On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

6 results for “Tsallis-INF”

A Best-of-Both-Worlds Proof for Tsallis-INF without Fenchel Conjugatescs.LG

Simplified proof for Tsallis-INF algorithm without conjugate functions.

problem Deriving a best-of-both-worlds guarantee for Tsallis-INF.

method Modern tools from online convex optimization, avoiding conjugate functions.

result A slimmer proof with simplified constants.

Tsallis-INF best-of-both-worlds online convex optimization conjugate functions slimmer proof

2025-11-14abs ↗pdf ↗

Improved Analysis of the Tsallis-INF Algorithm in Stochastically Constrained Adversarial Bandits and Stochastic Bandits with Adversarial Corruptionscs.LG

Improved regret bounds for Tsallis-INF in adversarial bandits and corruptions.

problem Adversarial bandits and corruptions in multiarmed bandit problems.

method Improved regret bounds for Tsallis-INF algorithm.

result Achieves $\mathcal{O}\left(\left(\sum_{i eq i^*} \frac{1}{Δ_i} ight)\log_+\left(\frac{(K-1)T}{\left(\sum_{i eq i^*} \frac{1}{Δ_i} ight)^2} ight)+\sqrt{C\left(\sum_{i eq i^*}\frac{1}{Δ_i} ight)\log_+\left(\frac{(K-1)T}{C\sum_{i eq i^*}\frac{1}{Δ_i}} ight)} ight)$ regret bound.

Tsallis-INF regret bounds adversarial bandits stochastic corruptions multiarmed bandits

2021-03-23abs ↗pdf ↗

LC-Tsallis-INF: Generalized Best-of-Both-Worlds Linear Contextual Banditscs.LG

Develops a Best-of-Both-Worlds algorithm for linear contextual bandits with Tsallis entropy.

problem Linear contextual bandits with i.i.d. contexts.

method Follow-The-Regularized-Leader (FTRL) with Tsallis entropy.

result Achieves $O\left(\log(T)^{\frac{1+β}{2+β}}T^{\frac{1}{2+β}} ight)$ regret under margin condition.

linear contextual bandits Tsallis entropy Follow-The-Regularized-Leader Best-of-Both-Worlds regret analysis

2024-03-05abs ↗pdf ↗

An Algorithm for Stochastic and Adversarial Bandits with Switching Costscs.LG

Algorithm for bandits with switching costs achieves optimal regret bounds.

problem Optimal regret bounds for stochastic and adversarial bandits with switching costs.

method Adaptation of Tsallis-INF algorithm with no prior knowledge of regime or time horizon.

result Achieves minimax optimal regret bounds in various settings.

bandits adversarial stochastic switching costs regret

2021-02-19abs ↗pdf ↗

Hierarchical Adversarial Bandits for Online Configuration Optimizationcs.LG

ABoB optimizes online configuration tuning by clustering parameters and accelerating learning.

problem Online optimization in large, dynamic parameter spaces.

method Hierarchical adversarial bandit framework.

result Significant performance gains in adversarial metric scenarios.

Adversarial Bandits Configuration Optimization Hierarchical Learning Metric Spaces Online Systems

2025-05-25abs ↗pdf ↗

Tsallis-INF: An Optimal Algorithm for Stochastic and Adversarial Banditscs.LG

We derive an algorithm that achieves the optimal (within constants) pseudo-regret in both adversarial and stochastic multi-armed bandits without prior knowledge of the regime and time horizon. The algorithm is based on online mirror descent (OMD) with Tsallis entropy regularization with power $α=1/2$ and reduced-varian…

2018-07-19abs ↗pdf ↗