Home /
Research
Showing 31 - 36 / 897
The large learning rate phase of deep learning
Anonymous....
Published date-01/01/2021
The choice of initial learning rate can have a profound effect on the performance of deep networks. We present empirical evidence that networks exhibit sharply distinct behaviors at small and …
Contrast to Divide: self-supervised pre-training for learning with noisy labels
Anonymous....
Published date-01/01/2021
ImageClassification, Learningwithnoisylabels
Advances in semi-supervised methods for image classification significantly boosted performance in the learning with noisy labels (LNL) task. Specifically, by discarding the erroneous labels (and keeping the samples), the LNL …
Ruminating Word Representations with Random Noise Masking
Anonymous....
Published date-01/01/2021
TextClassification, WordEmbeddings
We introduce a training method for better word representation and performance, which we call \textbf{GraVeR} (\textbf{Gra}dual \textbf{Ve}ctor \textbf{R}umination). The method is to gradually and iteratively add random noises and bias …
Hierarchical Meta Reinforcement Learning for Multi-Task Environments
Anonymous....
Published date-01/01/2021
HierarchicalReinforcementLearning, MetaReinforcementLearning
Deep reinforcement learning algorithms aim to achieve human-level intelligence by solving practical decisions-making problems, which are often composed of multiple sub-tasks. Complex and subtle relationships between sub-tasks make traditional methods …
How Robust are Randomized Smoothing based Defenses to Data Poisoning?
AkshayMehra, BhavyaKailkhura, Pin-YuChen....
Published date-12/02/2020
bileveloptimization, DataAugmentation, DataPoisoning
The prediction of certifiably robust classifiers remains constant around a neighborhood of a point, making them resilient to test-time attacks with a guarantee. In this work, we present a previously …
PlueckerNet: Learn to Register 3D Line Reconstructions
LiuLiu, HongdongLi, HaodongYao....
Published date-12/02/2020
Aligning two partially-overlapped 3D line reconstructions in Euclidean space is challenging, as we need to simultaneously solve correspondences and relative pose between line reconstructions. This paper proposes a neural network …