On Divergence Measures for Training GFlowNets

• URL: http://arxiv.org/abs/2410.09355v2
• Date: Mon, 21 Oct 2024 20:27:30 GMT
• Title: On Divergence Measures for Training GFlowNets
• Authors: Tiago da Silva, Eliezer de Souza da Silva, Diego Mesquita,
• Abstract summary: Generative Flow Networks (GFlowNets) are amortized inference models designed to sample from unnormalized distributions over composable objects. Traditionally, the training procedure for GFlowNets seeks to minimize the expected log-squared difference between a proposal (forward policy) and a target (backward policy) distribution. We review four divergence measures, namely, Renyi-$alpha$'s, Tsallis-$alpha$'s, reverse and forward KL's, and design statistically efficient estimators for their gradients in the context of training GFlowNets
• Score: 3.7277730514654555
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generative Flow Networks (GFlowNets) are amortized inference models designed to sample from unnormalized distributions over composable objects, with applications in generative modeling for tasks in fields such as causal discovery, NLP, and drug discovery. Traditionally, the training procedure for GFlowNets seeks to minimize the expected log-squared difference between a proposal (forward policy) and a target (backward policy) distribution, which enforces certain flow-matching conditions. While this training procedure is closely related to variational inference (VI), directly attempting standard Kullback-Leibler (KL) divergence minimization can lead to proven biased and potentially high-variance estimators. Therefore, we first review four divergence measures, namely, Renyi-$\alpha$'s, Tsallis-$\alpha$'s, reverse and forward KL's, and design statistically efficient estimators for their stochastic gradients in the context of training GFlowNets. Then, we verify that properly minimizing these divergences yields a provably correct and empirically effective training scheme, often leading to significantly faster convergence than previously proposed optimization. To achieve this, we design control variates based on the REINFORCE leave-one-out and score-matching estimators to reduce the variance of the learning objectives' gradients. Our work contributes by narrowing the gap between GFlowNets training and generalized variational approximations, paving the way for algorithmic ideas informed by the divergence minimization viewpoint.

Related papers

• Conformal Risk Minimization with Variance Reduction [37.74931189657469]
  Conformal prediction (CP) is a distribution-free framework for achieving probabilistic guarantees on black-box models. Recent research efforts have focused on optimizing CP efficiency during training. We formalize this concept as the problem of conformal risk minimization.
  arXiv  Detail & Related papers  (2024-11-03T21:48:15Z)
• Beyond Squared Error: Exploring Loss Design for Enhanced Training of Generative Flow Networks [36.084318189865066]
  We show that distinct regression losses correspond to specific divergence measures, enabling us to design and analyze regression losses according to the desired properties of the corresponding divergence measures. Based on our theoretical framework, we propose three novel regression losses, namely, Shifted-Cosh, Linex(1/2), and Linex(1). Our proposed losses are compatible with most existing training algorithms, and significantly improve the performances of the algorithms concerning convergence speed, sample diversity, and robustness.
  arXiv  Detail & Related papers  (2024-10-03T15:37:22Z)
• TransFusion: Covariate-Shift Robust Transfer Learning for High-Dimensional Regression [11.040033344386366]
  We propose a two-step method with a novel fused-regularizer to improve the learning performance on a target task with limited samples. Nonasymptotic bound is provided for the estimation error of the target model. We extend the method to a distributed setting, allowing for a pretraining-finetuning strategy.
  arXiv  Detail & Related papers  (2024-04-01T14:58:16Z)
• Pre-Training and Fine-Tuning Generative Flow Networks [61.90529626590415]
  We introduce a novel approach for reward-free pre-training of GFlowNets. By framing the training as a self-supervised problem, we propose an outcome-conditioned GFlowNet that learns to explore the candidate space. We show that the pre-trained OC-GFN model can allow for a direct extraction of a policy capable of sampling from any new reward functions in downstream tasks.
  arXiv  Detail & Related papers  (2023-10-05T09:53:22Z)
• Towards Understanding and Improving GFlowNet Training [71.85707593318297]
  We introduce an efficient evaluation strategy to compare the learned sampling distribution to the target reward distribution. We propose prioritized replay training of high-reward $x$, relative edge flow policy parametrization, and a novel guided trajectory balance objective.
  arXiv  Detail & Related papers  (2023-05-11T22:50:41Z)
• Learning GFlowNets from partial episodes for improved convergence and stability [56.99229746004125]
  Generative flow networks (GFlowNets) are algorithms for training a sequential sampler of discrete objects under an unnormalized target density. Existing training objectives for GFlowNets are either local to states or transitions, or propagate a reward signal over an entire sampling trajectory. Inspired by the TD($lambda$) algorithm in reinforcement learning, we introduce subtrajectory balance or SubTB($lambda$), a GFlowNet training objective that can learn from partial action subsequences of varying lengths.
  arXiv  Detail & Related papers  (2022-09-26T15:44:24Z)
• Distributionally Robust Models with Parametric Likelihood Ratios [123.05074253513935]
  Three simple ideas allow us to train models with DRO using a broader class of parametric likelihood ratios. We find that models trained with the resulting parametric adversaries are consistently more robust to subpopulation shifts when compared to other DRO approaches.
  arXiv  Detail & Related papers  (2022-04-13T12:43:12Z)
• Learning Diverse Representations for Fast Adaptation to Distribution Shift [78.83747601814669]
  We present a method for learning multiple models, incorporating an objective that pressures each to learn a distinct way to solve the task. We demonstrate our framework's ability to facilitate rapid adaptation to distribution shift.
  arXiv  Detail & Related papers  (2020-06-12T12:23:50Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.