])
The content discusses the challenges in patching security critical software that has side-channel leakages, due to limited resources and expertise. It highlights the increasing reliance on Large Language Models (LLMs) for code generation and proposes the use of LLMs...
A Line-Search Descent Algorithm with Complexity Guarantees for Strict Saddle Functions
A Line-Search Descent Algorithm for Strict Saddle Functions with Guaranteed Complexity Authors: Michael J. O'Neill, Stephen J. Wright; Published: 2023, Volume 24, Issue 10, Pages 1-34. Abstract This article presents a line-search algorithm that achieves the best-known...
Bayesian Exploration Networks: A Study in Machine Learning (arXiv:2308.13049v1 [cs.LG])
The paper discusses Bayesian reinforcement learning (RL) as an effective approach for making sequential decisions under uncertainty. Unlike frequentist methods, Bayesian agents do not face the exploration/exploitation dilemma. However, the computational complexity of...
Learning Sparse Graphs from Spatiotemporal Time Series Data
Sparse Graph Learning from Spatiotemporal Time Series Authors: Andrea Cini, Daniele Zambon, Cesare Alippi; Journal: 24(242):1−36, 2023. Abstract Graph neural networks have shown remarkable success in analyzing spatiotemporal time series. These networks leverage...
Federated Learning for Estimating Causal Effects with Incomplete Observational Data
The content has been rewritten as follows: arXivLabs is a platform where collaborators can develop and share innovative features for arXiv directly on our website. We welcome both individuals and organizations who align with our core values of openness, community,...
Using Properties of Additive Noise Channels to Derive Generalization Bounds for Noisy Iterative Algorithms
Generalization Bounds for Noisy Iterative Algorithms Using Properties of Additive Noise Channels Hao Wang, Rui Gao, Flavio P. Calmon; 24(26):1−43, 2023. Abstract This paper examines the generalization of models trained by noisy iterative algorithms and analyzes their...
Addressing Unconventional Hurdles with Machine Learning
[Submitted on 24 Aug 2023] Authors:Shan Guleria, Benjamin Schwartz, Yash Sharma, Philip Fernandes, James Jablonski, Sodiq Adewole, Sanjana Srivastava, Fisher Rhoads, Michael Porter, Michelle Yeghyayan, Dylan Hyatt, Andrew Copland, Lubaina Ehsan, Donald Brown, Sana...
Methodology and Asymptotics of the Convergence between Alpha-divergence Variational Inference and Importance Weighted Auto-Encoders
Alpha-divergence Variational Inference Meets Importance Weighted Auto-Encoders: Methodology and Asymptotics Authors: Kamélia Daudel, Joe Benton, Yuyang Shi, Arnaud Doucet; 24(243):1−83, 2023. Abstract Many algorithms have been proposed that utilize the Variational...
Leveraging Fine-Tuned Llama 2 GPT Model for Analyzing Financial News (arXiv:2308.13032v1 [cs.CL])
The paper explores the potential of using the Llama 2 Large Language Model (LLM) for multitask analysis of financial news. The authors employed a fine-tuning approach based on PEFT/LoRA. During the study, the model was fine-tuned for several tasks, including analyzing...
Enhancing Single-Model Deep Uncertainty with Distance-Awareness: A Simplified Approach
A Simple Approach to Enhance Single-Model Deep Uncertainty via Distance-Awareness Authors: Jeremiah Zhe Liu, Shreyas Padhy, Jie Ren, Zi Lin, Yeming Wen, Ghassen Jerfel, Zachary Nado, Jasper Snoek, Dustin Tran, Balaji Lakshminarayanan; Published in 2023; Volume 24,...
Training Neural Networks using Universal Adiabatic Quantum Computing
arXivLabs is a platform where collaborators can create and share innovative features for the arXiv website. Both individuals and organizations that collaborate with arXivLabs are aligned with our core principles of openness, community, excellence, and user data...
Conformal p-values: A Predictive Approach to Selection
Selection by Prediction with Conformal p-values Authors: Ying Jin, Emmanuel J. Candes; Published in volume 24(244) on pages 1-41 in 2023. Abstract Decision making and scientific discovery pipelines often involve multiple stages, where initial screening is used to...
Extreme Value Theory for Mitigating Extreme Risks in Reinforcement Learning
The content can be rewritten as: arXivLabs is a platform that enables collaborators to create and share innovative features directly on our website. Both individuals and organizations that collaborate with arXivLabs have embraced and embraced our core principles of...
Solving Non-smooth, Non-convex Phase Retrieval with Arbitrary Initialization using Online Stochastic Gradient Descent
Online Stochastic Gradient Descent with Arbitrary Initialization Solves Non-smooth, Non-convex Phase Retrieval Authors: Yan Shuo Tan, Roman Vershynin; Published in 24(58):1−47, 2023. Abstract The problem of phase retrieval can be solved using a two-step procedure....
Comparing Performance of Design Optimization and Deep Learning-based Inverse Design: A Study (arXiv:2308.13000v1 [math.OC])
The use of surrogate model-based optimization in engineering design has been on the rise. This method involves creating a surrogate model using data from simulations or real-world experiments, and then using numerical optimization techniques to find the optimal...
Convolution Smoothing and Debiasing Techniques for Confidence Intervals and Hypothesis Testing in High-dimensional Quantile Regression
Confidence Intervals and Hypothesis Testing for High-dimensional Quantile Regression: Convolution Smoothing and Debiasing Yibo Yan, Xiaozhou Wang, Riquan Zhang; 24(245):1−49, 2023. Abstract Quantile regression with an $\ell_1$ penalty ($\ell_1$-QR) is a valuable...
Rejection Sampling with Privacy Considerations
Privacy-Aware Rejection Sampling Jordan Awan, Vinayak Rao; 24(74):1−32, 2023. Abstract In this study, we examine the potential vulnerabilities of differential privacy (DP) mechanisms to side-channel attacks, specifically timing attacks, and propose a privacy-aware...
FedSoL: Unifying Global Alignment and Local Generality in Federated Learning. (arXiv:2308.12532v1 [cs.LG])
Federated Learning (FL) is a method that uses locally trained models from individual clients to create a global model. FL allows for model training while preserving data privacy. However, it can suffer from performance degradation when the data distributions among...
Reflecting on the Graph Attention Mechanism
Graph Attention Retrospective Authors: Kimon Fountoulakis, Amit Levi, Shenghao Yang, Aseem Baranwal, Aukosh Jagannath; Volume 24, Issue 246, Pages 1-52, 2023. Abstract Graph-based learning is a rapidly growing sub-field of machine learning that finds applications in...
Choosing Point-Based Characteristics for Mesh Networks
arXivLabs is a platform where collaborators can create and share new features for the arXiv website. Both individuals and organizations that collaborate with arXivLabs align with our principles of openness, community, excellence, and user data privacy. We are...
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