collaborators

12 papers

stat.ML2026

Discrete distributions are learnable from metastable samples

Abhijith Jayakumar, Andrey Y. Lokhov, Sidhant Misra +1

Physically motivated stochastic dynamics are widely used to sample from high-dimensional distributions. However, such samplers often get trapped in metastable states, approximately…

stat.ML2026

Symmetric Linear Dynamical Systems are Learnable from Few Observations

Minh Vu, Andrey Y. Lokhov, Marc Vuffray

We consider the problem of learning the parameters of a -dimensional stochastic linear dynamics under both full and partial observations from a single trajectory of time . We…

quant-ph2026

Potential Applications of Quantum Computing at Los Alamos National Laboratory

Andreas Bärtschi, Francesco Caravelli, Carleton Coffrin +16

The emergence of quantum computing technology over the last decade indicates the potential for a transformational impact in the study of quantum mechanical systems. It is natural t…

cs.LG2026

Finite Sample Bounds for Learning with Score Matching

Devin Smedira, Abhijith Jayakumar, Sidhant Misra +2

Learning of continuous exponential family distributions with unbounded support remains an important area of research for both theory and applications in high-dimensional statistics…

stat.ML2026

Selecting Optimal Variable Order in Autoregressive Ising Models

Shiba Biswal, Marc Vuffray, Andrey Y. Lokhov

Autoregressive models enable tractable sampling from learned probability distributions, but their performance critically depends on the variable ordering used in the factorization…

cs.LG2026

Discrete Diffusion with Sample-Efficient Estimators for Conditionals

Karthik Elamvazhuthi, Abhijith Jayakumar, Andrey Y. Lokhov

We study a discrete denoising diffusion framework that integrates a sample-efficient estimator of single-site conditionals with round-robin noising and denoising dynamics for gener…