activity
20182025
most citedUnderstanding Why Neural Networks Generalize Well Through GSNR of Parameters

10 citations · 20 across the 4 of their papers we have counts for

collaborators
Showing cs.LGShow all

9 papers · 1 filter

cs.LG2025

Rethinking Hebbian Principle: Low-Dimensional Structural Projection for Unsupervised Learning

Shikuang Deng, Jiayuan Zhang, Yuhang Wu +2

Hebbian learning is a biological principle that intuitively describes how neurons adapt their connections through repeated stimuli. However, when applied to machine learning, it su…

cs.LG2021

Cost-Efficient Online Hyperparameter Optimization

Jingkang Wang, Mengye Ren, Ilija Bogunovic +2

Recent work on hyperparameters optimization (HPO) has shown the possibility of training certain hyperparameters together with regular parameters. However, these online HPO algorith…

cs.LG2020

Intriguing Properties of Contrastive Losses

Ting Chen, Calvin Luo, Lala Li

We study three intriguing properties of contrastive learning. First, we generalize the standard contrastive loss to a broader family of losses, and we find that various instantiati…

cs.LG202010 cited

Understanding Why Neural Networks Generalize Well Through GSNR of Parameters

Jinlong Liu, Guoqing Jiang, Yunzhi Bai +2

As deep neural networks (DNNs) achieve tremendous success across many application domains, researchers tried to explore in many aspects on why they generalize well. In this paper,…

cs.LG2019

Differentiable Product Quantization for End-to-End Embedding Compression

Ting Chen, Lala Li, Yizhou Sun

Embedding layers are commonly used to map discrete symbols into continuous embedding vectors that reflect their semantic meanings. Despite their effectiveness, the number of parame…

cs.LG20192 cited

Doubly Sparse: Sparse Mixture of Sparse Experts for Efficient Softmax Inference

Shun Liao, Ting Chen, Tian Lin +2

Computations for the softmax function are significantly expensive when the number of output classes is large. In this paper, we present a novel softmax inference speedup method, Do…