Optimization for and by machine learning

Optimization for and by machine learning

<p>Optimization and machine learning are both extremely active research topics. In this thesis, we explore problems at the intersection of the two fields. In particular, we will develop two main ideas.</p> <p>First, optimization can be used to improve machine learning. We illustra...

Fuld beskrivelse

Bibliografiske detaljer
Hovedforfatter:	Desmaison, A
Andre forfattere:	Torr, PHS
Format:	Thesis
Sprog:	English
Udgivet:	2019
Fag:	Constrained optimization Machine learning

Lignende værker

Genetic algorithms in search, optimization, and and machine learning /
af: Goldberg, David E. (David Edward), 1953-
Udgivet: (1989)

Quasi-Newton type method via weak secant equations for unconstrained optimization
af: Lim, Keat Hee
Udgivet: (2021)

Leveraging structure for optimization in deep learning
af: Berrada, L
Udgivet: (2019)

Operator splitting methods for large convex conic programs
af: Garstka, M
Udgivet: (2021)

Efficient numerical algorithms for large-scale conic optimization
af: Chen, Y
Udgivet: (2024)

Machine learning-guided realization of full-color high-quantum-yield carbon quantum dots
af: Guo, Huazhang, et al.
Udgivet: (2024)

Machine learning : ECML-98 /
af: European Conference on Machine Learning (10th : Chemnitz, Germany : 1998), et al.
Udgivet: (1998)

Interpretable machine learning for optimizing computer system
af: Chen, Peilin
Udgivet: (2024)

Robust and stochastic receding horizon control
af: Yan, S
Udgivet: (2021)

NPE-DRL: enhancing perception constrained obstacle avoidance with non-expert policy guided reinforcement learning
af: Zhang, Yuhang, et al.
Udgivet: (2024)

Introduction to machine learning /
af: 458465 Alpaydin, Ethem
Udgivet: (2004)

Handling constrained many-objective optimization problems via problem transformation
af: Jiao, Ruwang, et al.
Udgivet: (2022)

Incorporating inductive biases into machine learning algorithms
af: Miao, N
Udgivet: (2024)

Casual and trustworthy machine learning: methods and applications
af: Gultchin, L
Udgivet: (2023)

Structural and statistical uncertainty in observational causal machine learning at scale
af: Jesson, A
Udgivet: (2023)

Exploiting prior knowledge in machine learning model design
af: Wagstaff, E
Udgivet: (2021)

Using Machine Learning to Trace Genetically Engineered DNA
Udgivet: (2023)

A Comparative Study on Optimization of Constrained Layer Damping for Vibration Control of Beams
af: Pau, G.S.H., et al.
Udgivet: (2003)

Optimization of Passive Constrained Layer Damping Treatments for Vibration Control of Cylindrical Shells
af: Zheng, H., et al.
Udgivet: (2003)

Machine learning in bioinformatics /
af: Zhang, Yan-qing
Udgivet: (2009)

Unlocking efficiency: end-to-end optimization learning for recurrent facility operational planning
af: Lin, Yun Hui, et al.
Udgivet: (2024)

Between integrals and optima: new methods for scalable machine learning
af: Maddison, C
Udgivet: (2020)

ECG classification and the "heart age" prediction using machine learning
af: Shen, Y
Udgivet: (2020)

Multimodal probabilistic reasoning for prediction and coordination problems in machine learning
af: Zand, J
Udgivet: (2021)

Machine learning for audio, image and video analysis : theory and applications /
af: Camastra, Francesco, 1960-, et al.
Udgivet: (2008)

Hybrid meta-heuristic algorithm based parameter optimization for extreme learning machines classification
af: Alade, Oyekale Abel
Udgivet: (2023)

On the adversarial robustness of Bayesian machine learning models
af: Blaas, AC
Udgivet: (2021)

Introduction to machine learning and bioinformatics /
af: Mitra, Sushmita
Udgivet: (2008)

Development of Machine Learning Algorithm for Acquiring Machining Data in Turning Process
af: Ali Al-Assadi, Hayder M. A.
Udgivet: (2004)

Towards robust machine learning with graph neural networks
af: Jaeckle, F
Udgivet: (2022)

DIRECT: a differential dynamic programming based framework for trajectory generation
af: Cao, Kun, et al.
Udgivet: (2022)

Optimal transport based simulation methods for deep probabilistic models
af: Thornton, J
Udgivet: (2023)

Continual learning for efficient machine learning
af: Chaudhry, A
Udgivet: (2020)

Topics in Bayesian machine learning for finance
af: Spears, T
Udgivet: (2024)

Towards trustworthy machine learning with kernels
af: Chau, SL
Udgivet: (2023)

Numerical optimization with applications to machine learning
af: Rontsis, N
Udgivet: (2019)

On the theory of Lipschitz continuous machine learning
af: Huang, JW
Udgivet: (2023)

Spectral machine learning
af: Granziol, D
Udgivet: (2020)

Inference and machine learning across the spatial scales in geophysics
af: Szenicer, A
Udgivet: (2021)

Two-gradient direction FXLMS : an adaptive active noise control algorithm with output constraint
af: Shi, Dong Yuan, et al.
Udgivet: (2019)