Search Results for author:
Found 13 papers, 3 papers with code
Optimal Transport with Cyclic Symmetry
On the basis of this reduction, our algorithms solve the small optimization problem instead of the original OT.
Embarrassingly Simple Text Watermarks
LLMs can generate texts that cannot be distinguished from human-written texts.
Necessary and Sufficient Watermark for Large Language Models
Although existing watermarking methods have successfully detected texts generated by LLMs, they significantly degrade the quality of the generated texts.
Momentum Tracking: Momentum Acceleration for Decentralized Deep Learning on Heterogeneous Data
In this study, we propose Momentum Tracking, which is a method with momentum whose convergence rate is proven to be independent of data heterogeneity.
Theoretical Analysis of Primal-Dual Algorithm for Non-Convex Stochastic Decentralized Optimization
However, the convergence rate of the ECL is provided only when the objective function is convex, and has not been shown in a standard machine learning setting where the objective function is non-convex.
Communication Compression for Decentralized Learning with Operator Splitting Methods
Moreover, we demonstrate that the C-ECL is more robust to heterogeneous data than the Gossip-based algorithms.
A DNN Optimizer that Improves over AdaBelief by Suppression of the Adaptive Stepsize Range
Firstly, we show that the particular placement of the parameter epsilon within the update expressions of AdaBelief reduces the range of the adaptive stepsizes, making AdaBelief closer to SGD with momentum.
Bilateral Video Magnification Filter
Eulerian video magnification (EVM) has progressed to magnify subtle motions with a target frequency even under the presence of large motions of objects.
SSFG: Stochastically Scaling Features and Gradients for Regularizing Graph Convolutional Networks
We show that applying stochastic scaling at the gradient level is complementary to that applied at the feature level to improve the overall performance.
Approximated Orthonormal Normalisation in Training Neural Networks
Considering a weight matrix W from a particular neural layer in the model, our objective is to design a function h(W) such that its row vectors are approximately orthogonal to each other while allowing the DNN model to fit the training data sufficiently accurate.
Rapidly Adapting Moment Estimation
Adaptive gradient methods such as Adam have been shown to be very effective for training deep neural networks (DNNs) by tracking the second moment of gradients to compute the individual learning rates.
DNN-based Source Enhancement to Increase Objective Sound Quality Assessment Score
Since OSQA scores have been used widely for sound-quality evaluation, constructing DNNs to increase OSQA scores would be better than using the minimum-MSE to create high-quality output signals.
GENERALIZED ADAPTIVE MOMENT ESTIMATION
Empirical studies for training four convolutional neural networks over MNIST and CIFAR10 show that under proper parameter selection, Game produces promising validation performance as compared to AMSGrad and PAdam.
