Institution profile

Xaira Therapeutics

Industry researchnorthamerica · us
Official website
Research library1linked papers
Opportunities12open roles
Selected work

Representative Papers

Sampling from Energy distributions with Target Concrete Score Identity

Oct 27, 2025

This work addresses the problem of efficient, unbiased sampling from unnormalized densities defined over discrete state spaces. We propose Time-Continuous Score-based Importance Sampling (TCSIS), a novel method grounded in the Target Concrete Score identity—a theoretical contribution that for the first time establishes an analytical link between marginal transition probabilities and ratios of Boltzmann-factor expectations, enabling self-normalized score estimation without target samples or the intractable partition function. TCSIS builds upon a forward uniform-noise continuous-time Markov chain (CTMC) and employs a neural network to model the Concrete Score, with expectations estimated via Monte Carlo. We design two variants: Self-Normalized TCSIS and Unbiased TCSIS. Empirical evaluation on statistical physics tasks demonstrates substantial improvements in both sampling efficiency and accuracy for discrete generative models, establishing a new paradigm for discrete sampling under unnormalized distributions.

0 citationsRead paper
Recent publications

Latest Papers

Sampling from Energy distributions with Target Concrete Score Identity

Oct 27, 2025

This work addresses the problem of efficient, unbiased sampling from unnormalized densities defined over discrete state spaces. We propose Time-Continuous Score-based Importance Sampling (TCSIS), a novel method grounded in the Target Concrete Score identity—a theoretical contribution that for the first time establishes an analytical link between marginal transition probabilities and ratios of Boltzmann-factor expectations, enabling self-normalized score estimation without target samples or the intractable partition function. TCSIS builds upon a forward uniform-noise continuous-time Markov chain (CTMC) and employs a neural network to model the Concrete Score, with expectations estimated via Monte Carlo. We design two variants: Self-Normalized TCSIS and Unbiased TCSIS. Empirical evaluation on statistical physics tasks demonstrates substantial improvements in both sampling efficiency and accuracy for discrete generative models, establishing a new paradigm for discrete sampling under unnormalized distributions.

0 citationsRead paper