Paper: arXiv 2501.06701

Authors: Duy Khanh Lam

Abstract

This paper investigates the investment problem of constructing an optimal no-short sequential portfolio strategy in a market with a latent dependence structure between asset prices and partly unobservable side information, which is often high-dimensional. The results demonstrate that a dynamic strategy, which forms a portfolio based on perfect knowledge of the dependence structure and full market information over time, may not grow at a higher rate infinitely often than a constant strategy, which remains invariant over time. Specifically, if the market is stationary, implying that the dependence structure is statistically stable, the growth rate of an optimal dynamic strategy, utilizing the maximum capacity of the entire market information, almost surely decays over time into an equilibrium state, asymptotically converging to the growth rate of a constant strategy. Technically, this work reassesses the common belief that a constant strategy only attains the optimal limiting growth rate of dynamic strategies when the market process is identically and independently distributed. By analyzing the dynamic log-optimal portfolio strategy as the optimal benchmark in a stationary market with side information, we show that a random optimal constant strategy almost surely exists, even when a limiting growth rate for the dynamic strategy does not. Consequently, two approaches to learning algorithms for portfolio construction are discussed, demonstrating the safety of removing side information from the learning process while still guaranteeing an asymptotic growth rate comparable to that of the optimal dynamic strategy.

Complexity vs Empirical Score

  • Math Complexity: 8.5/10
  • Empirical Rigor: 2.5/10
  • Quadrant: Lab Rats — high math complexity, limited empirical testing

Why this score: The paper relies heavily on measure theory, stochastic processes, and asymptotic analysis of growth rates, scoring high on math complexity. However, it lacks empirical elements such as backtesting, datasets, or implementation details, focusing instead on theoretical optimality proofs, resulting in low empirical rigor.

Research Flowchart

  flowchart TD
  A["Research Goal: <br>Sequential Portfolio Selection under Latent Side Information"] --> B["Key Methodology: <br>Analysis of Dynamic vs. Constant Strategies in Stationary Markets"]
  B --> C{"Data/Input: <br>High-dimensional Side Information & Latent Dependence Structure"}
  C --> D["Computational Process: <br>Dynamic Programming & Asymptotic Convergence Analysis"]
  D --> E["Key Finding 1: <br>Dynamic Strategy Growth Rate <br>Decays to Equilibrium over Time"]
  D --> F["Key Finding 2: <br>Random Optimal Constant Strategy <br>Exists Almost Surely"]
  E --> G["Outcome: <br>Safe Removal of Side Information in Learning Algorithms"]
  F --> G

Evidence Card

What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card

Proposes

The paper proposes learning algorithms that rely only on past asset prices, without side information or knowledge of latent dependence structures, and shows they achieve asymptotic growth comparable to the optimal dynamic log‑optimal strategy.

Source sentence
Based on our findings, a class of learning algorithms that relies solely on past assets’ prices, without any prior knowledge of latent dependence structures or side information, is shown to be optimal and comparable to another innovative learning algorithm that is more sophisticated and leverages complete market knowledge.

Assumes 6

  • The market is stationary, meaning the latent dependence structure is statistically stable over time. market
    Source sentence
    Specifically, if the market is stationary, implying that the dependence structure is statistically stable, the growth rate of an optimal dynamic strategy, utilizing the maximum capacity of the entire market information, almost surely decays over time into an equilibrium state, asymptotically converging to the growth rate of a constant strategy.
  • The latent dependence structure remains unchanged over time. model
    Source sentence
    Generally, if the latent dependence structure remains unchanged over time, a random optimal constant strategy could exist.
  • Portfolios are constructed without commission fees for arbitrary fractions. execution
    Source sentence
    With the above settings, let the initial capital S0 �b0  =: S0 = 1 by convention for any strategy, and assume that the portfolios are constructed without commission fees for arbitrary fractions.
  • No‑trash assets condition: the ratio of maximum to minimum asset returns is bounded away from zero. market
    Source sentence
    A market is said not to have trash assets if max1≤i≤m Xn,i/min1≤i≤m Xn,i ≥c ≫0 for all n almost surely.
Show 2 more
  • Results on convergence of the log‑optimal strategy can be proved without the no‑trash assets assumption, using ergodic theorem. statistical
    Source sentence
    It is important to highlight that the almost sure convergence of the log-optimal strategy in Theorem 2 can be proven without the assumption of no-trash assets, by simply using Birkhoff’s ergodic theorem, as in the original proof by Algoet and Cover (1988).
  • The analysis assumes positive real‑valued asset returns and real‑valued side information defined on a canonical probability space. model
    Source sentence
    Assume that the assets’ returns and side information are realized with respect to a pairwise random process  Xn,Yn ∞ n=1 that is jointly defined on the canonical probability space �Ω,F,P  , i.e., �Xn,Yn �ω  = �Xn �ω  ,Yn �ω  for all n, where ω ∈Ω. Specifically, the positive real-valued vector Xn := �Xn,1,...,Xn,m  ∈Rm ++ represents the positive returns of the assets at time n, which is defined as the ratio of

Data

No dataset named in the text.

Costs

Unclear - sources disagree The platform classifier and the paper-text extraction give different answers, so no value is asserted.

Platform classifier: Not applicable

Paper text extraction: Not modeled

Source sentence (the authors' words)
With the above settings, let the initial capital S0 �b0  =: S0 = 1 by convention for any strategy, and assume that the portfolios are constructed without commission fees for arbitrary fractions.

Finds 5

  • The best dynamic strategy cannot infinitely often outperform an optimal constant strategy in growth rate or expected growth rate as time goes to infinity. theoretical
    Source sentence
    We demonstrate that the best dynamic strategy, defined as a sequence of portfolios determined using the complete history of market observations over time, including even the unobservable features, cannot infinitely often outperform an optimal constant strategy, represented as a unique and random portfolio, in terms of both growth rate and expected growth rate as time progresses to infinity.
  • A random optimal constant strategy exists almost surely and can asymptotically match the growth rate of the log‑optimal dynamic strategy under a stationary market with side information. theoretical
    Source sentence
    By analyzing the dynamic log-optimal portfolio strategy as the optimal benchmark in a stationary market with side information, we show that a random optimal constant strategy almost surely exists, even when a limiting growth rate for the dynamic strategy does not. However, we show that a random optimal constant strategy can almost surely asymp-totically approach the optimal growth rate of the log-optimal strategy
  • Under stationarity, the advantage of utilizing the full market information decays over time, leading to equilibrium with the constant strategy’s growth rate. theoretical
    Source sentence
    It implies that under the stationarity condition, the ad-vantages of utilizing the maximum capacity of market information will almost surely decay over time into an equilibrium state.
  • An empirical distribution‑based learning algorithm, using only past prices, achieves asymptotic growth comparable to the universal strategy when an optimal constant strategy exists. theoretical
    Source sentence
    Despite the algorithm’s simplicity, such an empirical strategy, as proposed below, is comparable with the Universal strategy in general markets, as long as there exists an optimal constant strategy that is comparable to the log-optimal one, as demonstrated in Theorem 3. In comparison, Theorem 3 demonstrates the optimality of the empirical distribution-based log-optimal strategy in a more general market, without
  • The constant strategy does not require side information yet remains asymptotically optimal, contradicting conventional expectations that full information always yields better performance. theoretical
    Source sentence
    This finding implies that the constant strategy does not require knowledge of periodic side market information, yet it remains asymptotically optimal. Such a result contradicts conventional perspectives in the fields of information theory, finance, and potentially learning theory, which suggest that possessing full knowledge of market information and dependence structures should unequivocally outperform ig-norance.

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 20 related papers). Coverage is partial, so this is neither replication nor refutation.

Code

No repository by the authors found in the paper.

Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.