1 citations · 2 across the 10 of their papers we have counts for
4 papers · 1 filter
When are likely answers right? On Sequence Probability and Correctness in LLMs
Johannes Zenn, Jonas Geiping
Many decoding methods for large language models can be understood as shifting probability mass toward outputs that are more likely under the model, either locally at the token leve…
Differentiable Annealed Importance Sampling Minimizes The Symmetrized Kullback-Leibler Divergence Between Initial and Target Distribution
Johannes Zenn, Robert Bamler
Differentiable annealed importance sampling (DAIS), proposed by Geffner & Domke (2021) and Zhang et al. (2021), allows optimizing over the initial distribution of AIS. In this pape…
A Note on Generalization in Variational Autoencoders: How Effective Is Synthetic Data & Overparameterization?
Tim Z. Xiao, Johannes Zenn, Robert Bamler
Variational autoencoders (VAEs) are deep probabilistic models that are used in scientific applications. Many works try to mitigate this problem from the probabilistic methods persp…
Resampling Gradients Vanish in Differentiable Sequential Monte Carlo Samplers
Johannes Zenn, Robert Bamler
Annealed Importance Sampling (AIS) moves particles along a Markov chain from a tractable initial distribution to an intractable target distribution. The recently proposed Different…