Sam Reifenstein

2 accepted papers

2025

Non-Equilibrium Dynamics of Hybrid Continuous-Discrete Ground-State Sampling

ICLR 2025poster

We propose a general framework for a hybrid continuous-discrete algorithm that integrates continuous-time deterministic dynamics with Metropolis-Hastings (MH) steps to combine search dynamics that either preserve or break detailed balance. Our purpose is to study the non-equilibrium dynamics that le…

Cited by 1 Source ↗PDF ↗Scholar ↗

2024

Dynamic Anisotropic Smoothing for Noisy Derivative-Free Optimization

Sam Reifenstein, Timothee Leleu, Yoshihisa Yamamoto

ICML 2024poster

We propose a novel algorithm that extends the methods of ball smoothing and Gaussian smoothing for noisy derivative-free optimization by accounting for the heterogeneous curvature of the objective function. The algorithm dynamically adapts the shape of the smoothing kernel to approximate the Hessian…

Cited by 2 Source ↗PDF ↗Scholar ↗