4 papers
Large and Deep Factor Models
Bryan Kelly, Boris Kuznetsov, Semyon Malamud +1
We show that a deep neural network (DNN) trained to construct a stochastic discount factor (SDF) admits an additive decomposition separating nonlinear characteristic discovery from…
Scaling Point-in-Time Language Models
Bryan Kelly, Semyon Malamud, Johannes Schwab +1
Large language models trained on unrestricted internet corpora inevitably embed information from the future, introducing lookahead bias that compromises the validity of backtests a…
Limits To (Machine) Learning
Zhimin Chen, Bryan Kelly, Semyon Malamud
Machine learning (ML) methods are highly flexible, but their ability to approximate the true data-generating process is fundamentally constrained by finite samples. We characterize…
Training NTK to Generalize with KARE
Johannes Schwab, Bryan Kelly, Semyon Malamud +1
The performance of the data-dependent neural tangent kernel (NTK; Jacot et al. (2018)) associated with a trained deep neural network (DNN) often matches or exceeds that of the full…