- Approximate Fisher Information Matrix to Characterise the Training of Deep Neural Networks [reporter: "Nikita Kiselev "]
- Copulas, Sklar's theorem and Distributional Transform [reporter: "Kreinin Matvei"]
- Hyperparameters: optimize, or integrate out? [reporter: "Semkin Kirill"]
- Bayesian Inference under Small Sample Sizes Using General Noninformative Priors [reporter: "Dorin Daniil"]
- Bayesian Deep Learning via Subnetwork Inference [reporter: "Nikitina Maria"]
- On the Dirichlet prior and Bayesian regularization [reporter: "Babkin Petr"]
- A Widely Applicable Bayesian Information Criterion [reporter: Ernest Nasyrov]
- Rissanen data analysis: Examining dataset characteristics via description length [reporter: "Anastasia Voznyuk"]
Variational Learning and Bits-Back Coding: An Information-Theoretic View to Bayesian Learning [reporter: your name]Importance weighted AE [reporter: your name]
- The equivalence between Stein variational gradient descent and black-box variational inference [reporter: Ilgam Latypov]
- Pathwise Derivatives Beyond the Reparameterization Trick [reporter: Alexander Terentyev]
- A diffusion theory for deep learning dynamics: Stochastic gradient descent exponentially favors flat minima [reporter: "Veprikov Andrey"]
Infinitely deep bayesian neural networks with stochastic differential equations [reporter: your name]
- Fast exact multiplication by the Hessian [Yuri Sapronov]
- Some large-scale matrix computation problem [reporter: your name]
- Your diffusion model is secretly a zero-shot classifier [reporter: Dmitry Bylinkin]
- Combining deep generative and discriminative models for Bayesian semi-supervised learning [reporter: Aleksandr Shestakov]
- Learning to Discover Sparse Graphical Models [reporter: "Solodkin Vladimir"]
- GFlowNets [reporter: "Iryna Zabarianska"]
- Rethinking Parameter Counting in Deep Models: Effective Dimensionality Revisited [reporter: Nikita Okhotnikov]
- Fast Predictive Uncertainty for Classification with Bayesian Deep Networks [reporter: Ignashin Igor]