kl divergence

Variational Autoencoders: A Harmonic Perspective AISTATS 2022 Wide Bayesian neural networks have a simple weight posterior: theory and accelerated sampling ICML 2022 Adaptive Curriculum Learning ICCV 2021 Adaptive Sampling for Best Policy Identification in Markov Decision Processes ICML 2021 A Distributional Approach to Controlled Text Generation ICLR 2021 Adversarially Guided Actor-Critic ICLR 2021 Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillation IJCAI 2021 FILTER: An Enhanced Fusion Method for Cross-lingual Language Understanding AAAI 2021 Graph reparameterizations for enabling 1000+ Monte Carlo iterations in Bayesian deep neural networks UAI 2021 Hierarchical probabilistic model for blind source separation via Legendre transformation UAI 2021 Homeomorphic-Invariance of EM: Non-Asymptotic Convergence in KL Divergence for Exponential Families via Mirror Descent AISTATS 2021 KALE Flow: A Relaxed KL Gradient Flow for Probabilities with Disjoint Support NeurIPS 2021 Longitudinal Variational Autoencoder AISTATS 2021 On Robust Optimal Transport: Computational Complexity and Barycenter Computation NeurIPS 2021 On the Importance of Gradients for Detecting Distributional Shifts in the Wild NeurIPS 2021 Rate-Regularization and Generalization in Variational Autoencoders AISTATS 2021 R-Drop: Regularized Dropout for Neural Networks NeurIPS 2021 Scaling Ensemble Distribution Distillation to Many Classes with Proxy Targets NeurIPS 2021 Soft-IntroVAE: Analyzing and Improving the Introspective Variational Autoencoder CVPR 2021 A Batch Normalized Inference Network Keeps the KL Vanishing Away ACL 2020 All in the Exponential Family: Bregman Duality in Thermodynamic Variational Inference ICML 2020 A Non-Asymptotic Analysis for Stein Variational Gradient Descent NeurIPS 2020 Bayesian Adversarial Attack on Graph Neural Networks (Student Abstract) AAAI 2020 ControlVAE: Controllable Variational Autoencoder ICML 2020 Decentralized Langevin Dynamics for Bayesian Learning NeurIPS 2020