collaborators

10 papers

math.ST2026

A Profile-Separation Framework for Quantitative Convergence of No-U-Turn Samplers

Krishnakumar Balasubramanian

We study multinomial and biased-progressive No-U-Turn Samplers for strongly log-concave targets satisfying and $\|\nabla^2U(x)-\nabla^2U(y)\…

math.ST2026

Improved Finite-Particle Convergence Rates for Stein Variational Gradient Descent

Sayan Banerjee, Krishnakumar Balasubramanian, Promit Ghosal

We provide finite-particle convergence rates for the Stein Variational Gradient Descent (SVGD) algorithm in the Kernelized Stein Discrepancy () and Wasserstein-2 metr…

math.PR2026

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…

stat.ML2026

Finite-Particle Rates for Regularized Stein Variational Gradient Descent

Ye He, Krishnakumar Balasubramanian, Sayan Banerjee +1

We derive finite-particle rates for the regularized Stein variational gradient descent (R-SVGD) algorithm introduced by He et al. (2024) that corrects the constant-order bias of th…

stat.ML2026

Total Variation Rates for Riemannian Flow Matching

Yunrui Guan, Krishnakumar Balasubramanian, Shiqian Ma

Riemannian flow matching (RFM) extends flow-based generative modeling to data supported on manifolds by learning a time-dependent tangent vector field whose flow-ODE transports a s…

stat.ML2026

Dependence-Aware Label Aggregation for LLM-as-a-Judge via Ising Models

Krishnakumar Balasubramanian, Aleksandr Podkopaev, Shiva Prasad Kasiviswanathan

Large-scale AI evaluation increasingly relies on aggregating binary judgments from annotators, including LLMs used as judges. Most classical methods, e.g., Dawid-Skene or (weig…