| Date | Speaker | Title |
|---|---|---|
| 2025-09-09 | Serdar Yüksel | Stochastic Control
with Partial and Decentralized Information |
| 2025-09-23 | Emre Demirci |
Unique Ergodicity of Non-Linear Filters via Reachability and Uniform Weak Continuity |
| 2025-10-07 |
Connor Braun |
Within-Clusters Exchangeability of Optimal Policies for Discrete Time Graphon Mean-Field Teams |
| 2025-10-21 |
Thomas Emo |
Explicit Approximation Bounds via Wasserstein
Regularity in the Zero-Delay Coding Problem |
| 2025-10-28 |
Omar Mrani-Zentar |
Non-Sequential Decentralized Stochastic Control:
Causality and Static Reducibility |
| 2025-11-04 |
Serdar Yüksel | Quantized Q-Learning for Stochastic
Control with Borel Spaces and General Information
Structures |
| 2025-11-11 |
Omar Mrani-Zentar | White Noise Representation of Stochastic Processes |
| 2025-11-18 |
Serdar Yüksel | Multi-Agent Learning with Decentralized
Information via Characterization of Policy Revision
Paths to Equilibria (Part I) |
| 2025-11-25 |
Gwendolen Hickey |
Multi-Agent Learning with Decentralized
Information via Characterization of Policy Revision
Paths to Equilibria (Part II) |
| 2025-12-02 | Ilir Gusija |
Optimal solutions with rigorous
approximations for SLAM |
| 2026-01-13 |
Emre Demirci |
Near-Optimality of Finite Window
Policies in Stochastic Control with Partial
Information under Pointwise Controlled Filter
Stability |
| 2026-01-20 |
Connor Braun |
Mean-Field Control with Heterogeneous
Subteams: Structural Results and McKean-Vlasov Control
of Cluster-Representative Agents |
| 2026-01-27 |
Kağan Akman (Bilkent Univ.) |
An Optimal Control Approach to
Transformer Training |
| 2026-02-02 |
Thomas Emo |
Approximately Optimal Zero-Delay Coding
for Continuous Space Valued Markov Sources with
Explicit Rates of Convergence for Finite Sources |
| 2026-02-09 |
Serdar Yüksel | Agentic Subjective Learning Equilibrium |
| 2026-02-23 |
Spencer Hill |
Adaptive Data Analysis and
Information-Theoretic Generalization Bounds |
| 2026-03-02 |
Yunus Emre Demirci |
Near-Optimal Finite Approximations for
Controlled Diffusions with Partial Information via
Euler-Maruyama Discretization |
| 2026-03-09 |
Omar Mrani-Zentar |
Data-Driven Empirical and Bayesian
Learning for Control of MDPs with Borel Spaces:
Identifiability and Near Optimal Design |
| 2026-03-16 |
Matt Daly |
Reinforcement Learning with Function
Approximation (Part 1) |
| 2026-03-23 |
Yunus Emre Demirci | Near-Optimal Finite Approximations for
Controlled Diffusions with Partial Information via
Euler-Maruyama Discretization (Part 2) |
| 2026-03-30 |
Matt Daly | Reinforcement Learning with Function Approximation (Part 2) |
| 2026-05-07 |
Thomas Emo |
Sufficient Information in Zero-Delay
Coding |
| 2026-05-12 |
Omar Mrani-Zentar | Lift, Metrize, Quantize, and
Learn: A framework for learning in complex
stochastic control problems |
| 2026-05-14 |
Spencer Hill |
Rejection Sampling and the Ring Toss
Code |
| 2026-05-19 |
Connor Braun |
Optimality of Decentralized
Cluster-Symmetric Policies for Multi-Population
Mean-Field Teams |
| 2026-05-21 |
Ben van Eeden |
Scalar Conservation Laws, Weak and
Entropy Solutions, and an Application |
| 2026-05-26 |
Yunus Emre Demirci |
Euler-Maruyama versus Sampled
Approximations for Controlled Diffusions with Partial
Information |
| 2026-05-27 |
Ilir Gusija |
Active Simultaneous Localization and
Mapping (SLAM) as a Stochastic Control Problem |
Location: Room 319