2 papers
cs.LG2026
Mitigating Bias in Low-SNR Financial Reinforcement Learning via Quantum Representations
Zeyu Liu, Xuanzhi Feng, Sing Kwong Lai +6
The financial market is a typical low signal-to-noise ratio (SNR) setting, which often destabilizes off-policy maximum-entropy methods like Soft Actor-Critic (SAC). Specifically, n…
math.OC2026
The Dual Averaging Power-Prox Method with Application to Heavy-Tail Incremental Gradient
Yuan Gao, Jeremy Rack, Sebastian U. Stich
We study finite-sum composite optimization under two departures from classical stochastic gradient descent theory that are central in practice: incremental gradient access and heav…