5 papers
Quantitative Target Convergence and Uniform-in-Time Propagation of Chaos for Langevin-Regularized SVGD
Sayan Banerjee, Dohyeon Kim
We establish quantitative convergence to the target and uniform-in-time propagation of chaos for Langevin-regularized Stein variational gradient descent. The Stein interaction need…
Uniform-in-time Propagation-of-Chaos for Stein Variational Gradient Descent
Krishnakumar Balasubramanian, Sayan Banerjee, Anna Korba
We study uniform-in-time propagation-of-chaos for continuous-time Stein Variational Gradient Descent (SVGD). Classical finite-time propagation-of-chaos estimates for mean-field sys…
DRIFT: From Robustness Gaps to Invariance Manifolds for AI-Generated Image Detection
Abhishek Ameta, Sayan Banerjee, Shreyas Pandith +4
The rapid evolution of generative image models challenges existing AI-generated image detectors, particularly in open-world settings with unseen generators. Recent training-free ap…
Geodesic Flow Matching on a Riemannian Degradation Manifold for Blind Image Restoration
Akshay Janardan Bankar, Ankita Chatterjee, Sayan Banerjee +3
Blind image restoration requires recovering clean images from observations corrupted by unknown and potentially mixed degradations. While recent deterministic flow-based methods mo…
On the Structure of Stationary Solutions to McKean-Vlasov Equations with Applications to Noisy Transformers
Krishnakumar Balasubramanian, Sayan Banerjee, Philippe Rigollet
We study stationary solutions of McKean-Vlasov equations on the circle. Our main contributions stem from observing an exact equivalence between solutions of the stationary McKean-V…