剑桥大学PhD position in Nose-to-tail emulation with nested sampling for online decision making申请条件要求-申请方
主办方
剑桥大学
PhD直招介绍
About the Project
AI_CDT_DecisionMaking
Details
Modern scientific analyses and technological advancements increasingly rely on complex simulations and models, often requiring significant computational resources. This project explores the cutting-edge field of neural emulation, where computationally expensive models are replaced by fast, accurate approximations, enabling real-time decision-making and accelerating scientific discovery.
This PhD project focuses on a novel approach to emulation leveraging the unique strengths of nested sampling, a Bayesian algorithm renowned for its efficiency in exploring high-dimensional parameter spaces. Recent work has demonstrated that nested sampling provides targeted training data for emulators, resulting in superior performance and wider applicability compared to traditional methods.
**Key research objectives:**
1. **Emulator Development with Nested Sampling:** Building on the promising results demonstrated by the BAMBI algorithm, we will develop and refine novel emulation techniques utilizing nested sampling. This will involve exploring different emulator architectures, training strategies, and uncertainty quantification methods.
2. **Cosmological Applications:** We will apply these advanced emulators to accelerate cosmological analyses, enabling rapid exploration of cosmological models and efficient inference from large datasets like those from the upcoming Legacy Survey of Space and Time (LSST).
3. **Real-Time Decision Making:** Extending beyond cosmology, we will adapt these emulation techniques for real-time decision-making in complex systems. This will involve exploring applications in areas such as:
* **Adversarial Machine Learning:** Developing emulators for rapid prediction and response in adversarial scenarios.
* **Nested Active Learning:** Using emulators to efficiently guide data acquisition in active learning frameworks.
4. **Exploring Novel Emulation Architectures:** We will investigate the potential of using nested sampling itself to train Bayesian neural networks, potentially leading to more robust and uncertainty-aware emulators.
**Collaboration and Impact:**
This project will be conducted within the Cambridge astrophysics group, a leading center for research in nested sampling, machine learning, and cosmology. There will be opportunities to collaborate with the group's spin-out company, PolyChord Ltd., applying these techniques to industrial challenges, such as electric vehicle battery design. The project also intersects with the group's ongoing ERC research program in simulation-based inference and collaborations with the GAMBIT particle physics collaboration.
This project will result in novel emulation techniques with broad applicability across various scientific and technological domains. By enabling real-time decision-making and accelerating computationally demanding analyses, this research will contribute to advancements in cosmology, machine learning, and beyond.
Equality, diversity and inclusion is fundamental to the success of The University of Manchester, and is at the heart of all of our activities. We know that diversity strengthens our research community, leading to enhanced research creativity, productivity and quality, and societal and economic impact. (Equality, diversity and inclusion | The University of Manchester( https://www.manchester.ac.uk/connect/jobs/equality-diversity-inclusion/ )
We actively encourage applicants from diverse career paths and backgrounds and from all sections of the community, regardless of age, disability, ethnicity, gender, gender expression, sexual orientation and transgender status.
We also support applications from those returning from a career break or other roles. We are dedicated to supporting work-life balance and offer flexible working arrangements to accommodate individual needs. Our selection process is free from bias, and we are committed to ensuring fair and equal opportunities for all applicants.
剑桥大学 PhD position in Nose-to-tail emulation with nested sampling for online decision making项目有没有奖学金，是不是全奖Phd招生，下面我们一起看一下【大学名称】Phd的奖学金资助情况
项目资助情况
This is a fully funded AI UKRI CDT 4 year program; Home tuition fees will be provided, along with a tax-free stipend (subject to individual circumstances), set at the UKRI rate (e.g. £19,237 for 2024/25) . The start date is September 2025.
Project based in University of Cambridge
剑桥大学Phd申请条件和要求都有哪些？PhD position in Nose-to-tail emulation with nested sampling for online decision making项目是不是全奖？有没有奖学金？下面我们一起看一下剑桥大学申请Phd直招需要具备哪些条件和要求，以及托福、雅思语言成绩要到多少才能申请。
申请要求
Student Desirable Background:
Physics or Engineering or Computer Science
报名方式
申请链接
联系人
邮箱：aidecisionscdt@manchester.ac.uk
相关资源
扫描二维码
下载申请方APP
下载申请方APP
扫描二维码
下载申请方APP