| Date | Speaker | Title |
|---|---|---|
| 2024-09-09 | Serdar Yüksel | Stochastic Control
with Partial Information |
| 2024-09-16 | Yunus Emre Demirci | Refined bounds on near
optimality of finite window policies in POMDPs |
| 2024-09-23 | Curtis McDonald (Yale Univ.) |
Log Concave Coupling for Rapid Bayesian Neural
Network Sampling |
| 2024-10-01 |
Omar Mrani-Zentar |
Decentralized Stochastic Control in Standard Borel
Spaces: Centralized MDP Reductions and Near Optimality
of Finite Window Local Agent Information |
| 2024-10-07 |
Omar Mrani-Zentar | Decentralized Stochastic Control in Standard Borel Spaces: Centralized MDP Reductions and Near Optimality of Finite Window Local Agent Information |
| 2024-10-21 |
Connor Braun |
Synthesis of Decentralized Stochastic Control Models
for Neuronal Networks |
| 2024-10-28 |
Yunus Emre Demirci | Application of the Birkhoff-Hopf
Contraction Theorem: Stability of Nonlinear
Filters |
| 2024-11-05 |
Omar Mrani-Zentar |
Data-Driven Non-Parametric Model
Learning and Adaptive Control of MDPs with Borel
spaces: Identifiability and Near Optimal Design |
| 2024-11-11 |
Sinan Gezici (Bilkent Univ.) |
Optimal Decision Rules for Hypothesis
Testing Problems and Benefits of Detector
Randomization |
| 2024-11-18 |
Thomas Emo |
Optimal Zero Delay Coding of Markov
Sources and Reinforcement Learning for Near Optimality |
| 2024-11-25 | Sinan Gezici (Bilkent Univ.) | Prospect Theory based Hypothesis
Testing and Optimal Decision Rules under General
Criteria Involving Error Probabilities |
| 2025-01-17 |
Omar Mrani-Zentar | Topologies on Kernels, their
Approximations and Learning, and Optimal Adaptive
Control |
| 2025-01-31 |
Osman Biçer |
Finite Model Approximations in Standard
Borel MDPs via Non-Uniform Quantization: Continuity of
Discounted Cost in Policy and Implications for Error
Analysis |
| 2025-02-06 |
Thomas Emo |
Optimality of Stationary Policies for
Zero Delay Coding under Infinite Horizon Average Cost
Criteria |
| 2025-02-13 |
Connor Braun |
Introduction to Mean Field Games and
their Graphon Generalizations |
| 2025-02-27 |
Sina Sanjari |
Introduction to Generative Learning |
| 2025-03-07 |
Yunus Emre Demirci |
Robustness to Incorrect Models in
Partially Observable Markov Decision Processes via
Wasserstein Regularity of Filter Dynamics |
| 2025-03-14 |
Spencer Hill |
Mathematical Introduction to Deep
Learning |
| 2025-03-21 |
Hilaire Epstein Nonhou Zogo |
Event-Triggered Real Time Scheduling of
Stabilizing Control Tasks |
| 2025-04-04 |
Omar Mrani-Zentar | On Near Optimality of Stationary and
Finite Memory Policies in Decentralized Stochastic
Control |
| 2025-05-13 |
Yunus Emre Demirci |
Wasserstein Perturbation Bounds on
Filter Kernels in State Transition and Measurement
Kernel Uncertainty |
| 2025-05-15 | Omar Mrani-Zentar | Periodic Q-learning for POMDPs with
compression of the history process |
| 2025-05-20 |
Ilir Gujisa |
Simultaneous Localization and Mapping
(SLAM) as a Stochastic Control Problem |
| 2025-05-22 |
Connor Braun |
|
Fall: Mondays at 10:30-11:30 (Room 319)
Winter: Fridays at 15:45-16:45 (Room 319)