New GFlowNet training framework using policy gradients for combinatorial object generation.
problem Training efficiency and robustness in GFlowNet models.
method Policy-dependent rewards and coupled training strategy for forward and backward policies.
result Advanced RL perspectives for robust gradient estimation improve GFlowNet performance.
EP-GFlowNets parallelize GFlowNet training for large-scale Bayesian inference.
problem Prohibitive repeated evaluations of unnormalized distributions for large-scale posterior sampling.
method Divide-and-conquer approach with server learning from local models.
result EP-GFlowNets enable efficient parallel and federated Bayesian inference.
Theory broadens GFlowNets to handle continuous spaces.
problem Limitation of GFlowNets to discrete spaces.
method Developed a theory for generalized GFlowNets.
result Empirical results show strong performance in continuous cases.
Logit-GFN accelerates GFlowNets training by scaling logits based on temperature.
problem Training temperature-conditional GFlowNets is numerically challenging.
method Logit-GFN uses a learned function of temperature to scale policy logits.
result Logit-GFN greatly accelerates GFlowNets training and improves generalization and mode discovery.
Deriving and applying Proximal Policy Optimization to GFlowNets for efficient training of discrete sampling policies
problem Training stochastic policies to sample from structured discrete probability distributions
method Deriving policy gradient algorithms for GFlowNets and applying Proximal Policy Optimization
result Improved convergence speed and data efficiency compared to standard GFlowNet training objectives
Study explores learning behavior of GFlowNets, revealing key mechanisms.
problem Lack of theoretical understanding of GFlowNets' learning dynamics.
method Rigorous theoretical investigation of four dimensions: convergence, sample complexity, implicit regularization, and robustness.
result Elucidates mechanisms underlying GFlowNet's learning dynamics, providing insights into performance factors.
We explore non-acyclic GFlowNets in discrete settings.
problem Training and understanding non-acyclic GFlowNets in discrete environments.
method Relaxing acyclicity assumption, simpler theoretical framework, novel theoretical insights, experimental validation.
result Theoretical and experimental validation of non-acyclic GFlowNets in discrete environments.
Boosted GFlowNets improve exploration by sequentially training GFlowNets with residual rewards.
problem GFlowNets struggle to evenly explore reward landscapes, leading to poor coverage of high-reward areas.
method Sequential training of an ensemble of GFlowNets, each optimizing a residual reward.
result Boosted GFlowNets achieve better exploration and sample diversity on multimodal benchmarks and peptide design tasks.
EB-GFN models discrete data with amortized MCMC sampling.
problem Probabilistic modeling of high-dimensional discrete data.
method EB-GFN combines GFlowNets with energy-based models for efficient sampling.
result EB-GFN effectively models various discrete data tasks.
Stable GFlowNets prevent loss spikes and mode collapse in training.
problem Unstable training of GFlowNets leading to loss spikes and mode collapse.
method Assessed sensitivity of GFlowNet objectives, derived loss-to-TV bounds, and proposed Stable GFlowNets.
result Stable GFlowNets improve training behavior and distributional fidelity.
Local search improves GFlowNets' ability to generate high-reward samples.
problem GFlowNets struggle with over-exploration in high-reward space.
method Local search focusing on high-reward samples via backtracking and reconstruction.
result Significant performance improvement in biochemical tasks.
Enhances GFlowNets with distributional approach for risk-sensitive policies.
problem Limited applicability of current GFlowNet framework in handling stochastic reward functions.
method Adopting a distributional paradigm, parameterizing each edge flow through quantile functions, and introducing a risk-sensitive learning algorithm.
result Significant improvement on benchmarks due to enhanced training algorithm, even in deterministic reward settings.
New method trains GFlowNets from partial episodes to improve convergence and stability.
problem Improving convergence and stability of GFlowNets training.
method Introducing SubTB(λ) for GFlowNet training from partial action subsequences. result SubTB(λ) accelerates GFlowNet convergence and enables training in longer action sequences. Improved GFlowNets learn more efficiently with trajectory balance.
problem Inefficient credit assignment in GFlowNets leads to suboptimal learning.
method Proposed trajectory balance as a new learning objective.
result Trajectory balance leads to more efficient and robust GFlowNet learning.
GFlowNets improve combinatorial optimization by efficiently sampling from solution spaces.
problem NP-hard combinatorial optimization problems with structured constraints.
method Design Markov decision processes and train conditional GFlowNets to sample solutions.
result GFlowNet policies find high-quality solutions efficiently on various CO tasks.
Paper bridges VI and GFlowNets, showing their equivalence in certain cases.
problem Modeling distributions over continuous and discrete structures.
method Demonstrates equivalence between VI and GFlowNets in specific scenarios.
result GFlowNets are more suitable for off-policy training without high gradient variance.
Unified view of generative models using GFlowNet framework.
problem Diverse deep generative models with varied training and inference methods.
method Integrates GFlowNet framework to unify training and inference.
result Unified training and inference algorithms for generative models.
GFlowNet-EM learns complex latent variable models with discrete structures.
problem Challenges in modeling posteriors over discrete compositional latents with expectation-maximization.
method Uses GFlowNets to learn stochastic policies for sampling from complex posterior distributions.
result GFlowNet-EM enables training expressive LVMs with discrete compositional latents.
New methods minimize GFlowNet training divergences for better sampling.
problem Training GFlowNets with KL divergence leads to biased and high-variance estimators.
method Design and implement efficient estimators for four divergence measures.
result Properly minimizing these divergences yields a provably correct and effective training scheme.
ACE improves GFlowNet exploration efficiency by balancing complementary search strategies.
problem Efficient exploration of diverse high-probability regions in GFlowNets.
method Adaptive Complementary Exploration (ACE) trains a separate GFlowNet to search underexplored regions.
result Significantly improves approximation accuracy and diverse state discovery.
Generative flow networks use RL to learn probabilistic models efficiently.
problem Training generative models with RL for compositional discrete objects.
method Reformulate GFlowNet training as entropy-regularized RL with specific reward and regularizer.
result Entropy-regularized RL can be competitive with established GFlowNet training methods.
Path regularization improves GFlowNets exploration and generalization.
problem Improving GFlowNets exploration and generalization.
method Path regularization based on optimal transport theory.
result Path regularization enhances GFlowNets to generate more diverse and novel candidates.
SA-GFN corrects biases in GFlowNets due to graph symmetries.
problem Systematic biases in state transition probability computations.
method Incorporates symmetry corrections into the learning process through reward scaling.
result Eliminates need for explicit state transition computations.
GFlowNets sample diverse candidates in active learning.
problem Sampling diverse candidates in active learning.
method Generative Flow Networks (GFlowNets) for proportional sampling.
result GFlowNets estimate joint and marginal distributions.
Proposes MOGFNs for generating diverse Pareto optimal solutions in multi-objective optimization.
problem Generating diverse candidates in multi-objective optimization with conflicting objectives.
method Introduces MOGFNs based on GFlowNets, with two variants: MOGFN-PC and MOGFN-AL.
result Improved candidate diversity compared to existing methods.
Improves text-to-image diffusion models using GFlowNets.
problem Aligning diffusion models with text descriptions.
method Post-training diffusion models with GFlowNets to generate high-reward images.
result Effective alignment of large-scale text-to-image diffusion models with reward information.
OP-GFNs sample candidates in order-preserving proportion to a learned reward function.
problem Sampling diverse candidates with varying rewards in multi-objective optimization.
method Order-Preserving GFlowNets (OP-GFNs) use a learned reward function consistent with a provided order on candidates.
result Training OP-GFNs sparsifies the reward landscape, focusing on higher-ranked candidates.
PhyloGFN uses GFlowNets to infer phylogenetic trees from sequence data.
problem Challenging phylogenetic tree inference from sequence data due to high complexity.
method Adopting GFlowNets for parsimony-based and Bayesian phylogenetic inference.
result PhyloGFN produces diverse and high-quality evolutionary hypotheses.
Bayesian structure learning improved using GFlowNets.
problem Inferring Bayesian network structure from data.
method Using Generative Flow Networks (GFlowNets) for approximating posterior DAG distributions.
result DAG-GFlowNet provides an accurate approximation of the posterior over DAGs.
This work improves policy-based training by proposing an evaluation balance objective for GFlowNets.
problem Reliable estimation of policy divergence under directed acyclic graphs remains challenging.
method Proposes an evaluation balance objective over partial episodes to measure policy divergence and improve policy-based training reliability.
result Evaluation balance strengthens policy-based training reliability and broadens its flexibility.
Paper introduces VBG for Bayesian causal structure and mechanism learning.
problem Bayesian causal structure learning with uncertainty over models.
method Variational Bayes-DAG-GFlowNet (VBG) method.
result VBG outperforms existing methods in modeling posterior over DAGs and mechanisms.
Generative Flow Networks solve shortest path problems in graphs.
problem Finding shortest paths in graphs.
method Generative Flow Networks with flow regularization.
result Training a GFlowNet can solve pathfinding problems in arbitrary graphs.
A new algorithm optimizes multiple molecular properties efficiently.
problem Designing molecules with conflicting objectives and costly evaluations.
method Multi-objective Bayesian optimization with GFlowNets.
result HN-GFN samples diverse molecules from an approximate Pareto front.
AlphaSAGE mines diverse alphas via GFlowNets, overcoming RL issues.
problem Reward sparsity, inadequate sequential representations, and single optimal mode issues in RL for alphas.
method Structure-aware encoder (RGCN), GFlowNets, dense reward structure.
result Empirically outperforms existing baselines in mining diverse alphas.
A new method infers graph structure and parameters using a single generative flow network.
problem Bayesian Network structure and parameter inference from data.
method Single GFlowNet with two-phase sampling: DAG generation followed by parameter assignment.
result Accurate approximation of joint posterior distribution over graph structure and parameters.
Study improves sampling efficiency of diffusion models using RL and PDEs.
problem Training neural stochastic differential equations without access to target samples.
method Proves equivalences between RL methods and PDEs, uses coarse time discretization.
result Improves sample efficiency and reduces computational cost.
Adaptive stopping in MCMC using classifier-based dynamics
problem Sampling from complex, unnormalized probability densities
method Training state-dependent neural classifiers
result Significant reduction in average trajectory lengths
DGFS improves sampling from complex densities by optimizing partial trajectories.
problem Sampling from intractable high-dimensional density functions.
method DGFS uses a flow function to break down the training process into short partial trajectory segments, leveraging intermediate learning signals.
result DGFS achieves more accurate estimates of the normalization constant.
GFN-SR uses deep learning to generate diverse mathematical expressions.
problem Symbolic regression to find best mathematical expressions.
method Traversing a DAG to generate expression trees sequentially with GFlowNet.
result GFN-SR outperforms other SR algorithms in noisy data.
Generative Flow Networks use submodular upper bounds to generate more data.
problem Generating data from unknown, complex reward functions efficiently.
method Introduce submodular upper bounds to estimate reward, use Optimism in the Face of Uncertainty principle to train GFNs.
result SUBo-GFN generates significantly more data than classical GFNs.
Delta-AI speeds up inference in sparse PGMs by local credit assignment.
problem Efficient inference in sparse probabilistic graphical models.
method Local credit assignment in agent's policy learning objective.
result Trained sampler recovers marginals and conditional distributions.
AGFN improves causal discovery by integrating expert feedback and handling latent confounding.
problem Inaccurate causal discovery due to unreliable expert knowledge and latent confounding.
method Ancestral GFlowNet (AGFN) is a reinforcement learning algorithm that iteratively refines a policy based on noisy expert feedback to infer ancestral graphs.
result AGFN converges to the true ancestral graph given accurate expert responses and outperforms baselines in structural Hamming distance and Bayesian Information Criterion.
This tutorial reviews RL-based methods for optimizing diffusion models to maximize specific metrics.
problem Optimizing diffusion models to generate samples that maximize specific metrics in practical applications.
method Various RL algorithms including PPO, differentiable optimization, reward-weighted MLE, value-weighted sampling, and path consistency learning.
result Exploration of strengths and limitations of RL-based fine-tuning algorithms and their benefits compared to non-RL-based approaches.
AI methods often fail to outperform classical CPU-based solvers on Maximum Independent Set problems.
problem Comparing AI methods with classical CPU-based solvers on Maximum Independent Set problems.
method Comparison of AI methods (e.g., generative models, reinforcement learning) with classical CPU-based solvers (e.g., KaMIS) on Maximum Independent Set problem.
result AI-inspired methods are often outperformed by classical CPU-based solvers, even with post-processing techniques.
Polynomial chaos surrogates quantify epistemic uncertainty in AI-driven scientific models.
problem Uncertainty in reward estimates hinders interpretability in sequential generative models.
method Fit polynomial chaos expansions to trained models to propagate epistemic uncertainty and quantify sensitivity.
result Interpretable decomposition of reward components driving generative decisions.