| Date | Speaker | Title |
|---|---|---|
| 2022-09-09 | Ryan Simpson | Non-Sequential Stochastic Control and Static Reducibility via Change of Measures |
| 2022-09-16 | Yunus Emre Demirci |
Existence and Uniqueness of
Invariant Probability Measures in Markov Chains and
Non-Linear Filters |
| 2022-09-23 | Yunus Emre Demirci | Existence and Uniqueness of Invariant Probability Measures in Markov Chains and Non-Linear Filters |
| 2022-09-30 | Yunus Emre Demirci | Existence and Uniqueness of Invariant Probability Measures in Markov Chains and Non-Linear Filters |
| 2022-10-07 |
Somnath Pradhan |
Game Theoretic Approach to Risk-Sensitive Control of
Markov Processes in Countable State Space |
| 2022-10-21 |
Liam Cregg | Using Quantized Q-learning to Find Near-Optimal Policies for the Zero-Delay Lossy Coding Problem |
| 2022-10-28 |
Liam Cregg | Using Quantized Q-learning to Find Near-Optimal Policies for the Zero-Delay Lossy Coding Problem |
| 2022-11-04 |
Huizhen (Janey) Yu (Alberta) |
Average-Cost Markov Decision Processes with Borel Spaces and Universally Measurable Policies |
| 2022-11-11 | Zachary Selk |
The Small Noise Limit of the Most Likely Element is the Most Likely Element in the Small Noise Limit |
| 2022-11-18 |
Yunus Emre Demirci |
Average Cost Dynamic Programming
Equations for Partially Observed Markov Decision
Processes |
| 2022-11-25 |
Serdar Yuksel |
Merging of opinions with increasing
information and applications |
| 2023-01-27 |
Bora Yongacoglu |
An Introduction to Multi-Armed Bandits |
| 2023-02-03 |
Somnath Pradhan |
Robustness of Risk-Sensitive Stochastic
Optimal Control to Approximate Diffusion Models |
| 2023-02-10 |
Zachary Selk |
An Introduction to Malliavin Calculus - I |
| 2023-02-17 |
Zachary Selk | An Introduction to Malliavin Calculus - II |
| 2023-03-03 |
Yunus Emre Demirci |
Unique Ergodicity of Control-Free Non-Linear Filters |
| 2023-03-10 |
Serdar Yuksel |
On the
Relationship between Borkar and Young Control
Topologies and Continuous Dependence of Invariant
Measures on Stationary Control Policy |
| 2023-03-17 |
Bora Yongacoglu |
An explore-then-commit algorithm for decentralized bandits |
| 2023-03-22 |
Curtis McDonald (Yale) |
Background on Stochastic Differential Equations, Density Evolution, and Score Based Diffusion |
| 2023-03-24 |
Curtis McDonald (Yale) |
Score Based Diffusion as a Density Evolution Method |
| 2023-04-19 |
Ali D. Kara (Michigan) |
Finite Approximations and Q learning for Mean Field Type Multi-Agent Control Problems |
| 2023-05-09 |
Yunus Emre Demirci |
Furter Results on Unique Ergodicity of
Non-Linear Filters |
| 2023-05-12 |
Somnath Pradhan |
Robustness of Markov Chain Approximations for Optimal Control of Diffusions |
| 2023-05-16 |
Bora Yongacoglu | Subjective Equilibrium in
Mean-Field Games |
| 2023-05-23 |
Sina Sanjari |
Large Continuous-Time Convex Stochastic
Teams and Their Mean-Field Limit |
| 2023-05-26- |
Zachary Selk |
Robust Control of Systems of
Interacting Particles via Risk Sensitivity |
| 2023-05-30 |
Prof. Melkior Ornik (Illinois) |
Resilience and Guaranteed Performance
for Control Systems with Unknown Dynamics |
Zachary Selk also gave an 8-hour intensive course on Rough Paths Theory in October and November.
Bora Yongacoglu served as the seminar organizer for the 2nd part of the year.
Time : Fridays 1:30pm-2:30pm (Room 319). Sometimes we will start earlier at 1:00pm.