Partial Index Tracking: A Meta-Learning Approach

Yongxin Yang, Timothy M Hospedales

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Partial index tracking aims to cost effectively replicate the performance of a benchmark index by using a small number of assets. It is usually formulated as a regression problem, but solving it subject to real-world constraints is non-trivial. For example, the common L1 regularised model for sparse regression (i.e., LASSO) is not compatible with those constraints. In this work, we meta-learn a sparse asset selection and weighting strategy that subsequently enables effective partial index tracking by quadratic programming. In particular, we adopt an element-wise L1 norm for sparse regularisation, and meta-learn the weight for each L1 term. Rather than meta-learning a fixed set of hyper-parameters, we meta-learn an inductive predictor for them based on market history, which allows generalisation over time, and even across markets. Experiments are conducted on four indices from different countries, and the empirical results demonstrate the superiority of our method over other baselines. The code is released at
Original languageEnglish
Title of host publicationSecond Conference on Lifelong Learning Agents - CoLLAs 2023
PublisherMIT Press
Number of pages22
Publication statusPublished - 20 Nov 2023
EventSecond Conference on Lifelong Learning Agents
- Montreal, Canada
Duration: 22 Aug 202325 Aug 2023
Conference number: 2

Publication series

NameProceedings of Machine Learning Research
PublisherMIT Press
ISSN (Electronic)2640-3498


ConferenceSecond Conference on Lifelong Learning Agents
Abbreviated titleCoLLAs 2023
Internet address


Dive into the research topics of 'Partial Index Tracking: A Meta-Learning Approach'. Together they form a unique fingerprint.

Cite this