research
Quantum Bandits Still Had to Pay for Time
New lower bounds ruled out horizon-independent regret and a matching algorithm cut finite-action dimension dependence from quadratic to linear.
Summary
New lower bounds ruled out horizon-independent regret and a matching algorithm cut finite-action dimension dependence from quadratic to linear.
The analysis proves minimax lower bounds for quantum multi-armed and finite-action linear bandits, showing that regret cannot become independent of the time horizon in the studied oracle model. A design-based elimination algorithm then matches the finite-action linear lower bound up to polylogarithmic factors when the action set is polynomial in dimension. The result is theoretical progress inside a specified quantum-query model, not a near-term hardware speed claim.
Why it matters
New lower bounds ruled out horizon-independent regret and a matching algorithm cut finite-action dimension dependence from quadratic to linear.
Limits and context
- The analysis proves minimax lower bounds for quantum multi-armed and finite-action linear bandits, showing that regret cannot become independent of the time horizon in the studied oracle model.
- The result is theoretical progress inside a specified quantum-query model, not a near-term hardware speed claim.
Key claims
New lower bounds ruled out horizon-independent regret and a matching algorithm cut finite-action dimension dependence from quadratic to linear.
Qualification: The analysis proves minimax lower bounds for quantum multi-armed and finite-action linear bandits, showing that regret cannot become independent of the time horizon in the studied oracle model.
Evidence: source-2026-08-17-012
Sources
- arXiv preprint 2608.14319arXiv · primary research
Corrections
No corrections have been recorded for this story.