Filters








1,289 Hits in 3.2 sec

Adaptive Configuration Oracle for Online Portfolio Selection Methods [article]

Favour M. Nyikosa, Michael A. Osborne, Stephen J. Roberts
2019 arXiv   pre-print
We then propose an oracle based on adaptive Bayesian optimization for automatically and adaptively configuring online portfolio selection methods.  ...  One fundamental problem is online portfolio selection, the goal of which is to exploit this data to sequentially select portfolios of assets to achieve positive investment outcomes while managing risks  ...  We then propose a mechanism for using adaptive Bayesian optimization for tuning the parameters of online portfolio selection algorithms.  ... 
arXiv:1908.08258v1 fatcat:synx3iekf5do3ccijb3jj7idma

To personalize or not

Weinan Zhang, Jun Wang, Bowei Chen, Xiaoxue Zhao
2013 Proceedings of the 7th ACM conference on Recommender systems - RecSys '13  
From a risk management and portfolio retrieval perspective, there is no difference between the popularity-based and the personalized ranking as both of the recommendation outputs can be represented as  ...  Item Reranking via Portfolio Optimization We present the performance for the two portfolio-based reranking algorithms (Opt and Greedy) based on the two base recommendation algorithms (BPR and POP).  ...  Item Portfolio Optimization In this section, we focus on the item portfolio weighting optimization analysis.  ... 
doi:10.1145/2507157.2507167 dblp:conf/recsys/ZhangWCZ13 fatcat:be33yyzfqrfbffmv3oqdkech44

Multi-Model Generative Adversarial Network Hybrid Prediction Algorithm (MMGAN-HPA) for Stock Market Prices Prediction

Subba rao polamuri, Kudipudi Srinivas, A. Krishna Mohan
2021 Journal of King Saud University: Computer and Information Sciences  
In this paper, overcome this problem with reinforcement learning and Bayesian optimization. A deep learning framework based on GAN, named Stock-GAN, is implemented with generator and discriminator.  ...  In the financial domain, it is widely used for stock market prediction, trade execution strategies and portfolio optimization. Stock market prediction is a very significant use case in this domain.  ...  In order to tune the hyperparameters dynamically, Stock-GAN incorporates reinforcement learning framework along with Bayesian optimization technique.  ... 
doi:10.1016/j.jksuci.2021.07.001 fatcat:rua3fjhdhbewnmprqthu3y6rpe

Bayesian Optimization for Adaptive MCMC [article]

Nimalan Mahendran, Ziyu Wang, Firas Hamze, Nando de Freitas
2011 arXiv   pre-print
This paper proposes a new randomized strategy for adaptive MCMC using Bayesian optimization.  ...  It proposes the use of Bayesian optimization (Brochu et al., 2009) to tune the parameters of the Markov chain.  ...  Here, we show that this objective can be easily optimized with Bayesian optimization.  ... 
arXiv:1110.6497v1 fatcat:swkhgdjzjzbblkzb7z4poblwzy

A sequential Monte Carlo approach to Thompson sampling for Bayesian optimization [article]

Hildo Bijl, Thomas B. Schön, Jan-Willem van Wingerden, Michel Verhaegen
2017 arXiv   pre-print
Bayesian optimization through Gaussian process regression is an effective method of optimizing an unknown function for which every measurement is expensive.  ...  All this is done without requiring the optimization of a nonlinear acquisition function.  ...  Such optimization methods are suitable for tuning the parameters of systems with large amounts of uncertainty in an online data-based way.  ... 
arXiv:1604.00169v3 fatcat:tivcr6grvzg4hidfbsxlhk3fde

Adaptive MCMC with Bayesian Optimization

Nimalan Mahendran, Ziyu Wang, Firas Hamze, Nando de Freitas
2012 Journal of machine learning research  
This paper proposes a new randomized strategy for adaptive MCMC using Bayesian optimization.  ...  The proposed approach, Bayesian-optimized MCMC, has a few advantages over adaptive methods based on stochastic approximation.  ...  It proposes the use of Bayesian optimization (Brochu et al., 2009) to tune the parameters of the Markov chain.  ... 
dblp:journals/jmlr/MahendranWHF12 fatcat:vwgkjotsenar3djevdlavbwchm

AI in Finance: Challenges, Techniques and Opportunities [article]

Longbing Cao
2021 arXiv   pre-print
Rule-based modeling and controlled experiments; simulation; self-organizing mechanisms; mechanism testing; etc.  ...  Limited to evolutionary mechanisms; bias in local/global optimal and extremum; configuration and parameter tuning; etc.  ... 
arXiv:2107.09051v1 fatcat:g62cz4dqt5dcrbckn4lbveat3u

The Present and Future of Financial Risk Management

Carol Alexander
2004 Social Science Research Network  
We argue that consideration of the model risk arising from crude aggregation rules and inadequate data could lead to a new class of reduced-form Bayesian risk assessment models.  ...  We explain how such a framework could also provide the essential links between risk control, risk assessments, and the optimal allocation of resources.  ...  Fine tuning of market and credit VaR estimates of individual instruments or small portfolios may impact the relative risk capital allocations within a particular activity, but since very crude aggregation  ... 
doi:10.2139/ssrn.478802 fatcat:2gxwyneio5eingnloombslth5y

The Present and Future of Financial Risk Management

C. Alexander
2005 Journal of Financial Econometrics  
We argue that consideration of the model risk arising from crude aggregation rules and inadequate data could lead to a new class of reduced-form Bayesian risk assessment models.  ...  We explain how such a framework could also provide the essential links between risk control, risk assessments, and the optimal allocation of resources.  ...  Fine tuning of market and credit VaR estimates of individual instruments or small portfolios may impact the relative risk capital allocations within a particular activity, but since very crude aggregation  ... 
doi:10.1093/jjfinec/nbi003 fatcat:ino54isow5gmpamvar5ajat2ny

Dealing with Drift Uncertainty: A Bayesian Learning Approach

Carmine De Franco, Johann Nicolle, Huyên Pham
2019 Risks  
To illustrate the value added of using the optimal Bayesian learning strategy, we compare it with an optimal nonlearning strategy that keeps the drift constant at all times.  ...  Building on filtering techniques and learning methods, we use a Bayesian learning approach to solve the Markowitz problem and provide a simple and practical procedure to implement optimal strategy.  ...  The fine-tuning parameter unc is a simple way to increase the uncertainty in the initial guess b 0 . The workflow above and Table 2 represent the Base Case.  ... 
doi:10.3390/risks7010005 fatcat:fpqraaummvaz3ilermgkn46ieq

Learning Convex Optimization Control Policies [article]

Akshay Agrawal, Shane Barratt, Stephen Boyd, Bartolomeo Stellato
2019 arXiv   pre-print
These types of control policies are tuned by varying the parameters in the optimization problem, such as the LQR weights, to obtain good performance, judged by application-specific metrics.  ...  Tuning is often done by hand, or by simple methods such as a crude grid search.  ...  Learning optimization-based policies. Other work has considered tuning optimizationbased control policies.  ... 
arXiv:1912.09529v1 fatcat:acjmzbzozze5bpvjkrxqmmv4mm

Hyper-Parameter Optimization: A Review of Algorithms and Applications [article]

Tong Yu, Hong Zhu
2020 arXiv   pre-print
To lower the technical thresholds for common users, automated hyper-parameter optimization (HPO) has become a popular topic in both academic and industrial areas.  ...  Then, the research focuses on major optimization algorithms and their applicability, covering their efficiency and accuracy especially for deep learning networks.  ...  Bayesian Optimization and Its Variants Bayesian optimization (BO) is a traditional algorithm with decades of history.  ... 
arXiv:2003.05689v1 fatcat:jjbt54gb2nagdegdjf5lj2pyvi

Can we imitate the principal investor's behavior to learn option price? [article]

Xin Jin
2022 arXiv   pre-print
Eventually the optimal option price is learned by reinforcement learning to maximize the cumulative risk-adjusted return of a dynamically hedged portfolio over simulated price paths.  ...  This paper presents a framework of imitating the principal investor's behavior for optimal pricing and hedging options.  ...  There are two fine-tuned hyperparameters σ and λ for optimizing our model's performance.  ... 
arXiv:2105.11376v2 fatcat:ky6r72yiqnc35jyv7dhfaabbze

A Personalized Learning Service Compatible with Moodle E-Learning Management System

Yi-Chun Chang, Jian-Wei Li, De-Yao Huang
2022 Applied Sciences  
[22] developed a Moodle plugin, Middle, to infer personalized instruction for each student based on a Bayesian network model. Jeong et al.  ...  [12] proposed a personalized e-course composition approach based on particle swarm optimization, which considers the requirements for meeting learning objectives, required concepts, the difficulty of  ... 
doi:10.3390/app12073562 fatcat:uducqbvo6vc5xggvebdnb35n44

Theory of Randomized Optimization Heuristics (Dagstuhl Seminar 17191)

Carola Doerr, Christian Igel, Lothar Thiele, Xin Yao, Marc Herbstritt
2017 Dagstuhl Reports  
Topics that have been intensively discussed at the seminar include population-based heuristics, constrained optimization, non-static parameter choices as well as connections to research in machine learning  ...  This report summarizes the talks, breakout sessions, and discussions at the Dagstuhl Seminar 17191 on Theory of Randomized Optimization Heuristics, held during the week from May 08 until May 12, 2017,  ...  Bayesian optimization.  ... 
doi:10.4230/dagrep.7.5.22 dblp:journals/dagstuhl-reports/DoerrIT017 fatcat:guma4eanyne6vlkwexkevs4v6i
« Previous Showing results 1 — 15 out of 1,289 results