# Deep Portfolio Theory

arXiv: https://arxiv.org/abs/1605.07230 · HTML: https://mlsanity.com/paper/1605.07230/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 May 2016.

## Built on by (most cited first, 4 of 4)

- [Beyond Exponentially Fast Mixing in Average-Reward Reinforcement Learning via Multi-Level Monte Carlo Actor-Critic](https://mlsanity.com/paper/2301.12083/) (2023)
- [FinWorld: An All-in-One Open-Source Platform for End-to-End Financial AI Research and Deployment](https://mlsanity.com/paper/2508.02292/) (2025)
- [MountainLion: A Multi-Modal LLM-Based Agent System for Interpretable and Adaptive Financial Trading](https://mlsanity.com/paper/2507.20474/) (2025)
- [Meta Generative Flow Networks with Personalization for Task-Specific Adaptation](https://mlsanity.com/paper/2306.09742/) (2023)

## Abstract (arXiv)

We construct a deep portfolio theory. By building on Markowitz's classic risk-return trade-off, we develop a self-contained four-step routine of encode, calibrate, validate and verify to formulate an automated and general portfolio selection process. At the heart of our algorithm are deep hierarchical compositions of portfolios constructed in the encoding step. The calibration step then provides multivariate payouts in the form of deep hierarchical portfolios that are designed to target a variety of objective functions. The validate step trades-off the amount of regularization used in the encode and calibrate steps. The verification step uses a cross validation approach to trace out an ex post deep portfolio efficient frontier. We demonstrate all four steps of our portfolio theory numerically.