scholarly journals Still No Free Lunches: The Price to Pay for Tighter PAC-Bayes Bounds

Entropy ◽  
2021 ◽  
Vol 23 (11) ◽  
pp. 1529
Author(s):  
Benjamin Guedj ◽  
Louis Pujol
Keyword(s):  
Robust Statistics ◽  
Learning Algorithm ◽  
Finite Variance ◽  
Free Lunch ◽  
Recent Advances ◽  
Probably Approximately Correct ◽  
The Cost ◽  
No Free Lunch

“No free lunch” results state the impossibility of obtaining meaningful bounds on the error of a learning algorithm without prior assumptions and modelling, which is more or less realistic for a given problem. Some models are “expensive” (strong assumptions, such as sub-Gaussian tails), others are “cheap” (simply finite variance). As it is well known, the more you pay, the more you get: in other words, the most expensive models yield the more interesting bounds. Recent advances in robust statistics have investigated procedures to obtain tight bounds while keeping the cost of assumptions minimal. The present paper explores and exhibits what the limits are for obtaining tight probably approximately correct (PAC)-Bayes bounds in a robust setting for cheap models.

A Scalable Redefined Stochastic Blockmodel

2021 ◽  
Vol 15 (3) ◽  
pp. 1-28
Author(s):  
Xueyan Liu ◽  
Bo Yang ◽  
Hechang Chen ◽  
Katarzyna Musial ◽  
Hongxu Chen ◽  
...  
Keyword(s):  
Large Scale ◽  
Network Science ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Real World Data ◽  
Computational Overhead ◽  
Stochastic Blockmodel ◽  
Np Hard Problem ◽  
Large Scale Networks ◽  
The Cost

Stochastic blockmodel (SBM) is a widely used statistical network representation model, with good interpretability, expressiveness, generalization, and flexibility, which has become prevalent and important in the field of network science over the last years. However, learning an optimal SBM for a given network is an NP-hard problem. This results in significant limitations when it comes to applications of SBMs in large-scale networks, because of the significant computational overhead of existing SBM models, as well as their learning methods. Reducing the cost of SBM learning and making it scalable for handling large-scale networks, while maintaining the good theoretical properties of SBM, remains an unresolved problem. In this work, we address this challenging task from a novel perspective of model redefinition. We propose a novel redefined SBM with Poisson distribution and its block-wise learning algorithm that can efficiently analyse large-scale networks. Extensive validation conducted on both artificial and real-world data shows that our proposed method significantly outperforms the state-of-the-art methods in terms of a reasonable trade-off between accuracy and scalability. 1

Sparse Incremental Delta-Bar-Delta for System Identification

2014 ◽  
Vol 665 ◽  
pp. 643-646
Author(s):  
Ying Liu ◽  
Yan Ye ◽  
Chun Guang Li
Keyword(s):  
System Identification ◽  
Cost Function ◽  
Learning Algorithm ◽  
Learning System ◽  
The Other ◽  
Sparse System ◽  
Speed Up ◽  
Sparse System Identification ◽  
The Cost ◽  
Zero Attractor

Metalearning algorithm learns the base learning algorithm, targeted for improving the performance of the learning system. The incremental delta-bar-delta (IDBD) algorithm is such a metalearning algorithm. On the other hand, sparse algorithms are gaining popularity due to their good performance and wide applications. In this paper, we propose a sparse IDBD algorithm by taking the sparsity of the systems into account. Thenorm penalty is contained in the cost function of the standard IDBD, which is equivalent to adding a zero attractor in the iterations, thus can speed up convergence if the system of interest is indeed sparse. Simulations demonstrate that the proposed algorithm is superior to the competing algorithms in sparse system identification.

Potential HIV gene therapy strategies

2021 ◽  
Author(s):  
Moataz Dowaidar
Keyword(s):  
Gene Therapy ◽  
Cord Blood ◽  
Gene Editing ◽  
Mortality Risks ◽  
Recent Advances ◽  
Whole Exome ◽  
Localization Signal ◽  
Cord Blood Cells ◽  
The Cost ◽  
Therapy Strategies

The CCR5 null genotype generation has been a main focus in the HIV gene therapy industry. The presence of the X4 tropic virus, mobilization of HSPCs, the quality of the cells for manipulation, and gene editing efficiency appear to be the main obstacles in translating this technique. Unintended off-target cleavage is a key problem in CRISPR/Cas9 editing. With the development of small molecule expansion methods for cord blood HSPC, it would be advantageous to modify CCR5 in cord blood cells and expand them for transplantation. The generation of engraftable HSPCS from iPSCs would be an ideal technique for HSCC gene therapy.The haplotype-characterized iPSC would be the donor for many patients, and it could be a commercially available product. The 32 C CR5 homozygous people had no elevated mortality risks according to whole-exome sequencing and whole-genome genotyping, according to CCR 5 positive people, and had no higher mortality risks compared to those who were HIV positive. Recent advances in gene editing, such as non-viral delivery of Cas9 ribonucleoproteins, incorporation of a 3X-nuclear localization signal into spCas9, and use of HiFi Cas9 with chemically modified sgRNAs, can be combined with recent advances in transplantation. Infusing modest doses of gene modified primitive HSPC fractions indicated by CD34 + CD90 + CD45RA-, which can engraft better, is another option for lowering the cost of gene therapy.

A Hybrid Method Based on Semi-Supervised Learning for Relation Extraction in Chinese EMRs (Preprint)

2021 ◽  
Author(s):  
ChunMing Yang
Keyword(s):  
Supervised Learning ◽  
Learning Algorithm ◽  
Medical Knowledge ◽  
Relation Extraction ◽  
Small Scale ◽  
Semantic Features ◽  
Training Process ◽  
Network Layers ◽  
Relation Prediction ◽  
The Cost

BACKGROUND Extracting relations between the entities from Chinese electronic medical records(EMRs) is the key to automatically constructing medical knowledge graphs. Due to the less available labeled corpus, most of the current researches are based on shallow networks, which cannot fully capture the complex semantic features in the text of Chinese EMRs. OBJECTIVE In this study, a hybrid deep learning method based on semi-supervised learning is proposed to extract the entity relations from small-scale complex Chinese EMRs. METHODS The semantic features of sentences are extracted by residual network (ResNet) and the long dependent information is captured by bidirectional GRU (Gated Recurrent Unit). Then the attention mechanism is used to assign weights to the extracted features respectively, and the output of the two attention mechanisms is integrated for relation prediction. We adjusted the training process with manually annotated small-scale relational corpus and bootstrapping semi-supervised learning algorithm, and continuously expanded the datasets during the training process. RESULTS The experimental results show that the best F1-score of the proposed method on the overall relation categories reaches 89.78%, which is 13.07% higher than the baseline CNN model. The F1-score on DAP, SAP, SNAP, TeRD, TeAP, TeCP, TeRS, TeAS, TrAD, TrRD and TrAP 11 relation categories reaches 80.95%, 93.91%, 92.96%, 88.43%, 86.54%, 85.58%, 87.96%, 94.74%, 93.01%, 87.58% and 95.48%, respectively. CONCLUSIONS The hybrid neural network method strengthens the feature transfer and reuse between different network layers and reduces the cost of manual tagging relations. The results demonstrate that our proposed method is effective for the relation extraction in Chinese EMRs.

The Cost of a Free Lunch: Dabbling in Diversification

2015 ◽  
Author(s):  
Emlyn James Flint ◽  
Florence Chikurunhe ◽  
Anthony Seymour
Keyword(s):  
Free Lunch ◽  
The Cost
Sign in / Sign up

Export Citation Format

Share Document