11 papers
Scalable method for mean field control with kernel interactions via random Fourier features
Zhongyuan Cao, Kaustav Das, Nicolas Langrené +1
We develop a scalable algorithm for mean field control problems with kernel interactions by combining particle system simulations with random Fourier feature approximations. The me…
Dual Approaches to Stochastic Control via SPDEs and the Pathwise Hopf Formula
Mathieu Laurière, Jiefei Yang
We develop dual approaches for continuous-time stochastic control problems, enabling the computation of robust dual bounds in high-dimensional state and control spaces. Building on…
Controlling Exploration-Exploitation in GFlowNets via Markov Chain Perspectives
Lin Chen, Samuel Drapeau, Fanghao Shao +5
Generative Flow Network (GFlowNet) objectives implicitly fix an equal mixing of forward and backward policies, potentially constraining the exploration-exploitation trade-off durin…
Dynamic Programming Principle and Stabilization for Mean-Field Quantum Filtering Systems
Sofiane Chalal, Nina H. Amini, Hamed Amini +1
Working within the quantum filtering framework, we establish a dynamic programming principle in an infinite-dimensional setting by embedding the state space into the Hilbert-Schmid…
Clustering in Deep Stochastic Transformers
Lev Fedorov, Michaël E. Sander, Romuald Elie +2
Transformers have revolutionized deep learning across various domains but understanding the precise token dynamics remains a theoretical challenge. Existing theories of deep Transf…
Discrete-Time Mean Field Type Games: Probabilistic Setup
Grégoire Lambrecht, Mathieu Laurière
We introduce a general probabilistic framework for discrete-time, infinite-horizon discounted Mean Field Type Games (MFTGs) with both global common noise and team-specific common n…