Robert Bamler
3 papers in the PaperMetrix corpus
Papers by this author
-
Understanding Entropy Coding With Asymmetric Numeral Systems (ANS): a Statistician's Perspective
2022 · arXiv (Cornell University)
Entropy coding is the backbone data compression. Novel machine-learning based compression methods often use a new entropy coder called Asymmetric Numeral Systems (ANS) [Duda et al., 2015], which provides very close to optimal bitrates and …
-
Differentiable Annealed Importance Sampling Minimizes The Symmetrized Kullback-Leibler Divergence Between Initial and Target Distribution
2024 · arXiv (Cornell University)
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 paper, we show that, in the limit of many …
-
Dynamic word embeddings
2017 · International Conference on Machine Learning
We present a probabilistic language model for time-stamped text data which tracks the semantic evolution of individual words over time. The model represents words and contexts by latent trajectories in an embedding space. At each …