Optimal control theory connects diffusion models to generative modeling.
problem Sampling from unnormalized densities in statistics and computational sciences.
method Deriving a Hamilton-Jacobi-Bellman equation and applying control theory to minimize Kullback-Leibler divergence.
result Time-reversed diffusion sampler (DIS) outperforms other diffusion-based sampling methods.
Stabilizes complex systems using diffusion models trained on Lyapunov functions.
problem Generating stabilizing controllers for complex dynamical systems.
method Trains a diffusion model on pairs of asymptotically stable vector fields and their Lyapunov functions to identify the closest stable field and adjust control functions.
result Efficient and rapid stabilization of unseen systems, showcasing generalizability.
RNE provides a flexible framework for diffusion models, enabling inference-time control and energy-based training.
problem Insufficient knowledge of marginal densities in diffusion models.
method Introduces Radon-Nikodym Estimator (RNE) to reveal the connection between marginal densities and transition kernels.
result RNE delivers strong results in inference-time control and energy-based diffusion training.
New method learns diffusion bridges for rare events.
problem Simulating rare events in diffusion processes.
method Iterative online learning based on self-consistency.
result Strong performance in various empirical settings.
New diffusion models improve counterfactual image generation with semantic control.
problem Challenges in preserving identity, maintaining quality, and ensuring causal model faithfulness in counterfactual image generation.
method Integrates semantic representations into diffusion models through Pearlian causality, introducing spatial, semantic, and dynamic abduction.
result Demonstrates high-level semantic identity preservation and principled trade-offs between faithful causal control and identity preservation.
A RL-based method adds conditional controls to pre-trained diffusion models.
problem Precise control over generated samples in diffusion models.
method Formulates the task as an RL problem, using a classifier and KL divergence as reward functions.
result Produces soft-optimal policies that maximize reward functions, enabling conditional sampling.
New method guides pretrained diffusion models without additional training.
problem Guidance methods for diffusion models often require extra training or are task-specific.
method Variational Control using Diffusion Trajectory Matching (DTM)
result Achieves state-of-the-art results on various problems.
Develops a new model for controllable and realistic traffic simulation.
problem Lack of models that offer both controllability and realism in traffic simulation.
method Guided Conditional Diffusion (CTG) model using diffusion modeling and differentiable logic.
result Improves controllability-realism tradeoff over strong baselines.
This work formalizes guidance in diffusion models and introduces a stochastic control framework.
problem Lack of a solid theoretical foundation for guidance scheduling in diffusion models.
method Introduces a stochastic optimal control framework to cast guidance scheduling as an adaptive optimization problem.
result Establishes a principled foundation for more effective guidance in diffusion models.
Jeffrey guidance extends diffusion-model control to more complex applications.
problem Controlling diffusion models beyond simple cases like conditional sampling.
method Leveraging Jeffrey's rule of conditioning to update marginal distributions towards a target distribution.
result Significant reductions in FID on CIFAR-10 and FFHQ with Inception embeddings as the target.
New approach to control diffusion processes with soft constraints.
problem Finding an optimal diffusion process with a target terminal distribution.
method Generalized Schrödinger bridge problem with soft constraints, solving for a geometric mixture of target and other distributions.
result The terminal distribution of the optimally controlled process is a geometric mixture of the target and another distribution.
Study optimal control of diffusion processes with infimum or supremum costs.
problem Optimizing control of a diffusion process with costs dependent on its infimum or supremum.
method Introduced novel integral operators to solve two-dimensional singular control problems.
result Explicit solutions for optimal dividend problem with time-dependent preferences.
Develops diffusion samplers for target distributions with efficient score and density estimates.
problem Estimating scores and densities for time-varying distributions.
method Sequential Monte Carlo with diffusion paths and control variates.
result Effective samplers for time-varying distributions with theoretical guarantees and practical applications.
RL for jump-diffusions applies to financial portfolio selection and option hedging.
problem Optimizing control in systems with jump-diffusion dynamics.
method Entropy-regularized exploratory control with stochastic policies, using existing diffusion algorithms with modifications.
result RL algorithms and parameterizations are invariant to jumps in jump-diffusion systems.
Study on games with degenerate diffusion matrices, proving value existence and convergence.
problem Zero-sum games between singular controller and stopper with degenerate diffusion.
method Probabilistic approach using parameterized approximations, convergence analysis.
result Existence of value and optimal stopping times for the game with degenerate dynamics.
New text-to-image diffusion models improve scene understanding for AI agents.
problem Fine-grained scene understanding for AI agents from text and images.
method Pre-trained text-to-image diffusion models optimized for generating images from text prompts.
result Policies learned with Stable Control Representations outperform state-of-the-art approaches on various control tasks.
This paper extends neural network approximation results to denoising diffusion models.
problem Improving the efficiency and accuracy of generative models.
method Leveraging connections to stochastic control and neural network approximation.
result Established neural network approximation results for the Föllmer drift are extended to denoising diffusion models.
New method uses neural networks to solve complex PDEs from optimal control theory.
problem Solving high-dimensional Hamilton-Jacobi-Bellman PDEs.
method Iterative diffusion optimization techniques, focusing on path measures and divergences.
result Favourable properties of log-variance divergence for Monte Carlo estimators.
New method calibrates diffusion models for image regression tasks.
problem Ensuring reliability of diffusion models for critical applications.
method Risk-Controlling Prediction Sets (RCPS) with convex optimization.
result Calibrated entrywise intervals and risk control with minimal mean interval length.
Paper proposes DigMA to generate controllable financial market orders.
problem Generating realistic financial market orders with controllability.
method DigMA model using conditional diffusion and meta agent.
result DigMA achieves superior controllability and generation fidelity.
Study of multidimensional control problems with reflection controls.
problem Solving control problems with reflection controls in multidimensional settings.
method Gradient descent algorithm for polytope approximations, data-driven domain estimator, episodic learning algorithm.
result Data-driven solutions for unknown diffusion dynamics with sublinear regret.
Optimizes dividend policies in a Brownian model with controlled rates.
problem Realistic optimal dividend policies in a stochastic control problem.
method Delayed linear control strategies for refracted diffusion processes.
result Optimality of delayed linear control strategies for dividend payments.
DriftLite improves inference quality of diffusion models without retraining.
problem Adapting pre-trained diffusion models to new target distributions without retraining.
method Lightweight, training-free particle-based approach that steers inference dynamics with optimal stability control.
result Consistently reduces variance and improves sample quality over existing methods.
Improved diffusion models using energy distillation and sequential Monte Carlo.
problem Training instability and inferior performance in energy parameterized diffusion models.
method Introduced a novel training regime for energy functions through distillation of pre-trained diffusion models, and cast the sampling procedure as a Feynman Kac model.
result Demonstrated improved performance and new sampling techniques.
Optimizes control of hybrid systems with multiple switching processes.
problem Optimal control of hybrid systems with multiple Markov switching processes.
method Combines two separate Markov chains into one synthetic chain, derives HJB equations, and solves the portfolio choice problem.
result Derives explicit solutions and value functions for the optimal control problem.
New method controls classifier guidance in diffusion models.
problem Improving classifier guidance in diffusion models.
method Cross-entropy control of classifier gradients.
result Effective guidance vectors with mean squared error O ( d ε ) O(d \varepsilon ) O ( d ε ) . Paper solves MV portfolio selection in jump-diffusion models with no-shorting constraint.
problem Mean-variance portfolio selection in jump-diffusion model with no-shorting constraint.
method Reduces problem to LQ control and finding a maximal point of a function, constructs viscosity solution.
result Explicit viscosity solution to Hamilton-Jacobi-Bellman equation, optimal controls derived.
Algorithm learns diffusion processes with high-dimensional state spaces.
problem Stochastic control of unbounded diffusion processes with high-dimensional state spaces.
method Adaptive partitioning and learning algorithm that refines discretization based on estimation bias and statistical confidence.
result Established regret bounds that depend on problem parameters, extending to unbounded diffusion processes.
Study shows how to control jump-diffusion processes with stable feedback controls in reinforcement learning.
problem Control jump-diffusion processes with unknown coefficients in reinforcement learning.
method Lipschitz continuous optimal feedback controls, stability analysis of forward-backward SDEs, least-squares algorithm.
result Achieves O ( N ln N ) O(\sqrt{N\ln N}) O ( N ln N ) regret for linear-convex learning problems with jumps. New method modifies diffusions for singular rewards.
problem Handling singular rewards in diffusions.
method Malliavin calculus for non-differentiable rewards.
result Stable and reliable training of diffusions.
Improves diffusion models by controlling total variance and signal-to-noise-ratio.
problem Long sampling time in diffusion models.
method Total-Variance/Signal-to-Noise-Ratio (TV/SNR) disentangled framework.
result Improves generation performance by controlling TV and SNR independently.
RB-Modulation trains free diffusion models without external adapters.
problem Training-free personalization of diffusion models with style and content control.
method Stochastic optimal control with a style descriptor and cross-attention aggregation.
result Precise content and style extraction and control without external adapters.
Paper explores two methods for optimal portfolio selection in financial markets.
problem Optimal portfolio selection for financial markets with jumps.
method Maximum principle and dynamic programming approach.
result Relationship between two methods and their adjoint processes.
The paper defines and solves time-inconsistent stopping control problems in multi-dimensional diffusion models.
problem Time-inconsistent problems in control and stopping strategies.
method Formal definition of weak equilibria, extended HJB system, and verification methodology.
result Explicit equilibrium solutions and existence of non-constant equilibria.
NCT simplifies one-step generator adaptation to new controls.
problem Adapting one-step generators to new control conditions.
method Noise Consistency Training (NCT) integrates new controls without retraining.
result NCT achieves state-of-the-art controllable generation in a single pass.
DDS samples from noisy data by reversing diffusion, providing theoretical guarantees.
problem Sampling from unnormalized densities.
method Denoising diffusion process, score matching, optimal control, Schrödinger bridges.
result DDS provides theoretical guarantees for sampling.
Paper studies constrained control games with a novel approximation method.
problem Games with constrained control directions.
method Approximation procedure based on L 1 L^1 L 1 -stability estimates and almost sure convergence. result Existence of game's value and optimal strategy for the stopper.
Fine-tunes diffusion models to generate diverse samples with high genuine rewards.
problem Reward collapse in finetuning diffusion models.
method Entropy-regularized control against pretrained diffusion models.
result Efficient generation of diverse samples with high genuine rewards.
Replica exchange Langevin diffusion accelerates nonconvex optimization.
problem Nonconvex optimization challenges in machine learning.
method Replica exchange Langevin diffusion, discretization analysis.
result Replica exchange accelerates convergence to global minima.
The paper solves stochastic control problems with implicit objectives, finding equilibrium strategies.
problem Stochastic control problems with implicitly defined objectives leading to time-inconsistency.
method Closed-loop equilibrium solutions in a controlled diffusion framework, providing sufficient and necessary conditions.
result Explicit characterization of equilibrium portfolio strategies in terms of ordinary differential equations.
The paper tackles data-driven optimal control of unknown nonlinear systems using RKHS.
problem Unknown nonlinear dynamics and stage cost functions.
method Embed state densities into RKHS, learn Markov operators, solve Hamilton-Jacobi-Bellman recursions.
result Solves a wide range of nonlinear control problems, including depth regulation.
Adjoint Matching improves flow and diffusion models with reward fine-tuning.
problem Improving generative models with reward fine-tuning.
method Casting reward fine-tuning as stochastic optimal control (SOC) and enforcing a specific noise schedule.
result Adjoint Matching outperforms existing SOC algorithms.
We establish a stochastic maximum principle (SMP) for control problems of partially observed diffusions of mean-field type with risk-sensitive performance functionals.
Improved image synthesis with user scribbles and text prompts.
problem Inadequate details in generated images due to domain shift.
method Optimization problem formulation and cross-attention for control.
result Significant improvement in user satisfaction (85.32% higher).
CoFinDiff generates synthetic financial data capturing stylized facts and meeting specified conditions.
problem Limited data availability and difficulty in controlling synthetic financial data generation.
method Conditional diffusion model with cross-attention to incorporate conditions derived from price data.
result Synthetic data generated by CoFinDiff accurately meets specified conditions for trends and volatility.
This paper solves a Bayes sequential impulse control problem for a diffusion, whose drift has an unobservable parameter with a change point. The partially-observed problem is reformulated into one with full observations, via a change of probability measure which removes the drift. The optimal impulse controls can be ex…
Schrödinger bridge solved with Weyl calculus for quadratic state cost.
problem Optimal control policy to steer joint state statistics.
method Weyl calculus in quantum mechanics for reaction-diffusion PDEs.
result Explicit Markov kernel for quadratic state cost found.
New method reduces over-pessimism in Bayesian control under parameter uncertainty.
problem Over-pessimism in Bayesian control due to misspecified priors.
method Distributionally robust Bayesian control (DRBC) with strong duality and optimization.
result Validated algorithm on synthetic and real data, reducing over-pessimism.