2 papers
cs.LG2026
Revisiting Smoothed Online Learning: Competitive Ratio, Dynamic Regret with Switching Cost, and Best of Both Worlds
Lijun Zhang, Linzhe He, Wei Jiang +1
We revisit smoothed online learning and develop algorithms with improved competitive ratios, optimal dynamic regret with switching cost, and best-of-both-worlds guarantees. Surpris…
cs.LG2026
Efficient Multinomial Logistic Bandit via Frequent Directions
Linzhe He, Yu-Jie Zhang, Sifan Yang +1
This paper studies efficient online algorithms for multinomial logistic bandits (MLogB), where the feedback distribution over outcomes follows a multinomial logistic model of…