AI Blogs
Joint Optimization of Multiple Rewards using Reinforcement Learning
Reinforcement Learning for Joint Optimization of Multiple Rewards Mridul Agarwal, Vaneet Aggarwal; 24(49):1−41, 2023. Abstract To find optimal policies that maximize the long-term rewards of Markov Decision Processes, dynamic programming and backward induction are...
Quasi-Bernoulli Stick-breaking Process for Achieving Consistent Model-based Clustering
Consistent Model-based Clustering using the Quasi-Bernoulli Stick-breaking Process Cheng Zeng, Jeffrey W Miller, Leo L Duan; 24(153):1−32, 2023. Abstract In applications of mixture modeling and clustering, it is often unknown how many components and clusters exist....
Detecting Change-Points in High-Dimensional Covariance Structure of Dynamic Networks using Online Methods
Online Change-Point Detection in High-Dimensional Covariance Structure with Application to Dynamic Networks Lingjun Li, Jun Li; 24(51):1−44, 2023. Abstract This paper presents a novel approach for online change-point detection in high-dimensional data, specifically...
Adaptation and Evaluation of Influence-Estimation Techniques for Gradient-Boosted Decision Trees
Adapting and Evaluating Influence-Estimation Methods for Gradient-Boosted Decision Trees Jonathan Brophy, Zayd Hammoudeh, Daniel Lowd; 24(154):1−48, 2023. Abstract Analyzing the influence of changes to the training data on model predictions can provide valuable...
Designing the VCG Mechanism with Agents’ Unknown Values in the Presence of Stochastic Bandit Feedback
VCG Mechanism Design with Unknown Agent Values under Stochastic Bandit Feedback Kirthevasan Kandasamy, Joseph E Gonzalez, Michael I Jordan, Ion Stoica; 24(53):1−45, 2023. Abstract This study focuses on a multi-round mechanism design problem that aims to maximize...
![Early Fixing for Optimization of Gas-lifted Oil Production: A Comparison of Supervised and Weakly-supervised Approaches Using Deep Learning (arXiv:2309.00197v1 [cs.LG])](https://instadatanews.com/wp-content/uploads/2023/08/arxiv-logo-fb-400x250.png){kind=logo}
Early Fixing for Optimization of Gas-lifted Oil Production: A Comparison of Supervised and Weakly-supervised Approaches Using Deep Learning (arXiv:2309.00197v1 [cs.LG])
The aim of this paper is to enhance oil production from gas-lifted oil wells by solving Mixed-Integer Linear Programs (MILPs). These programs need to be repeatedly solved as the parameters of the wells change. Instead of using expensive exact methods or approximate...
Multi-Armed Bandits for Achieving Adaptive Data Depth
Adaptive Data Depth via Multi-Armed Bandits Tavor Baharav, Tze Leung Lai; 24(155):1−29, 2023. Abstract Data depth is an important tool in data science, robust statistics, and computational geometry. However, many common measures of depth are computationally intensive,...
RepCodec: A Codec for Speech Tokenization using Speech Representation (arXiv:2309.00169v1 [eess.AS])
The rapid growth of large language models (LLMs) has highlighted the importance of discrete speech tokenization in injecting speech into these models. However, this process of discretization results in a loss of information, leading to a decrease in overall...
The Rates of Minimax and Randomized Sketches
Minimax Rates and Randomized Sketches for Kernel-based Estimation in Partially Functional Linear Models Authors: Shaogao Lv, Xin He, Junhui Wang; Journal of Machine Learning Research, 24(55):1−38, 2023. Abstract This study focuses on the partially functional linear...
A Study on Information Fusion for Production Assessment in Assistance Systems (arXiv:2309.00157v1 [cs.LG])
We present a unique approach to defining assistance systems that utilize information fusion to combine various sources of information and provide an assessment. The main contribution of this study is the development of a comprehensive framework for fusing multiple...
Incorporating Random Effects into Deep Neural Networks
Integrating Random Effects in Deep Neural Networks The paper "Integrating Random Effects in Deep Neural Networks" by Giora Simchoni and Saharon Rosset (2023) explores the use of mixed models to handle correlated data in deep neural networks (DNNs). While DNNs...
TurboGP: An Advanced and Versatile Python-based Genetic Programming Library (arXiv:2309.00149v1 [cs.NE])
Introducing TurboGP, a Python-based Genetic Programming (GP) library that is exclusively developed for machine learning purposes. TurboGP stands out from other GP implementations by incorporating advanced features like island and cellular population schemes, along...
Tree Approximate Message Passing for Compositional Inference
Tree-AMP: Compositional Inference with Tree Approximate Message Passing Antoine Baker, Florent Krzakala, Benjamin Aubin, Lenka Zdeborová; 24(57):1−89, 2023. Abstract The python package Tree-AMP is introduced as a tool for compositional inference in high-dimensional...
Joint Power and Subchannel Allocation in IAB Networks using Multi-Agent Deep Reinforcement Learning
The content discusses the utilization of Integrated Access and Backhauling (IAB) as a cost-effective alternative to fiber-wired links for achieving higher data rates in future networks. The design of such networks presents optimization challenges due to non-convex and...
Eliminating Polylogarithmic Factor in O(epsilon^(-7/4)) Complexity
Improved Complexity for Restarted Nonconvex Accelerated Gradient Descent By Huan Li and Zhouchen Lin; 24(157):1−37, 2023. Abstract This paper focuses on accelerated gradient methods for nonconvex optimization problems with Lipschitz continuous gradient and Hessian. We...
Enhancing Keyword Spotting by Incorporating Dynamic Module Skipping in Streaming Conformer Encoder
We propose an architecture with input-dependent dynamic depth for processing streaming audio, using a vision-inspired keyword spotting framework. This architecture extends a conformer encoder by adding trainable binary gates, which allow the network to dynamically...
Deep Learning Enhanced with Topological Convolutional Layers
Topological Convolutional Layers for Deep Learning Ephy R. Love, Benjamin Filippenko, Vasileios Maroulas, Gunnar Carlsson; 24(59):1−35, 2023. Abstract This article presents the Topological CNN (TCNN), a collection of convolutional methods that are defined...
Using Time Series Analysis and Natural Language Processing to Forecast Financial Market Trends. (arXiv:2309.00136v1 [q-fin.ST])
Analyzing financial market trends using time series analysis and natural language processing is a complex task due to the multitude of variables that can influence stock prices. These variables include economic and political events, as well as public attitudes. Recent...
Improved Sequence Results with Enhanced Algorithmic Guarantees
New Sequence Results and Improved Algorithmic Guarantees for Asynchronous Iterations in Optimization Authors: Hamid Reza Feyzmahdavian, Mikael Johansson; Published in Journal of Machine Learning Research, 24(158):1−75, 2023. Abstract This paper presents novel...
A Flexible Trigger-Based Backdoor Attack: Enhancing Stealthiness and Robustness in Federated Learning
arXivLabs is a platform where collaborators can develop and share new features for arXiv directly on our website. Both individuals and organizations that are involved with arXivLabs have embraced and accepted our core values of openness, community, excellence, and...
An Approach to Density Estimation on Low-Dimensional Manifolds using Inflation-Deflation
Density Estimation on Low-Dimensional Manifolds: An Inflation-Deflation Approach Authors: Christian Horvat, Jean-Pascal Pfister; Volume 24, Issue 61, Pages 1-37, 2023. Abstract Normalizing flows (NFs) are density estimators that use neural networks. However, NFs have...
Differentially Private Functional Summaries using the Independent Component Laplace Process
We present a novel approach called the Independent Component Laplace Process (ICLP) mechanism for releasing differentially private functional summaries. Unlike previous methods that assume finite-dimensional data trajectories, our approach treats the functional...
Bayesian Nonparametric Learning and Optimization of Stochastic Differential Equations in Infinite Dimensions
Infinite-dimensional optimization and Bayesian nonparametric learning of stochastic differential equations Authors: Arnab Ganguly, Riten Mitra, Jinpu Zhou; 24(159):1−39, 2023. Abstract This paper focuses on two main topics. The first part of the paper presents general...
Anomaly Detection for Uncovering Fraud in the Futures Market using Deep Semi-Supervised Learning.
The modern financial electronic exchanges are dynamic and fast-moving marketplaces where billions of dollars are exchanged daily. However, these exchanges are also susceptible to manipulation and fraudulent activities. Traditionally, identifying such activities has...
Tractability Achieved by Knowledge Compilation and Non-Approximability Findings
Tractability and Non-Approximability of SHAP-Score-Based Explanations Marcelo Arenas, Pablo Barcelo, Leopoldo Bertossi, Mikael Monet; 24(63):1−58, 2023. Abstract Shapley values-based scores are commonly used to provide explanations for classification results in...
RePo: Enhancing Resilient Model-Based Reinforcement Learning through Posterior Predictability Regularization. (arXiv:2309.00082v1 [cs.LG])
In this paper, we present a novel approach to visual model-based RL methods. These methods often encode image observations into low-dimensional representations, but they do not effectively eliminate redundant information. As a result, they are vulnerable to spurious...
Efficiency of Sampling and Generative Modeling
Multivariate Soft Rank via Entropy-Regularized Optimal Transport: Sample Efficiency and Generative Modeling Shoaib Bin Masud, Matthew Werenski, James M. Murphy, Shuchin Aeron; 24(160):1−65, 2023. Abstract This paper introduces the concept of multivariate soft rank,...
Adam’s Implicit Bias: Unveiling the Truth (arXiv:2309.00079v1 [cs.LG])
Previous research utilized backward error analysis to identify ordinary differential equations (ODEs) that approximate the gradient descent trajectory. These studies revealed that finite step sizes implicitly regulate solutions by penalizing the two-norm of the loss...
The Hypothesis of Wide-minima Density and the Learning Rate Schedule for Explore-Exploit
Wide-minima Density Hypothesis and the Explore-Exploit Learning Rate Schedule Nikhil Iyer, V. Thejas, Nipun Kwatra, Ramachandran Ramjee, Muthian Sivathanu; 24(65):1−37, 2023. Abstract This paper presents detailed experiments that support the argument that wide minima...
Tackling Stochasticity in Multi-Step Regression Stock Price Prediction through Diffusion Variational Autoencoder
Predicting stock prices over a long-term period is crucial for various financial purposes such as forecasting volatility, pricing derivatives, hedging, and risk quantification. It is also important for institutional investors to have a liquidity horizon of several...
Continuous Time q-Learning
Continuous-Time q-Learning: A Study By Yanwei Jia and Xun Yu Zhou; 24(161):1−61, 2023. Abstract This study focuses on the continuous-time counterpart of Q-learning for reinforcement learning (RL) using the entropy-regularized, exploratory diffusion process formulation...
YaRN: Enhancing Context Window Extension of Large Language Models for Improved Efficiency (arXiv:2309.00071v1 [cs.CL])
The Rotary Position Embeddings (RoPE) have proven to be successful in encoding positional information in transformer-based language models. However, these models struggle to generalize beyond the maximum sequence length they were trained on. To address this...
Improving Prior Specification for Bayesian Matrix Factorization through Prior Predictive Matching
Prior Specification for Bayesian Matrix Factorization via Prior Predictive Matching Eliezer de Souza da Silva, Tomasz Kuśmierczyk, Marcelo Hartmann, Arto Klami; 24(67):1−51, 2023. Abstract The choice of prior distributions in Bayesian models used in machine learning...
Enhancing Multi-View Graph Clustering by Preserving Local and Global Structure
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 have embraced and accepted our core principles of openness, community, excellence, and user...
Quantile Regression: Enhancing Model Aggregation with Flexibility
Flexible Model Aggregation for Quantile Regression Rasool Fakoor, Taesup Kim, Jonas Mueller, Alexander J. Smola, Ryan J. Tibshirani; 24(162):1−45, 2023. Abstract Quantile regression is a fundamental problem in statistical learning that aims to quantify uncertainty in...
Continual Learning Using an API Stream (arXiv:2309.00023v1 [cs.LG])
The focus of this paper is on continual learning (CL), which involves learning new tasks without forgetting previous tasks. However, existing CL methods require a large amount of raw data, which is often unavailable due to copyright and privacy concerns. Instead,...
Designing Self-Adaptive AI-based Applications on the Edge with Energy Efficiency in Mind
The emergence of specialized edge devices for machine learning tasks has enabled the efficient processing and classification of data collected by resource-constrained devices in the Internet of Things. However, with the increasing demand for applications like critical...
Boundary encounters of Locally Linear Embedding
Locally Linear Embedding on Boundary of Riemannian Manifolds By Hau-Tieng Wu and Nan Wu; Published in 2023, Volume 24, Issue 69, Pages 1-80. Abstract This study investigates the behavior of the locally linear embedding (LLE) algorithm, a commonly used unsupervised...
Discovering Interpretable Visual Concepts through Unsupervised Learning
The content of the given text is as follows: Title: Unsupervised discovery of Interpretable Visual Concepts Author: Caroline Mazini Rodrigues Abstract: This paper proposes two methods, Maximum Activation Groups Extraction (MAGE) and Multiscale Interpretable...
Global Optimality Certification for Overparameterized Nonconvex Burer–Monteiro Factorization using Preconditioned Gradient Descent
Preconditioned Gradient Descent for Overparameterized Nonconvex Burer--Monteiro Factorization with Global Optimality Certification Gavin Zhang, Salar Fattahi, Richard Y. Zhang; 24(163):1−55, 2023. Abstract The objective of this research is to minimize the nonconvex...
Deep Reinforcement Learning for Cellular-Connected UAV Trajectory Design in Rainy Environments: A Physics-Based Approach (arXiv:2309.00017v1 [eess.SY])
The focus on cellular-connected unmanned aerial vehicles (UAVs) has been growing due to their ability to enhance conventional UAV capabilities by utilizing existing cellular infrastructure for reliable communication with base stations. These UAVs have been utilized in...
Estimating Determinants of Kernel Matrices using Stopped Cholesky Decomposition
Estimating Kernel-Matrix Determinants using Stopped Cholesky Decomposition Authors: Simon Bartels, Wouter Boomsma, Jes Frellsen, Damien Garreau; Published in Journal of Machine Learning Research, 24(71):1−57, 2023. Abstract Many algorithms involving Gaussian processes...
Improvement in Differentially Private Image Generation Quality with Large-Scale Public Data
The content below has been rewritten: arXivLabs is a platform where collaborators can collaborate and create new features for arXiv directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of...
Regression: A Comprehensive Framework and Benchmark for Deep Batch Active Learning
A Framework and Benchmark for Deep Batch Active Learning for Regression David Holzmüller, Viktor Zaverkin, Johannes Kästner, Ingo Steinwart; 24(164):1−81, 2023. Abstract This study focuses on active learning methods for improving the sample efficiency of neural...
Unveiling Imperceptible Adversarial Perturbations for Top-$k$ Multi-Label Learning in the Presence of Unreliable Measures. (arXiv:2309.00007v1 [cs.CV])
Adversarial learning has gained significant attention in various studies due to the success of deep neural networks. However, existing adversarial attacks in multi-label learning only focus on visual imperceptibility and overlook the perceptible issue related to...
Inferencing for an Extensive Directed Acyclic Graph with Unspecified Interventions
Inference for a Large Directed Acyclic Graph with Unspecified Interventions Chunlin Li, Xiaotong Shen, Wei Pan; 24(73):1−48, 2023. Abstract The statistical inference of directed relations, given unspecified interventions where the intervention targets are unknown,...
A Synthetic HyperSpectral Dataset with High Spectral Spatial Resolution Achieved through Multi-Source Fusion. (arXiv:2309.00005v1 [cs.CV])
This research paper introduces a novel synthetic hyperspectral dataset that overcomes the limitations of relying on a single camera for high spectral and spatial resolution imaging. The dataset combines three modalities: RGB, push-broom visible hyperspectral camera,...
Effective Approaches for Linear Learning in High-Dimensional Spaces
Robust Methods for High-Dimensional Linear Learning Ibrahim Merad, Stéphane Gaïffas; 24(165):1−44, 2023. Abstract This paper presents statistically robust and computationally efficient linear learning methods for high-dimensional batch settings, where the number of...
Density-based Metric Learning for Intrinsic Persistent Homology
Intrinsic Persistent Homology via Density-based Metric Learning Authors: Ximena Fernández, Eugenio Borghini, Gabriel Mindlin, Pablo Groisman; Published in: Journal of Machine Learning Research, Volume 24, Pages 1-42, 2023. Abstract This study focuses on estimating...
Decentralized Weakly Convex Optimization with Moreau Envelope ADMM
This paper introduces a modified version of the alternating direction method of multipliers (ADMM) for distributed optimization. While the current ADMM algorithms have shown promising results in finding near-optimal solutions for various convex and non-convex...
A Conditional Gradient Method for Composite Minimization without Parameter Dependence under Hölder Condition
A Parameter-Free Conditional Gradient Method for Composite Minimization under Hölder Condition Masaru Ito, Zhaosong Lu, Chuan He; 24(166):1−34, 2023. Abstract This paper addresses a composite optimization problem that involves minimizing the sum of a weakly smooth...
A Multi-Branch Network for Diagnosing Cervical Lymph Node Lesions in Ultrasound Images: US-SFNet in the Spatial-Frequency Domain (arXiv:2308.16738v1 [eess.IV])
Ultrasound imaging is a crucial tool for diagnosing cervical lymph node lesions. However, the accuracy of these diagnoses heavily relies on the expertise of medical professionals, making the process prone to misdiagnoses. While deep learning has significantly improved...
Using Deep Generative Models for Nonparametric Estimation of Singular Distributions: A Likelihood-Based Approach
A Likelihood Approach to Nonparametric Estimation of a Singular Distribution Using Deep Generative Models Minwoo Chae, Dongha Kim, Yongdai Kim, Lizhen Lin; 24(77):1−42, 2023. Abstract This study explores the statistical properties of a likelihood approach to...
Enhancing Localization with Resilient Networked Federated Learning
The focus of this paper is on the challenge of localizing data in a federated setting where the data is spread across multiple devices. This problem is complex due to the decentralized nature of federated environments and the presence of outlier data, which hinders...
Reducing Sample Complexity without Warm-Start for Optimal Performance
Bilevel Optimization with a Lower-level Contraction: Optimal Sample Complexity without Warm-Start Riccardo Grazzi, Massimiliano Pontil, Saverio Salzo; 24(167):1−37, 2023. Abstract This study examines a broad range of bilevel problems, where the upper-level problem...
Enhancing Representation Learning for Unreliable Partial Label Learning: A Robust Approach (arXiv:2308.16718v1 [cs.LG])
Partial Label Learning (PLL) is a form of weakly supervised learning in which each training instance is assigned multiple candidate labels, but only one label is considered the true label. However, this assumption may not always hold true due to potential mistakes in...
Group LASSO for Regression with Approximate Post-Selective Inference
Approximate Post-Selective Inference for Regression with the Group LASSO Snigdha Panigrahi, Peter W MacDonald, Daniel Kessler; 24(79):1−49, 2023. Abstract In the absence of adjustments for selection bias, inference for the selected parameters after using the Group...
Reimagining Lossy Compression as an Inherent Backdoor Attack: Enabling Universal Exploitation (arXiv:2308.16684v1 [cs.CR])
The trustworthiness of machine learning models in practical applications has been recently threatened by vulnerabilities to backdoor attacks. While it is commonly believed that not everyone can be an attacker due to the significant effort and extensive experimentation...
Detecting Change Points in High Dimensional Covariance Shifts: An Inference Approach
Inference on the Change Point in a High Dimensional Covariance Shift Authors: Abhishek Kaul, Hongjin Zhang, Konstantinos Tsampourakis, George Michailidis; Journal of Machine Learning Research, 24(168):1−68, 2023. Abstract This study addresses the problem of...
Evaluating the Impact of Model Design Decisions on Algorithmic Fairness through Multiverse Analysis
[Submitted on 31 Aug 2023] Download a PDF of the paper titled "Everything, Everywhere All in One Evaluation: Using Multiverse Analysis to Evaluate the Influence of Model Design Decisions on Algorithmic Fairness" by Jan Simson, Florian Pfisterer, and Christoph Kern...
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