Author

K. Balasubramanian

5 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

A Dimension-Free Bound on the Poincar\'e Constant of Isotropic Log-Concave Measures

The Kannan--Lov\'asz--Simonovits (KLS) conjecture asserts that isotropic log-concave probability measures have Poincar\'e constants bounded by a universal constant, independently of dimension. We give a deterministic variational proof with an explicit bound on the Poincar\'e constant $C_P(\mu)\le25$, where $\mu$ is any...

K. Balasubramanian, S. Kasiviswanathan · 0 citations

#machine learning Preprint Oct 2026

Read What Matters: Query-Adaptive Quantization for KV Caches

KV-cache entries are stored before their future queries are known, but each decoding query needs precision in different places. We study this mismatch using separate budgets for retained bits and bits fetched per query. ReadKV stores each key and value in a progressive code whose prefixes support different reconstructi...

Siddharth Bhandari, Lucas Gretta, K. Balasubramanian et al. · 0 citations

#machine learning Preprint Oct 2026

Adaptive Mean Estimation by In-Context Learning: A Gradient-Flow Analysis

Prior Fitted Networks (PFNs) such as TabPFN now rival established statistical procedures across prediction and estimation tasks. A natural explanation is that PFNs have the property of statistical adaptivity, that is, they perform nearly as well as a method tailored to the true data-generating model for a heterogeneous...

Martin Eppert, K. Balasubramanian, Subhro Ghosh et al. · 0 citations

#artificial intelligence Preprint Oct 2026

Learning Style, Forgetting Semantics: A Case Study of SFT and RFT on Classification Tasks

Why does supervised fine-tuning (SFT) lead to more forgetting than reinforcement fine-tuning (RFT), even when all teacher demonstrations are semantically correct? We study this question on classification tasks where tokens within each semantic class express the same semantic answer in different styles. The tasks share...

Hao-Dong Liang, Yan-Hao Jin, K. Balasubramanian et al. · 0 citations

#artificial intelligence Preprint Oct 2026

Counterfactual Generation via Flow Matching: Coupling-Sensitive End-to-End Rates

Counterfactual generation seeks to sample outcomes under a hypothetical intervention or decision using observational data collected under the factual assignment mechanism. We develop a flow-matching approach that combines a sample-split, doubly robust training objective with a learned coupling between observed source o...

Yun-Rui Guan, K. Balasubramanian, S. Kasiviswanathan · 0 citations