Relevant bibliographies by topics / Gradient query

Contents

  1. Journal articles
  2. Dissertations / Theses
  3. Book chapters
  4. Conference papers

Academic literature on the topic 'Gradient query'

Author: Grafiati
Published: 3 June 2025
Last updated: 31 July 2025

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles

Select a source type:

Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Gradient query.'

Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.

You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.

Journal articles on the topic "Gradient query"

1

Lapid, Raz, Zvika Haramaty, and Moshe Sipper. "An Evolutionary, Gradient-Free, Query-Efficient, Black-Box Algorithm for Generating Adversarial Instances in Deep Convolutional Neural Networks." Algorithms 15, no. 11 (2022): 407. http://dx.doi.org/10.3390/a15110407.

Full text
Abstract:
Deep neural networks (DNNs) are sensitive to adversarial data in a variety of scenarios, including the black-box scenario, where the attacker is only allowed to query the trained model and receive an output. Existing black-box methods for creating adversarial instances are costly, often using gradient estimation or training a replacement network. This paper introduces Qu ery-Efficient Evolutionary Attack—QuEry Attack—an untargeted, score-based, black-box attack. QuEry Attack is based on a novel objective function that can be used in gradient-free optimization problems. The attack only requires
APA, Harvard, Vancouver, ISO, and other styles
2

Bilquees, Samina, Hassan Dawood, Hussain Dawood, Nadeem Majeed, Ali Javed, and Muhammad Tariq Mahmood. "Noise Resilient Local Gradient Orientation for Content-Based Image Retrieval." International Journal of Optics 2021 (July 14, 2021): 1–19. http://dx.doi.org/10.1155/2021/4151482.

Full text
Abstract:
In a world of multimedia information, where users seek accurate results against search query and demand relevant multimedia content retrieval, developing an accurate content-based image retrieval (CBIR) system is difficult due to the presence of noise in the image. The performance of the CBIR system is impaired by this noise. To estimate the distance between the query and database images, CBIR systems use image feature representation. The noise or artifacts present within the visual data might confuse the CBIR when retrieving relevant results. Therefore, we propose Noise Resilient Local Gradie
APA, Harvard, Vancouver, ISO, and other styles
3

Zhao, Pu, Pin-yu Chen, Siyue Wang, and Xue Lin. "Towards Query-Efficient Black-Box Adversary with Zeroth-Order Natural Gradient Descent." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 04 (2020): 6909–16. http://dx.doi.org/10.1609/aaai.v34i04.6173.

Full text
Abstract:
Despite the great achievements of the modern deep neural networks (DNNs), the vulnerability/robustness of state-of-the-art DNNs raises security concerns in many application domains requiring high reliability. Various adversarial attacks are proposed to sabotage the learning performance of DNN models. Among those, the black-box adversarial attack methods have received special attentions owing to their practicality and simplicity. Black-box attacks usually prefer less queries in order to maintain stealthy and low costs. However, most of the current black-box attack methods adopt the first-order
APA, Harvard, Vancouver, ISO, and other styles
4

Kumar, R. Sathish, and M. Chandrasekaran. "Inducing and Refining Topics for Web Query Classification Using a Semantic Network." Journal of Computational and Theoretical Nanoscience 15, no. 2 (2018): 595–600. http://dx.doi.org/10.1166/jctn.2018.7127.

Full text
Abstract:
Web query classification, the task of inferring topical categories from a web search query is a non-trivial problem in Information Retrieval domain. The topic categories inferred by a Web query classification system may provide a rich set of features for improving query expansion and web advertising. Conventional methods for Web query classification derive corpus statistics from the web and employ machine-learning techniques to infer Open Directory Project categories. But they suffer from two major drawbacks, the computational overhead to derive corpus statistics and inferring topic categories
APA, Harvard, Vancouver, ISO, and other styles
5

Yang, Yuli, Zishuo Liu, Zhen Lei, Shuhong Wu, and Yongle Chen. "Black-Box Boundary Attack Based on Gradient Optimization." Electronics 13, no. 6 (2024): 1009. http://dx.doi.org/10.3390/electronics13061009.

Full text
Abstract:
Deep neural networks have gained extensive applications in computer vision, demonstrating significant success in fundamental research tasks such as image classification. However, the robustness of these networks faces severe challenges in the presence of adversarial attacks. In real-world scenarios, addressing hard-label attacks often requires the execution of tens of thousands of queries. To combat these challenges, the Black-Box Boundary Attack leveraging Gradient Optimization (GOBA) has been introduced. This method employs a binary search strategy to acquire an initial adversarial example w
APA, Harvard, Vancouver, ISO, and other styles
6

Sumalatha, V., and Suresh Pabboju. "Optimal Index Selection using Optimized Deep Deterministic Policy Gradient for NoSQL Database." Engineering, Technology & Applied Science Research 14, no. 6 (2024): 18125–30. https://doi.org/10.48084/etasr.8832.

Full text
Abstract:
As big data technology has developed, so have complex applications that require increasing resources. The need for high-performance reading and writing increases the usage of NoSQL (MongoDB) databases. As the number of queries in a given amount of time negatively affects the performance of the database, an automated index selection strategy should be used to improve the database performance. This study proposes an Optimized Deep Deterministic Policy Gradient (ODDPG) to select the optimal index. The Adaptive Crocodile Optimization Algorithm (ACOA) is used to improve DDPG's decision-making perfo
APA, Harvard, Vancouver, ISO, and other styles
7

Chang, Ting-Jui, and Shahin Shahrampour. "On Online Optimization: Dynamic Regret Analysis of Strongly Convex and Smooth Problems." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 8 (2021): 6966–73. http://dx.doi.org/10.1609/aaai.v35i8.16858.

Full text
Abstract:
The regret bound of dynamic online learning algorithms is often expressed in terms of the variation in the function sequence (V_T) and/or the path-length of the minimizer sequence after T rounds. For strongly convex and smooth functions, Zhang et al. (2017) establish the squared path-length of the minimizer sequence (C*_{2,T}) as a lower bound on regret. They also show that online gradient descent (OGD) achieves this lower bound using multiple gradient queries per round. In this paper, we focus on unconstrained online optimization. We first show that a preconditioned variant of OGD achieves O(
APA, Harvard, Vancouver, ISO, and other styles
8

Liu, Zhuang, Xin Feng, Jingjing Zhang, Teng Li, and Yanlong Wang. "An Improved GPSR Algorithm Based on Energy Gradient and APIT Grid." Journal of Sensors 2016 (2016): 1–7. http://dx.doi.org/10.1155/2016/2519714.

Full text
Abstract:
We investigate GPSR algorithms of WSN and propose an improved routing algorithm based on energy gradient and APIT grid to solve the problem of high and unbalanced energy consumption of GPSR. In GPSR, network uses greedy algorithm and right-hand rule to establish routing paths, and the path keeps running till some nodes within the path are invalid because energy is exhausted, which would lead to the high energy consumption of some nodes in the path and the low energy consumption of others nearby the nodes not in the path as well as bringing high and unbalanced energy consumption of the network.
APA, Harvard, Vancouver, ISO, and other styles
9

Meng, Fan'an, Chaoran Cui, Hongjun Dai, and Shuai Gong. "Black-Box Test-Time Prompt Tuning for Vision-Language Models." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 6 (2025): 6099–107. https://doi.org/10.1609/aaai.v39i6.32652.

Full text
Abstract:
Test-time prompt tuning (TPT) aims to adjust the vision-language models (e.g., CLIP) with learnable prompts during the inference phase. However, previous works overlooked that pre-trained models as a service (MaaS) have become a noticeable trend due to their commercial usage and potential risk of misuse. In the context of MaaS, users can only design prompts in inputs and query the black-box vision-language models through inference APIs, rendering the previous paradigm of utilizing gradient for prompt tuning is infeasible. In this paper, we propose black-box test-time prompt tuning (B²TPT), a n
APA, Harvard, Vancouver, ISO, and other styles
10

Han, Dong, Reza Babaei, Shangqing Zhao, and Samuel Cheng. "Exploring the Efficacy of Learning Techniques in Model Extraction Attacks on Image Classifiers: A Comparative Study." Applied Sciences 14, no. 9 (2024): 3785. http://dx.doi.org/10.3390/app14093785.

Full text
Abstract:
In the rapidly evolving landscape of cybersecurity, model extraction attacks pose a significant challenge, undermining the integrity of machine learning models by enabling adversaries to replicate proprietary algorithms without direct access. This paper presents a comprehensive study on model extraction attacks towards image classification models, focusing on the efficacy of various Deep Q-network (DQN) extensions for enhancing the performance of surrogate models. The goal is to identify the most efficient approaches for choosing images that optimize adversarial benefits. Additionally, we expl
APA, Harvard, Vancouver, ISO, and other styles
More sources

Dissertations / Theses on the topic "Gradient query"

1

Venkatamuniyappa, Vijay Kumar. "Towards automatic grading of SQL queries." Kansas State University, 2018. http://hdl.handle.net/2097/38819.

Full text
Abstract:
Master of Science<br>Department of Computer Science<br>Doina Caragea<br>An Introduction to Databases course involves learning the concepts of data storage, manipulation, and retrieval. Relational databases provide an ideal learning path for understanding database concepts. The Structured Query Language (SQL) is a standard language for interacting with relational database. Each database vendor implements a variation of the SQL standard. Furthermore, a particular question that asks for some data can be written in many ways, using somewhat similar or structurally different SQL queries. Evaluation
APA, Harvard, Vancouver, ISO, and other styles

Book chapters on the topic "Gradient query"

1

Huang, Haizun, Shihua Qin, Chihua Wang, et al. "The Application of Beidou High-Precision Positioning Technology in the Deformation Monitoring of Ship Locks." In Lecture Notes in Civil Engineering. Springer Nature Singapore, 2023. http://dx.doi.org/10.1007/978-981-19-6138-0_12.

Full text
Abstract:
AbstractAccompanying the construction of inland navigation projects is the generation of high slopes, whose stability has always been an important safety issue of great concern during the process. The safety incidents involving high slope instability often cause huge economic losses and even casualties. Therefore, it is of particular importance to monitor high slopes, to identify safety hazards and to predict the occurrence of safety accidents in advance through the tendency of changing. Once the project is completed, effective monitoring is also essential during the operation of the locks in
APA, Harvard, Vancouver, ISO, and other styles
2

Alves, Ronnie, Joel Ribeiro, Orlando Belo, and Jiawei Han. "Ranking Gradients in Multi-Dimensional Spaces." In Complex Data Warehousing and Knowledge Discovery for Advanced Retrieval Development. IGI Global, 2010. http://dx.doi.org/10.4018/978-1-60566-748-5.ch011.

Full text
Abstract:
Business organizations must pay attention to interesting changes in customer behavior in order to anticipate their needs and act accordingly with appropriated business actions. Tracking customer’s commercial paths through the products they are interested in is an essential technique to improve business and increase customer satisfaction. Data warehousing (DW) allows us to do so, giving the basic means to record every customer transaction based on the different business strategies established. Although managing such huge amounts of records may imply business advantage, its exploration, especial
APA, Harvard, Vancouver, ISO, and other styles
3

Satheesh Kumar, B., K. Seetharaman, and B. Sathiyaprasad. "A Novel Adaboost Regression Classifier for Video Retrieval in Video Sequence." In Intelligent Systems and Computer Technology. IOS Press, 2020. http://dx.doi.org/10.3233/apc200194.

Full text
Abstract:
This paper presents a new method for video retrieval, based on machine learning with regression. The proposed classification technique integrates Adaboost and regression classifier for significant retrieval of video frame. The proposed method consists of three stages such as key frames segmentation and gradient of pixels. In this technique, Adaboost classifier is involved in removal of noisy or blurred pixel of the segmented frame. Regression technique converts the video frame pixel either 0’s or 1’s which eliminates the noises in the frame. For the query video, the adopted classifier evaluate
APA, Harvard, Vancouver, ISO, and other styles
4

"Ranking Properties of Spatiotemporal RDF Data." In Advances in Systems Analysis, Software Engineering, and High Performance Computing. IGI Global, 2023. http://dx.doi.org/10.4018/978-1-6684-9108-9.ch004.

Full text
Abstract:
Based on the sorting algorithm, the authors discuss the ranking of spatiotemporal RDF data properties and attempt to improve the query efficiency of large RDF datasets. The chapter introduces three sorting algorithms in machine learning: LR (logistic regression) algorithm, GBDT (gradient boosting decision tree) and FM (factorization machines) model algorithm. After the data sorting system is completed, the authors use A/B test method to test the system. It is self-evident that the recommendation algorithm based on FM ranking is more efficient than linear regression ranking. Using the model per
APA, Harvard, Vancouver, ISO, and other styles
5

Zhang, Zhong’ao, Zuowei Xu, and Dan Zhu. "Intelligent Remote Monitoring Method for Power Operation Site Based on Video Recognition Technology." In Advances in Transdisciplinary Engineering. IOS Press, 2024. http://dx.doi.org/10.3233/atde231181.

Full text
Abstract:
In order to improve the accuracy of risk recognition in power operation site, an intelligent remote monitoring method for power operation site based on video recognition technology is proposed. First, according to the video recognition architecture, the pictures of the power operation site are collected through the video camera. Secondly, in order to improve the quality of the image, histogram enhancement, smooth denoising and gradient sharpening are performed on the collected image. Finally, the preprocessed image is input into BP neural network, and the risk recognition of power operation si
APA, Harvard, Vancouver, ISO, and other styles
6

Serafini, Luciano, Artur d’Avila Garcez, Samy Badreddine, Ivan Donadello, Michael Spranger, and Federico Bianchi. "Chapter 17. Logic Tensor Networks: Theory and Applications." In Frontiers in Artificial Intelligence and Applications. IOS Press, 2021. http://dx.doi.org/10.3233/faia210498.

Full text
Abstract:
The recent availability of large-scale data combining multiple data modalities has opened various research and commercial opportunities in Artificial Intelligence (AI). Machine Learning (ML) has achieved important results in this area mostly by adopting a sub-symbolic distributed representation. It is generally accepted now that such purely sub-symbolic approaches can be data inefficient and struggle at extrapolation and reasoning. By contrast, symbolic AI is based on rich, high-level representations ideally based on human-readable symbols. Despite being more explainable and having success at
APA, Harvard, Vancouver, ISO, and other styles
7

Zhai, Feng, Baofeng Li, Xiaobing Liang, Yu Qin, and Wen Ji. "Research on Power Data Security Classification Based on O-Svm Algorithm." In Frontiers in Artificial Intelligence and Applications. IOS Press, 2024. http://dx.doi.org/10.3233/faia231378.

Full text
Abstract:
With the development of the new digital power system, the scale, type and value of power data are increasing, and the security protection of power data is confronted with serious challenges and risks. Through scientific, reasonable and dynamic security grading of electric power data, it can achieve the refinement, differentiation and personalization of electric power data security protection and avoid the phenomenon of “one size fits all”. Therefore, this paper builds a power data security classification and query system, firstly, by analyzing the security requirements of data in multiple scen
APA, Harvard, Vancouver, ISO, and other styles

Conference papers on the topic "Gradient query"

1

Wang, Guanghui, Dakuan Zhao, and Lijun Zhang. "Minimizing Adaptive Regret with One Gradient per Iteration." In Twenty-Seventh International Joint Conference on Artificial Intelligence {IJCAI-18}. International Joint Conferences on Artificial Intelligence Organization, 2018. http://dx.doi.org/10.24963/ijcai.2018/383.

Full text
Abstract:
To cope with non-stationary environments, recent advances in online optimization have introduced the notion of adaptive regret, which measures the performance of an online learner against different comparators within different time intervals. Previous studies have proposed various algorithms to yield low adaptive regret under different scenarios. However, all of existing algorithms need to query the gradient of the loss function at least O(log t) times in every iteration t, which hinders their applications to broad domains, especially when the evaluation of gradients is expensive. To address t
APA, Harvard, Vancouver, ISO, and other styles
2

Marsden, Annie, Vatsal Sharan, Aaron Sidford, and Gregory Valiant. "Efficient Convex Optimization Requires Superlinear Memory (Extended Abstract)." In Thirty-Second International Joint Conference on Artificial Intelligence {IJCAI-23}. International Joint Conferences on Artificial Intelligence Organization, 2023. http://dx.doi.org/10.24963/ijcai.2023/722.

Full text
Abstract:
Minimizing a convex function with access to a first order oracle---that returns the function evaluation and (sub)gradient at a query point---is a canonical optimization problem and a fundamental primitive in machine learning. Gradient-based methods are the most popular approaches used for solving the problem, owing to their simplicity and computational efficiency. These methods, however, do not achieve the information-theoretically optimal query complexity for minimizing the underlying function to small error, which are achieved by more expensive techniques based on cutting-plane methods. Is i
APA, Harvard, Vancouver, ISO, and other styles
3

Acharya, Rajaneesh, and Debashisha Jena. "Gradient descent in sample-based single-query path planning algorithm." In 2018 IEEMA Engineer Infinite Conference (eTechNxT). IEEE, 2018. http://dx.doi.org/10.1109/etechnxt.2018.8385319.

Full text
APA, Harvard, Vancouver, ISO, and other styles
4

Liu, Han, Xingshuo Huang, Xiaotong Zhang, et al. "Boosting Decision-Based Black-Box Adversarial Attack with Gradient Priors." In Thirty-Second International Joint Conference on Artificial Intelligence {IJCAI-23}. International Joint Conferences on Artificial Intelligence Organization, 2023. http://dx.doi.org/10.24963/ijcai.2023/133.

Full text
Abstract:
Decision-based methods have shown to be effective in black-box adversarial attacks, as they can obtain satisfactory performance and only require to access the final model prediction. Gradient estimation is a critical step in black-box adversarial attacks, as it will directly affect the query efficiency. Recent works have attempted to utilize gradient priors to facilitate score-based methods to obtain better results. However, these gradient priors still suffer from the edge gradient discrepancy issue and the successive iteration gradient direction issue, thus are difficult to simply extend to d
APA, Harvard, Vancouver, ISO, and other styles
5

Guo, Ying, Zhongwen Guo, Feng Hong, and Lu Hong. "Sleep Scheduling and Gradient Query in Sensor Networks for Target Monitoring." In 2009 Sixth IFIP International Conference on Network and Parallel Computing (NPC). IEEE, 2009. http://dx.doi.org/10.1109/npc.2009.33.

Full text
APA, Harvard, Vancouver, ISO, and other styles
6

Yuan, Yang, Soo-Whan Chung, and Hong-Goo Kang. "Gradient-based Active Learning Query Strategy for End-to-end Speech Recognition." In ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2019. http://dx.doi.org/10.1109/icassp.2019.8683089.

Full text
APA, Harvard, Vancouver, ISO, and other styles
7

Hwang, J. N., J. J. Choi, S. Oh, and R. J. ,. II Marks. "Query learning based on boundary search and gradient computation of trained multilayer perceptrons." In 1990 IJCNN International Joint Conference on Neural Networks. IEEE, 1990. http://dx.doi.org/10.1109/ijcnn.1990.137824.

Full text
APA, Harvard, Vancouver, ISO, and other styles
8

Minervini, Pasquale, Erik Arakelyan, Daniel Daza, and Michael Cochez. "Complex Query Answering with Neural Link Predictors (Extended Abstract)*." In Thirty-First International Joint Conference on Artificial Intelligence {IJCAI-22}. International Joint Conferences on Artificial Intelligence Organization, 2022. http://dx.doi.org/10.24963/ijcai.2022/741.

Full text
Abstract:
Neural link predictors are useful for identifying missing edges in large scale Knowledge Graphs. However, it is still not clear how to use these models for answering more complex queries containing logical conjunctions (∧), disjunctions (∨), and existential quantifiers (∃). We propose a framework for efficiently answering complex queries on in- complete Knowledge Graphs. We translate each query into an end-to-end differentiable objective, where the truth value of each atom is computed by a pre-trained neural link predictor. We then analyse two solutions to the optimisation problem, including g
APA, Harvard, Vancouver, ISO, and other styles
9

Ahmed, KasimuJuma. "Batch-Stochastic Sub-Gradient Method for Solving Non-Smooth Convex Loss Function Problems." In 9th International Conference on Artificial Intelligence and Applications. Academy & Industry Research Collaboration Center, 2023. http://dx.doi.org/10.5121/csit.2023.131806.

Full text
Abstract:
Mean Absolute Error (MAE) and Mean Square Error (MSE) are machine learning loss functions that not only estimates the discrepancy between prediction and true label but also guide the optimal parameter of the model.Gradient is used in estimating MSE model and Sub-gradient in estimating MAE model. Batch and stochastic are two of the many variations of sub-gradient method but the former considers the entire dataset per iteration while the latter considers one data point per iteration. Batch-stochastic Sub-gradient method that learn based on the inputted data and gives stable estimated loss value
APA, Harvard, Vancouver, ISO, and other styles
10

Yu, Lang, Qin Chen, Jiaju Lin, and Liang He. "Black-box Prompt Tuning for Vision-Language Model as a Service." In Thirty-Second International Joint Conference on Artificial Intelligence {IJCAI-23}. International Joint Conferences on Artificial Intelligence Organization, 2023. http://dx.doi.org/10.24963/ijcai.2023/187.

Full text
Abstract:
In the scenario of Model-as-a-Service (MaaS), pre-trained models are usually released as inference APIs. Users are allowed to query those models with manually crafted prompts. Without accessing the network structure and gradient information, it's tricky to perform continuous prompt tuning on MaaS, especially for vision-language models (VLMs) considering cross-modal interaction. In this paper, we propose a black-box prompt tuning framework for VLMs to learn task-relevant prompts without back-propagation. In particular, the vision and language prompts are jointly optimized in the intrinsic param
APA, Harvard, Vancouver, ISO, and other styles
You might also be interested in the extended bibliographies on the topic 'Gradient query' for particular source types:
Journal articles
We offer discounts on all premium plans for authors whose works are included in thematic literature selections. Contact us to get a unique promo code!

To the bibliography