-
Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data
Self-training algorithms, which train a model to fit pseudolabels predic...
10/07/2020 ∙ by Colin Wei, et al. ∙
18
∙
share
read it
-
Heteroskedastic and Imbalanced Deep Learning with Adaptive Regularization
Real-world large-scale datasets are heteroskedastic and imbalanced – lab...
06/29/2020 ∙ by Kaidi Cao, et al. ∙
1
∙
share
read it
-
Active Online Domain Adaptation
Online machine learning systems need to adapt to domain shifts. Meanwhil...
06/25/2020 ∙ by Yining Chen, et al. ∙
9
∙
share
read it
-
Self-training Avoids Using Spurious Features Under Domain Shift
In unsupervised domain adaptation, existing theory focuses on situations...
06/17/2020 ∙ by Yining Chen, et al. ∙
0
∙
share
read it
-
Experience Augmentation: Boosting and Accelerating Off-Policy Multi-Agent Reinforcement Learning
Exploration of the high-dimensional state action space is one of the big...
05/19/2020 ∙ by Zhenhui Ye, et al. ∙
0
∙
share
read it
-
A random forest based approach for predicting spreads in the primary catastrophe bond market
We introduce a random forest approach to enable spreads' prediction in t...
01/28/2020 ∙ by Despoina Makariou, et al. ∙
0
∙
share
read it
-
Weakly Supervised Disentanglement with Guarantees
Learning disentangled representations that correspond to factors of vari...
10/22/2019 ∙ by Rui Shu, et al. ∙
12
∙
share
read it
-
An axiomatic nonparametric production function estimator: Modeling production in Japan's cardboard industry
We develop a new approach to estimate a production function based on the...
06/19/2019 ∙ by Daisuke Yagi, et al. ∙
0
∙
share
read it
-
Retrieval-Enhanced Adversarial Training for Neural Response Generation
Dialogue systems are usually built on either generation-based or retriev...
09/12/2018 ∙ by Qingfu Zhu, et al. ∙
0
∙
share
read it
-
Time-Space Tradeoffs for the Memory Game
A single-player Memory Game is played with n distinct pairs of cards, wi...
12/04/2017 ∙ by Amit Chakrabarti, et al. ∙
0
∙
share
read it
-
Recurrent Neural Networks as Weighted Language Recognizers
We investigate computational complexity of questions of various problems...
11/15/2017 ∙ by Yining Chen, et al. ∙
0
∙
share
read it
