7 citations · 7 across the 2 of their papers we have counts for
7 papers
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…
Batch Normalization Provably Avoids Rank Collapse for Randomly Initialised Deep Networks
Hadi Daneshmand, Jonas Kohler, Francis Bach +2
Randomly initialized neural networks are known to become harder to train with increasing depth, unless architectural enhancements like residual connections and batch normalization…
Mixing of Stochastic Accelerated Gradient Descent
Peiyuan Zhang, Hadi Daneshmand, Thomas Hofmann
We study the mixing properties for stochastic accelerated gradient descent (SAGD) on least-squares regression. First, we show that stochastic gradient descent (SGD) and SAGD are si…
LeDeepChef: Deep Reinforcement Learning Agent for Families of Text-Based Games
Leonard Adolphs, Thomas Hofmann
While Reinforcement Learning (RL) approaches lead to significant achievements in a variety of areas in recent history, natural language tasks remained mostly unaffected, due to the…
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…
Cosmological N-body simulations: a challenge for scalable generative models
Nathanaël Perraudin, Ankit Srivastava, Aurelien Lucchi +3
Deep generative models, such as Generative Adversarial Networks (GANs) or Variational Autoencoders (VAs) have been demonstrated to produce images of high visual quality. However, t…