Search Results for author:
Found 5 papers, 1 papers with code
Reinforcement Learning from Delayed Observations via World Models
In standard Reinforcement Learning settings, agents typically assume immediate feedback about the effects of their actions after taking them.
Moonwalk: Inverse-Forward Differentiation
Our method, Moonwalk, has a time complexity linear in the depth of the network, unlike the quadratic time complexity of na\"ive forward, and empirically reduces computation time by several orders of magnitude without allocating more memory.
Matching DNN Compression and Cooperative Training with Resources and Data Availability
To make machine learning (ML) sustainable and apt to run on the diverse devices where relevant data is, it is essential to compress ML models as needed, while still meeting the required learning quality and time performance.
Regularizing Recurrent Neural Networks via Sequence Mixup
In this paper, we extend a class of celebrated regularization techniques originally proposed for feed-forward neural networks, namely Input Mixup (Zhang et al., 2017) and Manifold Mixup (Verma et al., 2018), to the realm of Recurrent Neural Networks (RNN).
Structure Learning of Sparse GGMs over Multiple Access Networks
In Uncoded method, data symbols are scaled and transmitted through the channel.
