7 citations · 11 across the 6 of their papers we have counts for
5 papers · 1 filter
Optimizing Convergence for Iterative Learning of ARIMA for Stationary Time Series
Kevin Styp-Rekowski, Florian Schmidt, Odej Kao
Forecasting of time series in continuous systems becomes an increasingly relevant task due to recent developments in IoT and 5G. The popular forecasting model ARIMA is applied to a…
BERT as a Teacher: Contextual Embeddings for Sequence-Level Reward
Florian Schmidt, Thomas Hofmann
Measuring the quality of a generated sequence against a set of references is a central problem in many learning frameworks, be it to compute a score, to assign a reward, or to perf…
Generalization in Generation: A closer look at Exposure Bias
Florian Schmidt
Exposure bias refers to the train-test discrepancy that seemingly arises when an autoregressive generative model uses only ground-truth contexts at training time but generated ones…
Autoregressive Text Generation Beyond Feedback Loops
Florian Schmidt, Stephan Mandt, Thomas Hofmann
Autoregressive state transitions, where predictions are conditioned on past predictions, are the predominant choice for both deterministic and stochastic sequential models. However…
Deep State Space Models for Unconditional Word Generation
Florian Schmidt, Thomas Hofmann
Autoregressive feedback is considered a necessity for successful unconditional text generation using stochastic sequence models. However, such feedback is known to introduce system…