# State-Dependent Temperature Control for Langevin Diffusions

arXiv: https://arxiv.org/abs/2011.07456 · HTML: https://mlsanity.com/paper/2011.07456/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Nov 2020.

## Built on by (most cited first, 20 of 20)

- [Recent Advances in Reinforcement Learning in Finance](https://mlsanity.com/paper/2112.04553/) (2021)
- [Policy Gradient and Actor-Critic Learning in Continuous Time and Space: Theory and Algorithms](https://mlsanity.com/paper/2111.11232/) (2021)
- [q-Learning in Continuous Time](https://mlsanity.com/paper/2207.00713/) (2022)
- [Policy Evaluation and Temporal-Difference Learning in Continuous Time and Space: A Martingale Approach](https://mlsanity.com/paper/2108.06655/) (2021)
- [Fine-tuning of diffusion models via stochastic control: entropy regularization and beyond](https://mlsanity.com/paper/2403.06279/) (2024)
- [Learning to Optimally Stop Diffusion Processes, with Financial Applications](https://mlsanity.com/paper/2408.09242/) (2024)
- [Simulated annealing from continuum to discretization: a convergence analysis via the Eyring--Kramers law](https://mlsanity.com/paper/2102.02339/) (2021)
- [Continuous Q-Score Matching: Diffusion Guided Reinforcement Learning for Continuous-Time Control](https://mlsanity.com/paper/2510.17122/) (2025)
- [An Algebraically Converging Stochastic Gradient Descent Algorithm for Global Optimization](https://mlsanity.com/paper/2204.05923/) (2022)
- [Choquet regularization for reinforcement learning](https://mlsanity.com/paper/2208.08497/) (2022)
- [Fisher information dissipation for time inhomogeneous stochastic differential equations](https://mlsanity.com/paper/2402.01036/) (2024)
- [Reinforcement Learning for Jump-Diffusions, with Financial Applications](https://mlsanity.com/paper/2405.16449/) (2024)
- [Discretization error from regularized Reinforcement Learning to continuous-time stochastic control](https://mlsanity.com/paper/2604.21179/) (2026)
- [Uniform Generalization Bound on Time and Inverse Temperature for Gradient Descent Algorithm and its Application to Analysis of Simulated Annealing](https://mlsanity.com/paper/2205.12959/) (2022)
- [Accelerating Convergence in Global Non-Convex Optimization with Reversible Diffusion](https://mlsanity.com/paper/2305.11493/) (2023)
- [Consensus-based adaptive sampling and approximation for high-dimensional energy landscapes](https://mlsanity.com/paper/2311.05009/) (2023)
- [Research on Optimal Control Problem Based on Reinforcement Learning under Knightian Uncertainty](https://mlsanity.com/paper/2506.13207/) (2025)
- [Mean-Field Langevin Diffusions with Density-dependent Temperature](https://mlsanity.com/paper/2507.20958/) (2025)
- [Risk-Sensitive Q-Learning in Continuous Time with Application to Dynamic Portfolio Selection](https://mlsanity.com/paper/2512.02386/) (2025)
- [Fast PAC Global Optimization via Restarted Langevin: Exploration, Exploitation, and Degenerate Cooling](https://mlsanity.com/paper/2609.06196/) (2026)

## Abstract (arXiv)

We study the temperature control problem for Langevin diffusions in the context of non-convex optimization. The classical optimal control of such a problem is of the bang-bang type, which is overly sensitive to errors. A remedy is to allow the diffusions to explore other temperature values and hence smooth out the bang-bang control. We accomplish this by a stochastic relaxed control formulation incorporating randomization of the temperature control and regularizing its entropy. We derive a state-dependent, truncated exponential distribution, which can be used to sample temperatures in a Langevin algorithm, in terms of the solution to an HJB partial differential equation. We carry out a numerical experiment on a one-dimensional baseline example, in which the HJB equation can be easily solved, to compare the performance of the algorithm with three other available algorithms in search of a global optimum.