Machine learning for phenomenological applications

机器学习技术的普及程度大幅提高，其应用已经渗透到许多科学，商业和社会领域的广泛应用中。新技术、算法、软件和专用硬件的快速发展创造了许多新的机会。虽然机器学习最初在粒子物理数据分析中发挥了至关重要的作用，但最近，ML算法在粒子物理的更多理论方面找到了大量应用。博士项目将涉及为复杂的高阶计算开发可靠的仿真器，ML算法在蒙特卡罗积分优化中的应用，或现代密度估计技术在粒子物理交叉中的应用路段

Machine Learning technique have seen a massive rise in popularity and their use has permeated a very wide range of applications in many scientific, commercial and societal fields. The rapid development of new techniques, algorithms, software and dedicated hardware has created a multitude of new opportunities. While Machine learning has played a crucial role initially in the analysis of particle physics data, more recently, ML algorithms have found a multitude of applications in more theoretical aspects of particle physics.The PhD project will involve the development of reliable emulators for complicated higher order calculations, applications of ML algorithms to Monte Carlo integration optimization or the application of modern density estimation techniques to particle physics cross sections.