AI Blogs
Preserving Privacy in Time Series Data with a Utility-Preserving Mechanism
FLIP: A Privacy-Preserving Mechanism for Time Series Data Authors: Tucker McElroy, Anindya Roy, Gaurab Hore; Published in Journal of Machine Learning Research, Volume 24, Issue 111, Pages 1-29, 2023. Abstract Ensuring privacy in released data is a crucial objective...
Mitigating Accuracy-Robustness Tradeoff through Adversarial Finetuning and Latent Representation Constraint
[Submitted on 31 Aug 2023] Click here to download a PDF of the research paper titled "Adversarial Finetuning with Latent Representation Constraint to Mitigate Accuracy-Robustness Tradeoff" by Satoshi Suzuki and 6 other authors. Download PDF Abstract: This paper...
Using Maximum Mean Discrepancies to Metrize Weak Convergence
Metrizing Weak Convergence with Maximum Mean Discrepancies Authors: Carl-Johann Simon-Gabriel, Alessandro Barp, Bernhard Schölkopf, Lester Mackey; Volume 24, Issue 184, Pages 1-20, 2023. Abstract This paper investigates the maximum mean discrepancies (MMD) that can be...
Contrastive Pre-Training for Addressing Class Imbalance in Encrypted Traffic Classification
arXivLabs is a platform where collaborators can create and share new features directly on the arXiv website. Both individuals and organizations that collaborate with arXivLabs share our values of openness, community, excellence, and user data privacy. We only work...
Uncovering the Unconscious Bias Behind Benign Overfitting
The Implicit Bias of Benign Overfitting By Ohad Shamir; Published in 2023; Volume 24, Issue 113: Pages 1-40 Abstract Benign overfitting, a phenomenon where a predictor perfectly fits noisy training data while achieving near-optimal expected loss, has gained...
AntM$^{2}$C: A Comprehensive Dataset for Predicting Click-Through Rate in Diverse Scenarios using Multiple Modalities
Click-through rate (CTR) prediction is a crucial challenge in recommendation systems. Several public CTR datasets have emerged, but they have certain limitations. Firstly, existing datasets only include data from a single scenario and same type of items, while users...
The Theoretical Equivalence of Multiple Trade-Off Curves in Evaluating Statistical Proximity
Theoretical Equivalence of Trade-Off Curves for Statistical Proximity Assessment Rodrigue Siry, Ryan Webster, Loic Simon, Julien Rabin; 24(185):1−34, 2023. Abstract The development of quantitative measures to assess the proximity of two probability distributions has...
A High-dimensional Perspective on the Equivalence of Implicit and Explicit Neural Networks (arXiv:2308.16425v1 [cs.LG])
The effectiveness of implicit neural networks in different tasks has been proven. However, there is a need for theoretical analysis to understand the connections and distinctions between implicit and explicit networks. This study focuses on high-dimensional implicit...
Tensor Decomposition for Learning State and Action Representations in Markov Decision Processes
Learning Good State and Action Representations for Markov Decision Process via Tensor Decomposition Chengzhuo Ni, Yaqi Duan, Munther Dahleh, Mengdi Wang, Anru R. Zhang; 24(115):1−53, 2023. Abstract This paper presents a novel unsupervised learning approach that...
Decoding Extreme-Mass-Ratio Inspirals with Dilated Convolutional Neural Networks
The detection of Extreme Mass Ratio Inspirals (EMRIs) is challenging due to their complex waveforms, long duration, and low signal-to-noise ratio (SNR). This makes them harder to identify compared to compact binary coalescences. While matched filtering techniques are...
Conditioned Task Learning: Predicting Explicit Hyper-parameters
Learning a Predictive Function for Hyper-parameters Conditioned on Tasks Authors: Jun Shu, Deyu Meng, Zongben Xu; Published in 2023, Volume 24, Issue 186, Pages 1-74. Abstract Recently, meta learning has gained significant attention in the machine learning community....
CktGNN: Utilizing Circuit Graph Neural Network for Electronic Design Automation (arXiv:2308.16406v1 [cs.LG])
The field of integrated circuits has long struggled with automating the design of analog circuits. This is due to the complexity of circuit specifications and the vast design space. Previous research has mainly focused on automating transistor sizing within a given...
Deep linear networks outperform shallow networks by benignly overfitting
Deep linear networks can overfit benignly when shallow ones do Authors: Niladri S. Chatterji, Philip M. Long; Published in 2023, Vol. 24(117), Pages 1-39. Abstract This study focuses on bounding the excess risk of interpolating deep linear networks trained using...
Finding the Right Balance: Local and Global Structures in Graph Embedding
We propose a method to achieve a balance between the Local and Global Structures (LGS) in graph embedding. This is achieved through the use of a tunable parameter. While some embedding techniques focus on capturing global structures, and others prioritize preserving...
Measuring Network Similarity with Graph Cumulants
Quantifying Network Similarity using Graph Cumulants Gecia Bravo-Hermsdorff, Lee M. Gunderson, Pierre-André Maugis, Carey E. Priebe; 24(187):1−27, 2023. Abstract This study compares two statistical tests that assess the hypothesis of networks being sampled from the...
Enhancing Robustness and Accuracy of Ponzi Scheme Detection on Ethereum with Time-Dependent Features
[Submitted on 31 Aug 2023] Download a PDF of the paper titled "Improving Robustness and Accuracy of Ponzi Scheme Detection on Ethereum Using Time-Dependent Features" by Phuong Duy Huynh and 4 other authors. Download PDF Abstract: The rise of blockchain technology has...
A Graph Model with Annotated Nodes Addressing Differential Degree Heterogeneity in Directed Networks
An Annotated Graph Model with Differential Degree Heterogeneity for Directed Networks Authors: Stefan Stein, Chenlei Leng; Journal of Machine Learning Research, 24(119):1−69, 2023. Abstract Graphs are commonly used to represent directed networks, where the ordered...
BenchTemp: An All-Purpose Benchmark for Assessing Temporal Graph Neural Networks (arXiv:2308.16385v1 [cs.LG])
A proposal has been made to address the challenges of handling graphs with evolving features or connectivities over time. This proposal introduces a series of temporal graph neural networks (TGNNs). However, previous evaluations of these TGNNs have identified several...
The Proximity Identification Algorithm
The Proximal ID Algorithm Ilya Shpitser, Zach Wood-Doughty, Eric J. Tchetgen Tchetgen; 24(188):1−46, 2023. Abstract Unobserved confounding poses a significant challenge in establishing valid causal conclusions from observational data. To address this challenge, two...
Offline Reinforcement Learning with Multi-Objective Decision Transformers (arXiv:2308.16379v1 [cs.LG])
The aim of Offline Reinforcement Learning (RL) is to derive policies from static trajectory data without real-time environment interactions. Recent studies have explored using the transformer architecture to predict actions based on prior context, treating offline RL...
Minimum Width Requirement for Universal Property of Deep RNN
Minimal Width for Universality of Deep RNNs Chang hoon Song, Geonho Hwang, Jun ho Lee, Myungjoo Kang; 24(121):1−41, 2023. Abstract Recurrent neural networks (RNNs) are commonly used deep learning networks for handling sequential data. An infinite-width RNN can...
Privacy in Graph Neural Networks: Examining Attacks, Preservation, and Applications – A Comprehensive Survey
arXivLabs is a platform that enables collaborators to create and share new features on the arXiv website. Both individuals and organizations that collaborate with arXivLabs embrace our core principles of openness, community, excellence, and user data privacy. We are...
Random Feature Neural Networks Overcome Curse of Dimensionality to Learn Black-Scholes Type PDEs
Random Feature Neural Networks: Learning Black-Scholes Type PDEs Without the Curse of Dimensionality By Lukas Gonon; 24(189):1−51, 2023. Abstract This study explores the application of random feature neural networks in learning Kolmogorov partial...
Improving LLM Inference Efficiency through Chunked Prefills and Piggybacked Decodes
arXivLabs is a platform where collaborators can create and share new features for arXiv directly on our website. Both individuals and organizations that participate in arXivLabs are aligned with our values of openness, community, excellence, and user data privacy. We...
The Phenomenon of Benign Overfitting in Ridge Regression
Benign overfitting in ridge regression Alexander Tsigler, Peter L. Bartlett; 24(123):1−76, 2023. Abstract Many modern applications of deep learning involve neural networks with a large number of parameters compared to the amount of training data. This has led to a...
An Integrated Examination of Subgradient Methods in the Optimization of Composite Nonconvex, Nonsmooth, and Non-Lipschitz Functions.
This paper presents a new method called Prox-SubGrad for solving nonconvex and nonsmooth optimization problems without the need for Lipschitz continuity conditions. The authors introduce several subgradient upper bounds and discuss their relationships. These upper...
An Algorithmic Framework with Theoretical Guarantees
Clustering with Tangles: Algorithmic Framework and Theoretical Guarantees Solveig Klepper, Christian Elbracht, Diego Fioravanti, Jakob Kneip, Luca Rendsburg, Maximilian Teegen, Ulrike von Luxburg; Volume 24, Issue 190, Pages 1-56, 2023. Abstract Tangles were...
The Impact of Emoji on GitHub: Encouraging Developer Engagement and Resolving Issues (arXiv:2308.16360v1 [cs.CY])
Despite the growing adoption of remote working during the pandemic, there is a concern about the decreased efficiency in this type of work. One of the reasons for this is the lack of non-verbal cues, such as facial expressions and body language, in text-based...
Introducing Streaming Support in Amazon SageMaker Hosting: Enhancing the Generative AI Experience
We are thrilled to announce that response streaming is now available through Amazon SageMaker real-time inference. This new feature allows you to continuously stream inference responses back to the client when using SageMaker real-time inference, enabling you to build...
The Statistical Robustness of Empirical Risks in Machine Learning: An Analysis
Statistical Robustness of Empirical Risks in Machine Learning Shaoyan Guo, Huifu Xu, Liwei Zhang; 24(125):1−38, 2023. Abstract This paper investigates the convergence of empirical risks in reproducing kernel Hilbert spaces (RKHS). Previous research has assumed that...
Using BabyBERTa for Grammar Learning and Language Understanding in Toddlers (arXiv:2308.16336v1 [cs.CL])
Introducing ToddlerBERTa, a language model similar to BabyBERTa, that we have developed to explore its capabilities. We have experimented with five different models, each having different hyperparameters. To evaluate the performance of ToddlerBERTa, we have tested it...
Operationalize Generative AI and Distinguish it from MLOps: FMOps/LLMOps
In today's business landscape, many customers are enthusiastic about large language models (LLMs) and how generative AI can revolutionize their operations. However, integrating such solutions and models into regular business operations is not a simple task. In this...
A Comprehensive Evaluation of Ordinal Embedding Algorithms: Gaining Deeper Insights
A Systematic Evaluation of Ordinal Embedding Algorithms Leena Chennuru Vankadara, Michael Lohaus, Siavash Haghiri, Faiz Ul Wahab, Ulrike von Luxburg; 24(191):1−83, 2023. Abstract Ordinal embedding aims to find a Euclidean representation of abstract items using triplet...
Preservation of Symmetry in Hamiltonian Systems: A Study on Simulation and Learning
[Submitted on 30 Aug 2023] Download a PDF of the paper titled "Symmetry Preservation in Hamiltonian Systems: Simulation and Learning" by Miguel Vaquero and 1 other author. Download PDF Abstract: This work introduces a comprehensive geometric framework for simulating...
Using Graph Neural Networks for Graph Clustering
Graph Clustering with Graph Neural Networks Anton Tsitsulin, John Palowitch, Bryan Perozzi, Emmanuel Müller; 24(127):1−21, 2023. Abstract Graph Neural Networks (GNNs) have achieved state-of-the-art results in various graph analysis tasks, such as node classification...
A Comprehensive Review of the State-of-the-Art in Generative Adversarial Nets (GANs) Over the Past Decade (arXiv:2308.16316v1 [cs.LG])
Generative Adversarial Networks (GANs) have rapidly gained popularity since their inception in 2014. They are powerful tools for generating realistic and diverse data in various domains, including computer vision. GANs consist of a discriminative network and a...
Strategic Classification: A PAC-learning Approach
PAC-learning for Strategic Classification Ravi Sundaram, Anil Vullikanti, Haifeng Xu, Fan Yao; 24(192):1−38, 2023. Abstract The recent attention in the study of strategic or adversarial manipulation of testing data to deceive a classifier has led to various research...
Anomaly Classification in Telecommunication Network KPI Time Series
The complexity and scale of telecommunication networks have led to a growing interest in automated systems for detecting anomalies. However, there has been less focus on classifying anomalies detected on network Key Performance Indicators (KPI), resulting in a lack of...
Columnar-Constructive Networks: Enabling Scalable Real-Time Recurrent Learning
Scalable Real-Time Recurrent Learning Using Columnar-Constructive Networks Authors: Khurram Javed, Haseeb Shah, Richard S. Sutton, Martha White; 24(256):1−34, 2023. Abstract Constructing states from sequences of observations is a crucial aspect of reinforcement...
Enhancing Generalization by Incorporating Diverse Features in Vision Transformers
arXivLabs is a platform where collaborators can create and share new features for our website. We welcome individuals and organizations who share our values of openness, community, excellence, and user data privacy. We only collaborate with partners who adhere to...
The Fusion Approach: Divide and Conquer
Divide-and-Conquer Fusion Ryan S.Y. Chan, Murray Pollock, Adam M. Johansen, Gareth O. Roberts; 24(193):1−82, 2023. Abstract Combining multiple distributions, referred to as sub-posteriors, into a single distribution proportional to their product is a common challenge....
A deep neural network-based numerical method for approximating the fractional Laplacian
[Submitted on 30 Aug 2023] Download a PDF of the paper titled "A numerical approach for the fractional Laplacian via deep neural networks" by Nicolás Valenzuela Download PDF Abstract: We investigate the solution of the fractional elliptic problem with Dirichlet...
Efficient Support Tensor Train Machine with Preserved Structure
Efficient Structure-preserving Support Tensor Train Machine Kirandeep Kour, Sergey Dolgov, Martin Stoll, Peter Benner; 24(4):1−22, 2023. Abstract With the increasing amount of collected data being high-dimensional multi-way arrays (tensors), it is crucial for...
The Emergence of Segmentation through Minimalistic White-Box Transformers
The content below has been rewritten: arXivLabs is a platform where collaborators can create and exchange new features for arXiv directly on our website. Both individuals and organizations that collaborate with arXivLabs have embraced and accepted our core principles...
Aggregated Two-Sample Test for MMD
MMD Aggregated Two-Sample Test Authors: Antonin Schrab, Ilmun Kim, Mélisande Albert, Béatrice Laurent, Benjamin Guedj, Arthur Gretton; 24(194):1−81, 2023. Abstract The paper introduces two new nonparametric two-sample kernel tests that are based on the Maximum Mean...
A Language Model for Predicting Interpretable Materials Properties: Introducing the Materials Informatics Transformer (arXiv:2308.16259v1 [cs.LG])
In recent times, large language models (LLMs) have demonstrated their remarkable abilities in various research fields such as natural language processing, computer vision, and molecular modeling. To expand on this, we present our model called Materials Informatics...
A Calm Inertial Forward-Backward-Forward Approach for Resolving Monotone Inclusions with Utilization in GANs
A Relaxed Inertial Forward-Backward-Forward Algorithm for Solving Monotone Inclusions with Application to GANs Authors: Radu I. Bot, Michael Sedlmayer, Phan Tu Vuong; Published: 24(8):1−37, 2023. Abstract This paper presents the relaxed inertial...
Regression: Enhanced Explanations with Calibration. (arXiv:2308.16245v1 [cs.LG])
Artificial Intelligence (AI) plays a crucial role in modern decision support systems (DSSs). However, the lack of transparency in the best-performing AI models used in DSSs is a significant challenge. Explainable Artificial Intelligence (XAI) addresses this challenge...
Causal Diagrams: Exploring Clustering and Ensuring Structural Robustness
Clustering and Structural Robustness in Causal Diagrams Authors: Santtu Tikka, Jouni Helske, Juha Karvanen; 24(195):1−32, 2023. Abstract Causal relations are commonly represented and visualized using graphs. While this approach is concise and clear for a small number...
Controlling the Deep Video Codec (arXiv:2308.16215v1 [eess.IV])
Lossy video compression is widely used for transmitting and storing video data. Despite the availability of advanced compression approaches, the current standard remains unified video codecs like H.264 or H.265. These codecs need to adapt to varying compression...
Enhancing Count-Min Sketches with Bayesian Nonparametrics for Improved Learning
Learning-augmented count-min sketches via Bayesian nonparametrics Emanuele Dolera, Stefano Favaro, Stefano Peluchetti; 24(12):1−60, 2023. Abstract The count-min sketch (CMS) is an efficient randomized data structure that estimates the frequencies of tokens in a data...
Using Markov Bridges for Modeling Retrosynthesis
arXivLabs is a platform that enables collaboration and sharing of new features on our website. Both individuals and organizations working with arXivLabs share our values of openness, community, excellence, and user data privacy. We only partner with those who uphold...
Estimating Statistical Models from Incomplete Data Using Variational Gibbs Inference
Variational Gibbs Inference for Statistical Model Estimation from Incomplete Data Authors: Vaidotas Simkus, Benjamin Rhodes, Michael U. Gutmann; Journal of Machine Learning Research, 24(196):1−72, 2023. Abstract Statistical models play a crucial role in machine...
Application of Globally-Consistent Rule-Based Summary-Explanations for Machine Learning Models in Credit-Risk Evaluation
Globally-Consistent Rule-Based Summary-Explanations for Machine Learning Models: Application to Credit-Risk Evaluation Cynthia Rudin, Yaron Shaposhnik; 24(16):1−44, 2023. Abstract This study presents a novel method for comprehending specific predictions made by global...
Combining Deep Inductive Logic Programming with Reinforcement Learning (arXiv:2308.16210v1 [cs.LG])
One way to explain the hierarchical levels of understanding in a machine learning model is through the use of inductive logic programming (ILP), which is a data efficient approach capable of learning logical rules that can capture data behavior. A variation of ILP,...
Comparing Assumptions for Average Causal Effects: Evaluating Robustness and Semiparametric Efficiency
Contrasting Identifying Assumptions of Average Causal Effects: Robustness and Semiparametric Efficiency Tetiana Gorbach, Xavier de Luna, Juha Karvanen, Ingeborg Waernbaum; 24(197):1−65, 2023. Abstract This paper examines different identifying assumptions for...
Multi-anchor Space-aware Temporal Convolutional Neural Networks for EEG Emotion Recognition: MASA-TCN Approach (arXiv:2308.16207v1 [cs.LG])
The content can be rewritten as: Emotion recognition using electroencephalogram (EEG) encompasses two main scenarios: classifying discrete labels and regressing continuously tagged labels. While numerous algorithms have been proposed for classification tasks, there...
Few Mistakes Made by Interpolating Classifiers
Interpolating Classifiers with Few Mistakes Tengyuan Liang and Benjamin Recht; 24(20):1−27, 2023. Abstract This paper presents a basic analysis of the regret and generalization capabilities of minimum-norm interpolating classifiers (MNIC). MNIC is a function that...
Graph-Based Multi-Agent Reinforcement Learning for Collaborative Information Dissemination
The following content is about a paper titled "Learning Collaborative Information Dissemination with Graph-based Multi-Agent Reinforcement Learning" written by Raffaele Galliera and three other authors. The paper discusses the importance of efficient and reliable...
A Platform for Scientific Challenges: Open Source and Collaborative
CodaLab Competitions: An Open Source Platform for Organizing Scientific Challenges Authors: Adrien Pavao, Isabelle Guyon, Anne-Catherine Letournel, Dinh-Tuan Tran, Xavier Baro, Hugo Jair Escalante, Sergio Escalera, Tyler Thomas, Zhen Xu; Published in 24(198):1−6,...
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