activity
20162020
most citedBERT as a Teacher: Contextual Embeddings for Sequence-Level Reward

7 citations · 7 across the 2 of their papers we have counts for

collaborators

7 papers

cs.LG20207 cited

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…

stat.ML2020

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…

math.OC2019

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…

cs.LG2019

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…

cs.LG2019

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…

physics.comp-ph2019

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…