Search Results for author:
Found 8 papers, 0 papers with code
SignSGD with Federated Voting
SignSGD with majority voting (signSGD-MV) is an effective distributed learning algorithm that can significantly reduce communication costs by one-bit quantization.
SignSGD with Federated Defense: Harnessing Adversarial Attacks through Gradient Sign Decoding
Distributed learning is an effective approach to accelerate model training using multiple workers.
Posterior Distillation Sampling
PDS matches the stochastic latents of the source and the target, enabling the sampling of targets in diverse parameter spaces that align with a desired attribute while maintaining the source's identity.
Fast Word Error Rate Estimation Using Self-Supervised Representations For Speech And Text
WER estimation is a task aiming to predict the WER of an ASR system, given a speech utterance and a transcription.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Sparse-SignSGD with Majority Vote for Communication-Efficient Distributed Learning
The training efficiency of complex deep learning models can be significantly improved through the use of distributed optimization.
Unsupervised data selection for Speech Recognition with contrastive loss ratios
By using the submodular function, a training set for automatic speech recognition matching the target data set is selected.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Bayesian AirComp with Sign-Alignment Precoding for Wireless Federated Learning
In this paper, we present a simple yet effective precoding method with limited channel knowledge, called sign-alignment precoding.
Bayesian Federated Learning over Wireless Networks
This paper proposes a Bayesian federated learning (BFL) algorithm to aggregate the heterogeneous quantized gradient information optimally in the sense of minimizing the mean-squared error (MSE).
