From the 1 of 5 linked papers with an AI index.
5 papers
Sharp Optimal Algorithm for Derivative-Free Stochastic Convex Optimization in One Dimension
Alexandra Carpentier, Chloé Rouyer, Alexandre Tsybakov +1
The paper introduces a computationally efficient algorithm for one‑dimensional stochastic convex optimization using only noisy function evaluations, achieving the optimal O(1/√T) c…
Gradient-free stochastic optimization of derivatives under strong convexity
Arya Akhavan, Sirine Louati, Alexandre B. Tsybakov
We consider the problem of minimizing the -th order partial derivative of an unknown function along a fixed coordinate direction , based on noisy queri…
Minimax estimation of functionals in sparse vector model with correlated observations
Yuhao Wang, Pengkun Yang, Alexandre B. Tsybakov
We consider the observations of an unknown -sparse vector corrupted by Gaussian noise with zero mean and unknown covariance matrix . We propos…
A conversion theorem and minimax optimality for continuum contextual bandits
Arya Akhavan, Karim Lounici, Massimiliano Pontil +1
We study the contextual continuum bandits problem, where the learner sequentially receives a side information vector and has to choose an action in a convex set, minimizing a funct…
Gradient-free stochastic optimization for additive models
Arya Akhavan, Alexandre B. Tsybakov
We address the problem of zero-order optimization from noisy observations for an objective function satisfying the Polyak-Åojasiewicz or the strong convexity condition. Additional…