collaborators

11 papers

cs.LG2026

Sample Complexity of Multicalibration for Multilevel Properties

Jiuyao Lu, Krishnakumar Balasubramanian, Aleksandr Podkopaev +1

Calibration requires a predictor to be unbiased after conditioning on its own predictions. Multicalibration asks for this guarantee simultaneously across a collection of groups. Ma…

cs.LG2026

All Routes Lead to Collapse

K. R. Balasubramanian

Attention sinks, representation collapse, and norm stratification are treated as transformer-specific pathologies. We show they are not specific to attention: they are what content…

cs.LG2026

FoundCause: Causal Discovery with Latent Confounders from Observational Data

Patrick Blöbaum, Krishnakumar Balasubramanian, Shiva Prasad Kasiviswanathan

Causal discovery from observational data remains challenging due to the need to recover directed structure and latent confounding without interventions. We propose FoundCause, an a…

stat.ML2026

Finite-Particle Convergence Rates for Conservative and Non-Conservative Drifting Models

Krishnakumar Balasubramanian

We propose and analyze a conservative drifting method for one-step generative modeling. The method replaces the original displacement-based drifting velocity by a kernel density es…

stat.ML2026

Large-Step Training Dynamics of a Two-Factor Linear Transformer Model

Krishnakumar Balasubramanian

Gradient-flow analyses show that simplified linear transformers can learn the in-context linear-regression algorithm, but they do not explain the finite-step behavior of gradient d…

cs.LG2026

A Quantitative Characterization of Forgetting in Post-Training

Krishnakumar Balasubramanian, Shiva Prasad Kasiviswanathan

Continual post-training of generative models is widely used, yet a principled understanding of when and why forgetting occurs remains limited. We develop theoretical results under…