Zeroth-Order Optimization
A class of algorithmic frameworks that optimize an objective function using only function-value queries, without relying on gradients. It is commonly used for black-box parameter tuning, policy search in reinforcement learning, and simulation-based optimization where gradients are unavailable.
Timeline (last 90 days)
In zeroth-order optimization, converting function values into gradient estimates via finite differences or Gaussian smoothing and then applying first-order methods usually incurs a cost linear in the dimension d.
Advice for practitioners: do not expect to eliminate the linear dependence on dimension d in zeroth-order optimization through smarter query strategies or sample reuse.
All Facts (2)
In zeroth-order optimization, converting function values into gradient estimates via finite differences or Gaussian smoothing and then applying first-order methods usually incurs a cost linear in the dimension d.
50%UnverifiedAdvice for practitioners: do not expect to eliminate the linear dependence on dimension d in zeroth-order optimization through smarter query strategies or sample reuse.
50%