Open Access. Powered by Scholars. Published by Universities.®

Artificial Intelligence and Robotics Commons™

Open Access. Powered by Scholars. Published by Universities.®

2022

Discipline
Institution
Keyword
Publication
Publication Type

Articles 31 - 60 of 965

Full-Text Articles in Artificial Intelligence and Robotics

Iot-Based Smart Fishing Gear For Sustainability Of The Tanzania Blue Economy, Abdi Abdalla Dec 2022

Iot-Based Smart Fishing Gear For Sustainability Of The Tanzania Blue Economy, Abdi Abdalla

Tanzania Journal of Engineering and Technology (TJET)

The fishing industry engages many Tanzanians and is among the leading sectors of Blue Economy in the country. However, fishing practices are small-scale with poor and insufficient number of fishing facilities, hence limiting productivity and efficacy. Studies argue that the low level of technology currently used in the country could possibly be an impeding factor. Specifically, fishers use non interactive gears that cannot instantaneously update status and alert them whenever the gears are ready for collection. In such scenarios, fishers not only waste their time but also scarce resources such as fuel to facilitate trips to and from the fishing …

Go to article

Polarmix: A General Data Augmentation Technique For Lidar Point Clouds, Aoran Xiao, Jiaxing Huang, Dayan Guan, Kaiwen Cui, Shijian Lu, Ling Shao Dec 2022

Polarmix: A General Data Augmentation Technique For Lidar Point Clouds, Aoran Xiao, Jiaxing Huang, Dayan Guan, Kaiwen Cui, Shijian Lu, Ling Shao

Computer Vision Faculty Publications

LiDAR point clouds, which are usually scanned by rotating LiDAR sensors continuously, capture precise geometry of the surrounding environment and are crucial to many autonomous detection and navigation tasks. Though many 3D deep architectures have been developed, efficient collection and annotation of large amounts of point clouds remain one major challenge in the analytics and understanding of point cloud data. This paper presents PolarMix, a point cloud augmentation technique that is simple and generic but can mitigate the data constraint effectively across different perception tasks and scenarios. PolarMix enriches point cloud distributions and preserves point cloud fidelity via two cross-scan …

Go to article

Towards Improving Calibration In Object Detection Under Domain Shift, Muhammad Akhtar Munir, Muhammad Haris Khan, M. Saquib Sarfraz, Mohsen Ali Dec 2022

Towards Improving Calibration In Object Detection Under Domain Shift, Muhammad Akhtar Munir, Muhammad Haris Khan, M. Saquib Sarfraz, Mohsen Ali

Computer Vision Faculty Publications

With deep neural network based solution more readily being incorporated in real-world applications, it has been pressing requirement that predictions by such models, especially in safety-critical environments, be highly accurate and well-calibrated. Although some techniques addressing DNN calibration have been proposed, they are only limited to visual classification applications and in-domain predictions. Unfortunately, very little to no attention is paid towards addressing calibration of DNN-based visual object detectors, that occupy similar space and importance in many decision making systems as their visual classification counterparts. In this work, we study the calibration of DNN-based object detection models, particularly under domain shift. …

Go to article

Intermediate Prototype Mining Transformer For Few-Shot Semantic Segmentation, Yuanwei Liu, Nian Liu, Xiwen Yao, Junwei Han Dec 2022

Intermediate Prototype Mining Transformer For Few-Shot Semantic Segmentation, Yuanwei Liu, Nian Liu, Xiwen Yao, Junwei Han

Computer Vision Faculty Publications

Few-shot semantic segmentation aims to segment the target objects in query under the condition of a few annotated support images. Most previous works strive to mine more effective category information from the support to match with the corresponding objects in query. However, they all ignored the category information gap between query and support images. If the objects in them show large intra-class diversity, forcibly migrating the category information from the support to the query is ineffective. To solve this problem, we are the first to introduce an intermediate prototype for mining both deterministic category information from the support and adaptive …

Go to article

A Call For Research: Ethical Dilemmas Of Autonomous Vehicle Manufacturers, Remy Harwood Dec 2022

A Call For Research: Ethical Dilemmas Of Autonomous Vehicle Manufacturers, Remy Harwood

Cybersecurity Undergraduate Research Showcase

While autonomous vehicles accounted for about 31.4 million vehicles on the road in 2019 (Placek). They have continued to flood the market and have a projected growth to 58 million in just 8 years from now (Placek) As well as a market cap in the billions of dollars. Even the comparatively new AV company Tesla has over 3 times the market cap value of the leading non AV brand Toyota (Market Cap) who are also working toward AVs as well, like their level 2 teammate driver assistance. Following Moore’s Law, as technology continues to improve, their social impact and ethical …

Go to article

Explainable Ai Helps Bridge The Ai Skills Gap: Evidence From A Large Bank, Selina Carter, Jonathan Hersh Dec 2022

Explainable Ai Helps Bridge The Ai Skills Gap: Evidence From A Large Bank, Selina Carter, Jonathan Hersh

Economics Faculty Articles and Research

Advances in machine learning have created an “AI skills gap” both across and within firms. As AI becomes embedded in firm processes, it is unknown how this will impact the digital divide between workers with and without AI skills. In this paper we ask whether managers trust AI to predict consequential events, what manager characteristics are associated with increasing trust in AI predictions, and whether explainable AI (XAI) affects users’ trust in AI predictions. Partnering with a large bank, we generated AI predictions for whether a loan will be late in its final disbursement. We embedded these predictions into a …

Go to article

Assessing Wood Failure In Plywood By Deep Learning/Semantic Segmentation, Ramon Ferreira Oliveira Dec 2022

Assessing Wood Failure In Plywood By Deep Learning/Semantic Segmentation, Ramon Ferreira Oliveira

Theses and Dissertations

The current method for estimating wood failure is highly subjective. Various techniques have been proposed to improve the current protocol, but none have succeeded. This research aims to use deep learning/semantic segmentation using SegNet architecture to estimate wood failure in four types of three-ply plywood from mechanical shear strength specimens. We trained and tested our approach on custom and commercial plywood with bio-based and phenol-formaldehyde adhesives. Shear specimens were prepared and tested. Photographs of 255 shear bonded areas were taken. Forty photographs were used to solicit visual estimates from five human evaluators, and the remaining photographs were used to train …

Go to article

Iitd At The Wanlp 2022 Shared Task: Multilingual Multi-Granularity Network For Propaganda Detection, Shubham Mittal, Preslav Nakov Dec 2022

Iitd At The Wanlp 2022 Shared Task: Multilingual Multi-Granularity Network For Propaganda Detection, Shubham Mittal, Preslav Nakov

Natural Language Processing Faculty Publications

We present our system for the two subtasks of the shared task on propaganda detection in Arabic, part of WANLP'2022. Subtask 1 is a multi-label classification problem to find the propaganda techniques used in a given tweet. Our system for this task uses XLM-R to predict probabilities for the target tweet to use each of the techniques. In addition to finding the techniques, Subtask 2 further asks to identify the textual span for each instance of each technique that is present in the tweet; the task can be modeled as a sequence tagging problem. We use a multi-granularity network with …

Go to article

Transfer Of Personality Through Text Style, Michael O'Mahony, Robert Ross Dec 2022

Transfer Of Personality Through Text Style, Michael O'Mahony, Robert Ross

Other resources

The style of generated text is how something is said rather than what is said. We hypothesize that changing the style of generated text can change the perceived personality of the text generation agent. Dialogue systems that aim to imitate a human agent can appear to have a consistent personality through a consistent, controllable style of conversation. Some recent work on the style of generated text [1] performs impressively in the small number of domains selected for their experiments using transformer and LSTM-based models. Lin et al. [1] used weak supervised learning as their data set lacks parallel data. The …

Go to article

Hate-Clipper: Multimodal Hateful Meme Classification Based On Cross-Modal Interaction Of Clip Features, Gokul Karthik Kumar, Karthik Nandakumar Dec 2022

Hate-Clipper: Multimodal Hateful Meme Classification Based On Cross-Modal Interaction Of Clip Features, Gokul Karthik Kumar, Karthik Nandakumar

Computer Vision Faculty Publications

Hateful memes are a growing menace on social media. While the image and its corresponding text in a meme are related, they do not necessarily convey the same meaning when viewed individually. Hence, detecting hateful memes requires careful consideration of both visual and textual information. Multimodal pretraining can be beneficial for this task because it effectively captures the relationship between the image and the text by representing them in a similar feature space. Furthermore, it is essential to model the interactions between the image and text features through intermediate fusion. Most existing methods either employ multimodal pre-training or intermediate fusion, …

Go to article

Actively Guided Cansats For Assisting Localization And Mapping In Unstructured And Unknown Environments, Cary Chun, M. Hassan Tanveer Dec 2022

Actively Guided Cansats For Assisting Localization And Mapping In Unstructured And Unknown Environments, Cary Chun, M. Hassan Tanveer

Symposium of Student Scholars

When navigating in unknown and unstructured environments, Unmanned Arial Vehicles (UAVs) can struggle when attempting to preform Simultaneous Localization and Mapping (SLAM) operations. Particularly challenging circumstance arise when an UAV may need to land or otherwise navigate through treacherous environments. As the primary UAV may be too large and unwieldly to safely investigate in these types of situations, this research effort proposes the use of actively guided CanSats for assisting in localization and mapping of unstructured environments. A complex UAV could carry multiple of these SLAM capable CanSats, and when additional mapping and localization capabilities where required, the CanSat would …

Go to article

A High-Accuracy Detection System: Based On Transfer Learning For Apical Lesions On Periapical Radiograph, Yueh Chuo, Wen-Ming Lin, Tsung-Yi Chen, Mei-Ling Chan, Yu-Sung Chang, Yan-Ru Lin, Yuan-Jin Lin, Yu-Han Shao, Chiung-An Chen, Patricia Angela R. Abu Dec 2022

A High-Accuracy Detection System: Based On Transfer Learning For Apical Lesions On Periapical Radiograph, Yueh Chuo, Wen-Ming Lin, Tsung-Yi Chen, Mei-Ling Chan, Yu-Sung Chang, Yan-Ru Lin, Yuan-Jin Lin, Yu-Han Shao, Chiung-An Chen, Patricia Angela R. Abu

Department of Information Systems & Computer Science Faculty Publications

Apical Lesions, one of the most common oral diseases, can be effectively detected in daily dental examinations by a periapical radiograph (PA). In the current popular endodontic treatment, most dentists spend a lot of time manually marking the lesion area. In order to reduce the burden on dentists, this paper proposes a convolutional neural network (CNN)-based regional analysis model for spical lesions for periapical radiographs. In this study, the database was provided by dentists with more than three years of practical experience, meeting the criteria for clinical practical application. The contributions of this work are (1) an advanced adaptive threshold …

Go to article

College Teaching And Ai, Leo Irakliotis Dec 2022

College Teaching And Ai, Leo Irakliotis

Computer Science: Faculty Publications and Other Works

Artificial Intelligence will reshape the way we assess student learning in ways that no one has prepared us for.

Go to article

The Interaction Of Normalisation And Clustering In Sub-Domain Definition For Multi-Source Transfer Learning Based Time Series Anomaly Detection, Matthew Nicholson, Rahul Agrahari, Clare Conran, Haythem Assem, John D. Kelleher Dec 2022

The Interaction Of Normalisation And Clustering In Sub-Domain Definition For Multi-Source Transfer Learning Based Time Series Anomaly Detection, Matthew Nicholson, Rahul Agrahari, Clare Conran, Haythem Assem, John D. Kelleher

Articles

This paper examines how data normalisation and clustering interact in the definition of sub-domains within multi-source transfer learning systems for time series anomaly detection. The paper introduces a distinction between (i) clustering as a primary/direct method for anomaly detection, and (ii) clustering as a method for identifying sub-domains within the source or target datasets. Reporting the results of three sets of experiments, we find that normalisation after feature extraction and before clustering results in the best performance for anomaly detection. Interestingly, we find that in the multi-source transfer learning scenario clustering on the target dataset and identifying subdomains in the …

Go to article

Artificial Intelligence In The Medical Field: Medical Review Sentiment Analysis, Nicholas Podlesak Dec 2022

Artificial Intelligence In The Medical Field: Medical Review Sentiment Analysis, Nicholas Podlesak

Honors Capstones

In this research project, natural language processing techniques’ ability to accurately classify medical text was measured to reinforce the relevance of artificial intelligence in the medical field. Sentiment analyses (analyses to determine whether the text was positive or negative) were performed on the prescription drug reviews in an open-source dataset using four different models: lexical, a neural network, a support vector machine, and a logistic regression model. Each model’s effectiveness was gauged by its ability to correctly classify unlabeled drug reviews (i.e., a percentage representing accuracy). The machine learning models were able to accurately classify the text, while the lexical …

Go to article

Predicting Publication Of Clinical Trials Using Structured And Unstructured Data: Model Development And Validation Study, Siyang Wang, Simon Šuster, Timothy Baldwin, Karin Verspoor Dec 2022

Predicting Publication Of Clinical Trials Using Structured And Unstructured Data: Model Development And Validation Study, Siyang Wang, Simon Šuster, Timothy Baldwin, Karin Verspoor

Natural Language Processing Faculty Publications

Background: Publication of registered clinical trials is a critical step in the timely dissemination of trial findings. However, a significant proportion of completed clinical trials are never published, motivating the need to analyze the factors behind success or failure to publish. This could inform study design, help regulatory decision-making, and improve resource allocation. It could also enhance our understanding of bias in the publication of trials and publication trends based on the research direction or strength of the findings. Although the publication of clinical trials has been addressed in several descriptive studies at an aggregate level, there is a lack …

Go to article

Assisting The Human Fact-Checkers: Detecting All Previously Fact-Checked Claims In A Document, Shaden Shaar, Nikola Georgiev, Firoj Alam, Giovanni Da San Martino, Aisha Mohamed, Preslav Nakov Dec 2022

Assisting The Human Fact-Checkers: Detecting All Previously Fact-Checked Claims In A Document, Shaden Shaar, Nikola Georgiev, Firoj Alam, Giovanni Da San Martino, Aisha Mohamed, Preslav Nakov

Natural Language Processing Faculty Publications

Given the recent proliferation of false claims online, there has been a lot of manual fact-checking effort. As this is very time-consuming, human fact-checkers can benefit from tools that can support them and make them more efficient. Here, we focus on building a system that could provide such support. Given an input document, it aims to detect all sentences that contain a claim that can be verified by some previously fact-checked claims (from a given database). The output is a re-ranked list of the document sentences, so that those that can be verified are ranked as high as possible, together …

Go to article

Overview Of The Wanlp 2022 Shared Task On Propaganda Detection In Arabic, Firoj Alam, Hamdy Mubarak, Wajdi Zaghouani, Giovanni Da San Martino, Preslav Nakov Dec 2022

Overview Of The Wanlp 2022 Shared Task On Propaganda Detection In Arabic, Firoj Alam, Hamdy Mubarak, Wajdi Zaghouani, Giovanni Da San Martino, Preslav Nakov

Natural Language Processing Faculty Publications

Propaganda is the expression of an opinion or an action by an individual or a group deliberately designed to influence the opinions or the actions of other individuals or groups with reference to predetermined ends, which is achieved by means of well-defined rhetorical and psychological devices. Propaganda techniques are commonly used in social media to manipulate or to mislead users. Thus, there has been a lot of recent research on automatic detection of propaganda techniques in text as well as in memes. However, so far the focus has been primarily on English. With the aim to bridge this language gap, …

Go to article

Supervised Acoustic Embeddings And Their Transferability Across Languages, Sreepratha Ram, Hanan Aldarmaki Dec 2022

Supervised Acoustic Embeddings And Their Transferability Across Languages, Sreepratha Ram, Hanan Aldarmaki

Natural Language Processing Faculty Publications

In speech recognition, it is essential to model the phonetic content of the input signal while discarding irrelevant factors such as speaker variations and noise, which is challenging in low-resource settings. Self-supervised pretraining has been proposed as a way to improve both supervised and unsupervised speech recognition, including frame-level feature representations and Acoustic Word Embeddings (AWE) for variable-length segments. However, self-supervised models alone cannot learn perfect separation of the linguistic content as they are trained to optimize indirect objectives. In this work, we experiment with different pre-trained self-supervised features as input to AWE models and show that they work best …

Go to article

Camelira: An Arabic Multi-Dialect Morphological Disambiguator, Ossama Obeid, Go Inoue, Nizar Habash Dec 2022

Camelira: An Arabic Multi-Dialect Morphological Disambiguator, Ossama Obeid, Go Inoue, Nizar Habash

Computer Vision Faculty Publications

We present Camelira, a web-based Arabic multi-dialect morphological disambiguation tool that covers four major variants of Arabic: Modern Standard Arabic, Egyptian, Gulf, and Levantine. Camelira offers a user-friendly web interface that allows researchers and language learners to explore various linguistic information, such as part-of-speech, morphological features, and lemmas. Our system also provides an option to automatically choose an appropriate dialect-specific disambiguator based on the prediction of a dialect identification component. Camelira is publicly accessible at http://camelira.camel-lab.com.

Go to article

Pasta: Table-Operations Aware Fact Verification Via Sentence-Table Cloze Pre-Training, Zihui Gu, Ju Fan, Nan Tang, Preslav Nakov, Xiaoman Zhao, Xiaoyong Du Dec 2022

Pasta: Table-Operations Aware Fact Verification Via Sentence-Table Cloze Pre-Training, Zihui Gu, Ju Fan, Nan Tang, Preslav Nakov, Xiaoman Zhao, Xiaoyong Du

Natural Language Processing Faculty Publications

Fact verification has attracted a lot of research attention recently, e.g., in journalism, marketing, and policymaking, as misinformation and disinformation online can sway one's opinion and affect one's actions. While fact-checking is a hard task in general, in many cases, false statements can be easily debunked based on analytics over tables with reliable information. Hence, table-based fact verification has recently emerged as an important and growing research area. Yet, progress has been limited due to the lack of datasets that can be used to pre-train language models (LMs) to be aware of common table operations, such as aggregating a column …

Go to article

Greener: Graph Neural Networks For News Media Profiling, Panayot Panayotov, Utsav Shukla, Husrev T. Sencar, Mohamed Nabeel, Preslav Nakov Dec 2022

Greener: Graph Neural Networks For News Media Profiling, Panayot Panayotov, Utsav Shukla, Husrev T. Sencar, Mohamed Nabeel, Preslav Nakov

Natural Language Processing Faculty Publications

We study the problem of profiling news media on the Web with respect to their factuality of reporting and bias. This is an important but under-studied problem related to disinformation and “fake news” detection, but it addresses the issue at a coarser granularity compared to looking at an individual article or an individual claim. This is useful as it allows to profile entire media outlets in advance. Unlike previous work, which has focused primarily on text (e.g., on the articles published by the target website, or on the textual description in their social media profiles or in Wikipedia), here we …

Go to article

Asdot: Any-Shot Data-To-Text Generation With Pretrained Language Models, Jiannan Xiang, Zhengzhong Liu, Yucheng Zhou, Eric P. Xing, Zhiting Hu Dec 2022

Asdot: Any-Shot Data-To-Text Generation With Pretrained Language Models, Jiannan Xiang, Zhengzhong Liu, Yucheng Zhou, Eric P. Xing, Zhiting Hu

Machine Learning Faculty Publications

Data-to-text generation is challenging due to the great variety of the input data in terms of domains (e.g., finance vs sports) or schemata (e.g., diverse predicates). Recent end-to-end neural methods thus require substantial training examples to learn to disambiguate and describe the data. Yet, real-world data-to-text problems often suffer from various data-scarce issues: one may have access to only a handful of or no training examples, and/or have to rely on examples in a different domain or schema. To fill this gap, we propose Any-Shot Data-to-Text (ASDOT), a new approach flexibly applicable to diverse settings by making efficient use of …

Go to article

Impact Of Digital Twins And Metaverse On Cities: History, Current Situation, And Application Perspectives, Zhihan Lv, Wen Long Shang, Mohsen Guizani Dec 2022

Impact Of Digital Twins And Metaverse On Cities: History, Current Situation, And Application Perspectives, Zhihan Lv, Wen Long Shang, Mohsen Guizani

Machine Learning Faculty Publications

To promote the expansion and adoption of Digital Twins (DTs) in Smart Cities (SCs), a detailed review of the impact of DTs and digitalization on cities is made to assess the progression of cities and standardization of their management mode. Combined with the technical elements of DTs, the coupling effect of DTs technology and urban construction and the internal logic of DTs technology embedded in urban construction are discussed. Relevant literature covering the full range of DTs technologies and their applications is collected, evaluated, and collated, relevant studies are concatenated, and relevant accepted conclusions are summarized by modules. First, the …

Go to article

Resel: N-Ary Relation Extraction From Scientific Text And Tables By Learning To Retrieve And Select, Yuchen Zhuang, Yinghao Li, Jerry Junyang Cheung, Yue Yu, Yingjun Mou, Xiang Chen, Le Song, Chao Zhang Dec 2022

Resel: N-Ary Relation Extraction From Scientific Text And Tables By Learning To Retrieve And Select, Yuchen Zhuang, Yinghao Li, Jerry Junyang Cheung, Yue Yu, Yingjun Mou, Xiang Chen, Le Song, Chao Zhang

Machine Learning Faculty Publications

We study the problem of extracting N-ary relation tuples from scientific articles. This task is challenging because the target knowledge tuples can reside in multiple parts and modalities of the document. Our proposed method RESEL decomposes this task into a two-stage procedure that first retrieves the most relevant paragraph/table and then selects the target entity from the retrieved component. For the high-level retrieval stage, RESEL designs a simple and effective feature set, which captures multilevel lexical and semantic similarities between the query and components. For the low-level selection stage, RESEL designs a cross-modal entity correlation graph along with a multi-view …

Go to article

Efficient (Soft) Q-Learning For Text Generation With Limited Good Data, Han Guo, Bowen Tan, Zhengzhong Liu, Eric P. Xing, Zhiting Hu Dec 2022

Efficient (Soft) Q-Learning For Text Generation With Limited Good Data, Han Guo, Bowen Tan, Zhengzhong Liu, Eric P. Xing, Zhiting Hu

Machine Learning Faculty Publications

Maximum likelihood estimation (MLE) is the predominant algorithm for training text generation models. This paradigm relies on direct supervision examples, which is not applicable to many emerging applications, such as generating adversarial attacks or generating prompts to control language models. Reinforcement learning (RL) on the other hand offers a more flexible solution by allowing users to plug in arbitrary task metrics as reward. Yet previous RL algorithms for text generation, such as policy gradient (on-policy RL) and Q-learning (off-policy RL), are often notoriously inefficient or unstable to train due to the large sequence space and the sparse reward received only …

Go to article

Amp: Automatically Finding Model Parallel Strategies With Heterogeneity Awareness, Dacheng Li, Hongyi Wang, Eric Xing, Hao Zhang Dec 2022

Amp: Automatically Finding Model Parallel Strategies With Heterogeneity Awareness, Dacheng Li, Hongyi Wang, Eric Xing, Hao Zhang

Machine Learning Faculty Publications

Scaling up model sizes can lead to fundamentally new capabilities in many machine learning (ML) tasks. However, training big models requires strong distributed system expertise to carefully design model-parallel execution strategies that suit the model architectures and cluster setups. In this paper, we develop AMP, a framework that automatically derives such strategies. AMP identifies a valid space of model parallelism strategies and efficiently searches the space for high-performed strategies, by leveraging a cost model designed to capture the heterogeneity of the model and cluster specifications. Unlike existing methods, AMP is specifically tailored to support complex models composed of uneven layers …

Go to article

Unpaired Image-To-Image Translation With Density Changing Regularization, Shaoan Xie, Qirong Ho, Kun Zhang Dec 2022

Unpaired Image-To-Image Translation With Density Changing Regularization, Shaoan Xie, Qirong Ho, Kun Zhang

Machine Learning Faculty Publications

Unpaired image-to-image translation aims to translate an input image to another domain such that the output image looks like an image from another domain while important semantic information are preserved. Inferring the optimal mapping with unpaired data is impossible without making any assumptions. In this paper, we make a density changing assumption where image patches of high probability density should be mapped to patches of high probability density in another domain. Then we propose an efficient way to enforce this assumption: we train the flows as density estimators and penalize the variance of density changes. Despite its simplicity, our method …

Go to article

On Pac Learning Halfspaces In Non-Interactive Local Privacy Model With Public Unlabeled Data, Jinyan Su, Jinhui Xu, Di Wang Dec 2022

On Pac Learning Halfspaces In Non-Interactive Local Privacy Model With Public Unlabeled Data, Jinyan Su, Jinhui Xu, Di Wang

Machine Learning Faculty Publications

In this paper, we study the problem of PAC learning halfspaces in the non-interactive local differential privacy model (NLDP). To breach the barrier of exponential sample complexity, previous results studied a relaxed setting where the server has access to some additional public but unlabeled data. We continue in this direction. Specifically, we consider the problem under the standard setting instead of the large margin setting studied before. Under different mild assumptions on the underlying data distribution, we propose two approaches that are based on the Massart noise model and self-supervised learning and show that it is possible to achieve sample …

Go to article

A Damped Newton Method Achieves Global O(1/K2) And Local Quadratic Convergence Rate, Slavomír Hanzely, Dmitry Kamzolov, Dmitry Pasechnyuk, Alexander Gasnikov, Peter Richtárik, Martin Takáč Dec 2022

A Damped Newton Method Achieves Global O(1/K2) And Local Quadratic Convergence Rate, Slavomír Hanzely, Dmitry Kamzolov, Dmitry Pasechnyuk, Alexander Gasnikov, Peter Richtárik, Martin Takáč

Machine Learning Faculty Publications

In this paper, we present the first stepsize schedule for Newton method resulting in fast global and local convergence guarantees. In particular, a) we prove an O (1/k2) global rate, which matches the state-of-the-art global rate of cubically regularized Newton method of Polyak and Nesterov (2006) and of regularized Newton method of Mishchenko (2021) and Doikov and Nesterov (2021), b) we prove a local quadratic rate, which matches the best-known local rate of second-order methods, and c) our stepsize formula is simple, explicit, and does not require solving any subproblem. Our convergence proofs hold under affine-invariance assumptions closely related to …

Go to article

First Prev Next Last