The analysis separates fine-scale comparisons from the regional information needed to allocate their samples at low regret, which separates fine-scale comparisons from the regional information needed to allocate their samples at low regret.
Abstract
Lipschitz bandits admit near-optimal regret $\widetilde O_d(T^{(d+1)/(d+2)})$ with little memory under full adaptivity, or with few batches under unrestricted memory. We characterize the minimax expected pseudo-regret over $T$ rounds with $W$ bits of memory and at most $B$ batches in dimension $d$. For every memory budget $W$, we prove a lower bound of order $T^{\frac{d+2}{d+3}} (1+(B-1)W)^{-\frac{1}{d(d+3)}}$. When $W\gtrsim_d\log(eT)$, algorithms with fixed batch boundaries attain, up to logarithmic factors, the larger of this bound and the optimal $B$-batch regret with unrestricted memory. The analysis separates fine-scale comparisons from the regional information needed to allocate their samples at low regret. Attaining $\widetilde O_d(T^{(d+1)/(d+2)})$ regret requires both $B=\Omega_d(\log\log T)$ and $(B-1)W=\widetilde{\Omega}_d(T^{d/(d+2)})$. With one bit of memory, minimax regret is $\widetilde\Theta_d(TB^{-1/(d+2)})$ under adaptive batch boundaries while $\Theta_d(T)$ under fixed boundaries.
We study multi-armed bandits (MAB) with multiple optimal arms, motivated by the fact that many practical decision making problems admit multiple correct answers. For $K$-armed bandits with $A$ optimal arms, we first provide a sharper analysis of previous sub-sampling algorithms (De Heide et al., 2021; Zhu and Nowak, 20...
Kaixuan Ji, Qi-Wei Di, Qing-Yue Zhao et al.· arXiv.org· 0 citations
A change-of-measure lower bound identifies the noise power of this logarithm for learners retaining a full-horizon optimal guarantee, under explicit conditions.
The upper bound improves the dependence on $K$ by a factor of $K^{1/4}$ and the regret smoothly recovers the $d\sqrt T$ scale once $\log K$ reaches order $d$.
Can a constant number of linear minimizations per round improve on the $T^{3/4}$ regret rate of online Frank-Wolfe on general convex sets? Weibel et al. conjectured that fixed-coefficient methods cannot. We prove their conjecture and extend the lower bound to every deterministic learner in an oracle-only model. The lea...
The results resolve the open question raised in the literature concerning the sharp arm-dependent regret--instability frontier and develop a new offline top-prefix representation that removes path dependence from online decisions.
A learner probes at most $k$ of $n$ arms each round, receives the maximum of their rewards in $[0,1]$, and competes with the best fixed arm. When does the probing advantage pay for learning? We determine two minimax laws. Under independent stochastic rewards with winner feedback (the maximum and a winning label), or on...
Yong-Jie Guan· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 6, 2026
A machine-learning approach called CheMeleon provides a practical way to develop new drugs or other molecules with much less detailed, expensive experimentation.
Learn how Google DeepMind and GovTech Singapore uses lightweight on-device Gemma models to intercept conversational scams in private chats with zero cloud data egress.