29 citations · 144 across the 30 of their papers we have counts for
5 papers · 1 filter
Clustering above Exponential Families with Tempered Exponential Measures
Ehsan Amid, Richard Nock, Manfred Warmuth
The link with exponential families has allowed -means clustering to be generalized to a wide variety of data generating distributions in exponential families and clustering dist…
Layerwise Bregman Representation Learning with Applications to Knowledge Distillation
Ehsan Amid, Rohan Anil, Christopher Fifty +1
In this work, we propose a novel approach for layerwise representation learning of a trained neural network. In particular, we form a Bregman divergence based on the layer's transf…
Extracting Targeted Training Data from ASR Models, and How to Mitigate It
Ehsan Amid, Om Thakkar, Arun Narayanan +2
Recent work has designed methods to demonstrate that model updates in ASR training can leak potentially sensitive attributes of the utterances used in computing the updates. In thi…
Learning from Randomly Initialized Neural Network Features
Ehsan Amid, Rohan Anil, Wojciech Kotłowski +1
We present the surprising result that randomly initialized neural networks are good feature extractors in expectation. These random features correspond to finite-sample realization…
Step-size Adaptation Using Exponentiated Gradient Updates
Ehsan Amid, Rohan Anil, Christopher Fifty +1
Optimizers like Adam and AdaGrad have been very successful in training large-scale neural networks. Yet, the performance of these methods is heavily dependent on a carefully tuned…