We investigate the economic consequences of statistical learning for arbitrage pricing in a high dimensional setting. Arbitrageurs learn about alphas from historical data. When alphas are weak and rare, estimation errors hinder arbitrageurs—even those employing optimal machine learning techniques—from fully exploiting all true pricing errors. This statistical limit to arbitrage widens the equilibrium bounds of alphas beyond what traditional arbitrage pricing theory predicts, leading to a significant divergence between the feasible Sharpe ratio achievable by arbitrageurs and the unattainable theoretical maximum under perfect knowledge of alphas.

More on this topic

BFI Working Paper·Nov 2, 2026

Risk and Return in Government Bonds

Matteo Leombroni, Carolin Pflueger, and Adi Sunderam
Topics: Financial Markets, Monetary Policy
BFI Working Paper·Nov 2, 2026

Green Tastes, Beliefs, and Portfolios: Evidence from Synthetic Investors

Xindi He and Lubos Pastor
Topics: Energy & Environment, Financial Markets
BFI Working Paper·Oct 21, 2026

Venture Capital and Customer Capital

Martin Aragoneses, Young Soo Jang, and Amir Sufi
Topics: Financial Markets