Fri, 24 Jan 2020

12:00 - 13:00
L4

Tensor methods in optimization

Geovani Grapiglia
(Universidade Federal do Paraná)
Abstract


In this talk we present p-order methods for unconstrained minimization of convex functions that are p-times differentiable with Hölder continuous p-th derivatives. We establish worst-case complexity bounds for methods with and without acceleration. Some of these methods are "universal", that is, they do not require prior knowledge of the constants that define the smoothness level of the objective function. A lower complexity bound for this problem class is also obtained. This is a joint work with Yurii Nesterov (Université Catholique de Louvain).
 

Limit theorems for sequential MCMC methods
Finke, A Doucet, A Johansen, A Advances in Applied Probability volume 52 issue 2 377-403 (15 Jul 2020)
Particle filtering in digital communications
Punskaya, E Doucet, A Fitzgerald, W The Cable and Telecommunications Professionals' Reference: PSTN, IP and Cellular Networks, and Mathematical Techniques 417-434 (01 Jan 2012)
Ready-made cellular plugs heal skin wounds
Coles, M Buckley, C Nature volume 576 issue 7786 215-216 (27 Nov 2019)
Certified reinforcement learning with logic guidance
Hasanbeig, H Kroening, D Abate, A Artificial Intelligence volume 322 103949 (Sep 2023)
DeepSynth: Program Synthesis for Automatic Task Segmentation in Deep Reinforcement Learning.
Hasanbeig, M Jeppu, N Abate, A Melham, T Kroening, D volume abs/1911.10244 (01 Jan 2019)
Modular Deep Reinforcement Learning with Temporal Logic Specifications.
Yuan, L Hasanbeig, M Abate, A Kroening, D CoRR volume abs/1909.11591 (01 Jan 2019)
Efficiency through Uncertainty: Scalable Formal Synthesis for Stochastic Hybrid Systems.
Cauchi, N Laurenti, L Lahijanian, M Abate, A Kwiatkowska, M Cardelli, L CoRR volume abs/1901.01576 (01 Jan 2019)
Subscribe to