Harnessing Distribution Ratio Estimators for Learning Agents with Quality and Diversity

利用奖励不确定性在强化学习中诱导多样化行为

Using Reward Uncertainty to Induce Diverse Behaviour in Reinforcement Learning

针对传统强化学习缺乏多样性的问题，提出将奖励函数替换为奖励分布，通过非线性集合目标自然产生可控的多样化行为，并推导出梯度估计器，实验证明其鲁棒性和理论优势。

Gradient Estimators for Implicit Models

Implicit models, which allow for the generation of samples but not for point-wise evaluation of probabilities, are omnipresent in real-world problems tackled by machine learning and a hot topic of current research. Some examples include data simulators that are widely used in engineering and scientific research, generative adversarial networks (GANs) for image synthesis, and hot-off-the-press approximate inference techniques relying on implicit distributions. The majority of existing approaches to learning implicit models rely on approximating the intractable distribution or optimisation objec…

DirMixE：利用层次化标签变异实现测试无关长尾识别

DirMixE: Harnessing Test Agnostic Long-tail Recognition with Hierarchical Label Variations

DirMixE通过分层标签变异策略提升测试无关长尾识别性能，结合参数高效微调框架实现更稳定的模型泛化能力。

Instance-Optimal Compressed Sensing via Posterior Sampling

We characterize the measurement complexity of compressed sensing of signals drawn from a known prior distribution, even when the support of the prior is the entire space (rather than, say, sparse vectors). We show for Gaussian measurements and \emph{any} prior distribution on the signal, that the posterior sampling estimator achieves near-optimal recovery guarantees. Moreover, this result is robust to model mismatch, as long as the distribution estimate (e.g., from an invertible generative model) is close to the true distribution in Wasserstein distance. We implement the posterior sampling est…

向量策略优化：为多样性训练改进测试时间搜索

Vector Policy Optimization: Training for Diversity Improves Test-Time Search

本文提出向量策略优化（VPO）方法，通过训练策略以预测多样化的下游奖励函数，从而产生多样化的解决方案，以改进测试时间搜索的性能。

EvolGAN: Evolutionary Generative Adversarial Networks

We propose to use a quality estimator and evolutionary methods to search the latent space of generative adversarial networks trained on small, difficult datasets, or both. The new method leads to the generation of significantly higher quality images while preserving the original generator's diversity. Human raters preferred an image from the new version with frequency 83.7pc for Cats, 74pc for FashionGen, 70.4pc for Horses, and 69.2pc for Artworks, and minor improvements for the already excellent GANs for faces. This approach applies to any quality scorer and GAN generator.