13.3.12.10 Gradient Descent

Chapter Contents (Back)
Gradient Descent>. Optimization.

Kobayashi, T.[Takumi], Watanabe, K.[Kenji], Otsu, N.[Nobuyuki],
Logistic label propagation,
PRL(33), No. 5, 1 April 2012, pp. 580-588.
Elsevier DOI 1202
Semi-supervised learning; Logistic function; Label propagation; Similarity; Gradient descent BibRef

Baidoo-Williams, H.E., Dasgupta, S., Mudumbai, R., Bai, E.[Erwei],
On the Gradient Descent Localization of Radioactive Sources,
SPLetters(20), No. 11, 2013, pp. 1046-1049.
IEEE DOI 1310
gradient methods BibRef

Chen, J., Liu, Y.,
Data-Time Tradeoffs for Corrupted Sensing,
SPLetters(25), No. 7, July 2018, pp. 941-945.
IEEE DOI 1807
Gaussian processes, gradient methods, signal reconstruction, PGD method, corrupted sensing problems, data-time tradeoff, projected gradient descent (PGD) BibRef

Bottarelli, L.[Lorenzo], Loog, M.[Marco],
Gaussian process variance reduction by location selection,
PRL(125), 2019, pp. 727-734.
Elsevier DOI 1909
BibRef
Earlier:
Gradient Descent for Gaussian Processes Variance Reduction,
SSSPR18(160-169).
Springer DOI 1810
Gaussian process, Variance reduction, Gradient descent, Sampling BibRef

Li, P.L.[Pei-Lin], Lee, S.H.[Sang-Heon], Park, J.S.[Jae-Sam],
Development of a global batch clustering with gradient descent and initial parameters in colour image classification,
IET-IPR(13), No. 1, January 2019, pp. 161-174.
DOI Link 1812
BibRef

Cheng, C., Emirov, N., Sun, Q.,
Preconditioned Gradient Descent Algorithm for Inverse Filtering on Spatially Distributed Networks,
SPLetters(27), 2020, pp. 1834-1838.
IEEE DOI 2011
Signal processing algorithms, Approximation algorithms, Iterative methods, Data processing, Symmetric matrices, quasi-Newton method BibRef

Qu, Q.[Qing], Li, X.[Xiao], Zhu, Z.H.[Zhi-Hui],
Exact Recovery of Multichannel Sparse Blind Deconvolution via Gradient Descent,
SIIMS(13), No. 3, 2020, pp. 1630-1652.
DOI Link 2010
BibRef

Benning, M.[Martin], Betcke, M.M.[Marta M.], Ehrhardt, M.J.[Matthias J.], Schönlieb, C.B.[Carola-Bibiane],
Choose Your Path Wisely: Gradient Descent in a Bregman Distance Framework,
SIIMS(14), No. 2, 2021, pp. 814-843.
DOI Link 2107
BibRef

Sun, T., Qiao, L., Liao, Q., Li, D.,
Novel Convergence Results of Adaptive Stochastic Gradient Descents,
IP(30), 2021, pp. 1044-1056.
IEEE DOI 2012
Convergence, Training, Optimization, Task analysis, Stochastic processes, Adaptive systems, Sun, nonergodic convergence BibRef

Tirer, T.[Tom], Giryes, R.[Raja],
On the Convergence Rate of Projected Gradient Descent for a Back-Projection Based Objective,
SIIMS(14), No. 4, 2021, pp. 1504-1531.
DOI Link 2112
BibRef

Lei, Y.[Yunwen], Tang, K.[Ke],
Learning Rates for Stochastic Gradient Descent With Nonconvex Objectives,
PAMI(43), No. 12, December 2021, pp. 4505-4511.
IEEE DOI 2112
Complexity theory, Training data, Convergence, Statistics, Behavioral sciences, Computational modeling, early stopping BibRef

Xu, J.[Jie], Zhang, W.[Wei], Wang, F.[Fei],
A(DP)^2SGD: Asynchronous Decentralized Parallel Stochastic Gradient Descent With Differential Privacy,
PAMI(44), No. 11, November 2022, pp. 8036-8047.
IEEE DOI 2210
Differential privacy, Computational modeling, Servers, Training, Privacy, Stochastic processes, Data models, Distributed learning, differential privacy BibRef

Guo, S.W.[Shang-Wei], Zhang, T.W.[Tian-Wei], Yu, H.[Han], Xie, X.F.[Xiao-Fei], Ma, L.[Lei], Xiang, T.[Tao], Liu, Y.[Yang],
Byzantine-Resilient Decentralized Stochastic Gradient Descent,
CirSysVideo(32), No. 6, June 2022, pp. 4096-4106.
IEEE DOI 2206
Training, Servers, Learning systems, Distance learning, Computer aided instruction, Security, Fault tolerant systems, Byzantine fault tolerance BibRef

Wang, B.[Bao], Nguyen, T.[Tan], Sun, T.[Tao], Bertozzi, A.L.[Andrea L.], Baraniuk, R.G.[Richard G.], Osher, S.J.[Stanley J.],
Scheduled Restart Momentum for Accelerated Stochastic Gradient Descent,
SIIMS(15), No. 2, 2022, pp. 738-761.
DOI Link 2206
BibRef

Lv, X.[Xiao], Cui, W.[Wei], Liu, Y.L.[Yu-Long],
A Sharp Analysis of Covariate Adjusted Precision Matrix Estimation via Alternating Projected Gradient Descent,
SPLetters(29), No. 2022, pp. 877-881.
IEEE DOI 2204
Signal processing algorithms, Convergence, Estimation, Complexity theory, Estimation error, Linear regression, alternating gradient descent BibRef

Jin, B.[Bangti], Kereta, Z.[Zeljko],
On the Convergence of Stochastic Gradient Descent for Linear Inverse Problems in Banach Spaces,
SIIMS(16), No. 2, 2023, pp. 671-705.
DOI Link 2306
BibRef

Lazzaretti, M.[Marta], Kereta, Z.[Zeljko], Estatico, C.[Claudio], Calatroni, L.[Luca],
Stochastic Gradient Descent for Linear Inverse Problems in Variable Exponent Lebesgue Spaces,
SSVM23(457-470).
Springer DOI 2307
BibRef

Huang, F.H.[Fei-Hu], Gao, S.Q.[Shang-Qian],
Gradient Descent Ascent for Minimax Problems on Riemannian Manifolds,
PAMI(45), No. 7, July 2023, pp. 8466-8476.
IEEE DOI 2306
Manifolds, Optimization, Training, Machine learning, Complexity theory, Principal component analysis, Neural networks, stiefel manifold BibRef

Bigolin-Lanfredi, R.[Ricardo], Schroeder, J.D.[Joyce D.], Tasdizen, T.[Tolga],
Quantifying the preferential direction of the model gradient in adversarial training with projected gradient descent,
PR(139), 2023, pp. 109430.
Elsevier DOI 2304
Robustness, Robust models, Gradient direction, Gradient alignment, Deep learning, PGD, Adversarial training, GAN BibRef

Fermanian, R.[Rita], Pendu, M.L.[Mikael Le], Guillemot, C.[Christine],
PnP-ReG: Learned Regularizing Gradient for Plug-and-Play Gradient Descent,
SIIMS(16), No. 2, 2023, pp. 585-613.
DOI Link 2306
BibRef

Pasadakis, D.[Dimosthenis], Bollhöfer, M.[Matthias], Schenk, O.[Olaf],
Sparse Quadratic Approximation for Graph Learning,
PAMI(45), No. 9, September 2023, pp. 11256-11269.
IEEE DOI 2309
BibRef


Liu, R.S.[Ruo-Shi], Mao, C.Z.[Cheng-Zhi], Tendulkar, P.[Purva], Wang, H.[Hao], Vondrick, C.[Carl],
Landscape Learning for Neural Network Inversion,
ICCV23(2239-2250)
IEEE DOI 2401
BibRef

Hurault, S.[Samuel], Chambolle, A.[Antonin], Leclaire, A.[Arthur], Papadakis, N.[Nicolas],
A Relaxed Proximal Gradient Descent Algorithm for Convergent Plug-and-play with Proximal Denoiser,
SSVM23(379-392).
Springer DOI 2307
BibRef

Barbano, R.[Riccardo], Zhang, C.[Chen], Arridge, S.[Simon], Jin, B.[Bangti],
Quantifying Model Uncertainty in Inverse Problems via Bayesian Deep Gradient Descent,
ICPR21(1392-1399)
IEEE DOI 2105
Training, Uncertainty, Inverse problems, Computational modeling, Scalability, Neural networks, Reconstruction algorithms BibRef

Liu, H.K.[Hui-Kang], Wang, X.L.[Xiao-Lu], Li, J.J.[Jia-Jin], So, A.M.C.[Anthony Man-Cho],
Low-Cost Lipschitz-Independent Adaptive Importance Sampling of Stochastic Gradients,
ICPR21(2150-2157)
IEEE DOI 2105
Gradient descent. Training, Monte Carlo methods, Upper bound, Neural networks, Training data, Sampling methods BibRef

Zhuo, L., Zhang, B., Yang, L., Chen, H., Ye, Q., Doermann, D., Ji, R., Guo, G.,
Cogradient Descent for Bilinear Optimization,
CVPR20(7956-7964)
IEEE DOI 2008
Optimization, Convergence, Training, Convolutional codes, Kernel, Filtering algorithms, Machine learning BibRef

Volhejn, V.[Václav], Lampert, C.H.[Christoph H.],
Does SGD Implicitly Optimize for Smoothness?,
GCPR20(246-259).
Springer DOI 2110
stochastic gradient descent. BibRef

Kobayashi, T.[Takumi],
SCW-SGD: Stochastically Confidence-Weighted SGD,
ICIP20(1746-1750)
IEEE DOI 2011
Stochastic Gradient Descent. Uncertainty, Perturbation methods, Training, Stochastic processes, Neural networks, Optimization, Robustness, Neural Network, Stochastic weighting BibRef

Hsueh, B., Li, W., Wu, I.,
Stochastic Gradient Descent With Hyperbolic-Tangent Decay on Classification,
WACV19(435-442)
IEEE DOI 1904
condition monitoring, gradient methods, learning (artificial intelligence), neural nets, Light rail systems BibRef

Rodriguez, P.,
Accelerated Gradient Descent Method for Projections onto the L_1-Ball,
IVMSP18(1-5)
IEEE DOI 1809
Acceleration, Newton method, Optimization, Extrapolation, Electrical engineering, Indexes, Accelerated gradient descent BibRef

Larsson, M.[Måns], Arnab, A.[Anurag], Kahl, F.[Fredrik], Zheng, S.[Shuai], Torr, P.H.S.[Philip H.S.],
A Projected Gradient Descent Method for CRF Inference Allowing End-to-End Training of Arbitrary Pairwise Potentials,
EMMCVPR17(564-579).
Springer DOI 1805
BibRef

Roy, S.K., Harandi, M.,
Constrained Stochastic Gradient Descent: The Good Practice,
DICTA17(1-8)
IEEE DOI 1804
geometry, gradient methods, learning (artificial intelligence), optimisation, stochastic processes, Riemannian geometry, Symmetric matrices BibRef

Luo, Z.J.[Zhi-Jian], Liao, D.P.[Dan-Ping], Qian, Y.T.[Yun-Tao],
Bound analysis of natural gradient descent in stochastic optimization setting,
ICPR16(4166-4171)
IEEE DOI 1705
Computer science, Convergence, Extraterrestrial measurements, Mirrors, Neural networks, Optimization, Bound Analysis, Mirror Gradient, Natural Gradient, Riemannian Space, Stochastic, Optimization BibRef

Yildiz, A.[Alparslan], Akgul, Y.S.[Yusuf Sinan],
A Gradient Descent Approximation for Graph Cuts,
DAGM09(312-321).
Springer DOI 0909
BibRef

Ishikawa, H.[Hiroshi],
Higher-order gradient descent by fusion-move graph cut,
ICCV09(568-574).
IEEE DOI 0909
BibRef
And:
Higher-order clique reduction in binary graph cut,
CVPR09(2993-3000).
IEEE DOI 0906
BibRef

Chapter on Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants continues in
Bayesian Networks, Bayes Nets .


Last update:Nov 26, 2024 at 16:40:19