sato9hara / sgd-influence
Python codes for influential instance estimation
☆53Updated last year
Related projects: ⓘ
- This repo provides code used in the paper "Predicting with High Correlation Features" (https://arxiv.org/abs/1910.00164):☆55Updated 4 years ago
- Unofficial pytorch implementation of a paper, Distributional Smoothing with Virtual Adversarial Training [Miyato+, ICLR2016].☆26Updated 6 years ago
- code release for Representer point Selection for Explaining Deep Neural Network in NeurIPS 2018☆65Updated 3 years ago
- Implementation of Invariant Risk Minimization https://arxiv.org/abs/1907.02893☆84Updated 4 years ago
- Explaining a black-box using Deep Variational Information Bottleneck Approach☆46Updated last year
- This repo contains the code used for NeurIPS 2019 paper "Asymmetric Valleys: Beyond Sharp and Flat Local Minima".☆14Updated 4 years ago
- Gradients as Features for Deep Representation Learning☆41Updated 4 years ago
- Computing various measures and generalization bounds on convolutional and fully connected networks☆33Updated 5 years ago
- ☆48Updated last year
- ☆13Updated 5 years ago
- Official adversarial mixup resynthesis repository☆33Updated 4 years ago
- Toy datasets to evaluate algorithms for domain generalization and invariance learning.☆42Updated 2 years ago
- Public code for a paper "Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networks."☆34Updated 5 years ago
- Simple data balancing baselines for worst-group-accuracy benchmarks.☆39Updated 10 months ago
- Code for the paper 'Understanding Measures of Uncertainty for Adversarial Example Detection'☆57Updated 6 years ago
- Implementation of the paper "Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theory", Ron Amit and Ron Meir, ICML 2018☆22Updated 4 years ago
- ☆55Updated 4 years ago
- Implementation for "Classification from Pairwise Similarity and Unlabeled Data"☆27Updated 4 years ago
- code for the ICML paper "SelectiveNet - A Deep Neural Network with an Integrated Reject Option"☆45Updated 5 years ago
- ☆65Updated 3 years ago
- Sinkhorn Label Allocation is a label assignment method for semi-supervised self-training algorithms. The SLA algorithm is described in fu…☆53Updated 3 years ago
- Code for Self-Tuning Networks (ICLR 2019) https://arxiv.org/abs/1903.03088☆53Updated 5 years ago
- ☆20Updated this week
- Rethinking Bias-Variance Trade-off for Generalization of Neural Networks☆49Updated 3 years ago
- ☆53Updated 6 years ago
- Code for ICLR 2019 Paper, "MAX-MIG: AN INFORMATION THEORETIC APPROACH FOR JOINT LEARNING FROM CROWDS"☆25Updated last year
- Self-Explaining Neural Networks☆14Updated last year
- Neural Ensemble Search for Uncertainty Estimation and Dataset Shift☆30Updated 5 months ago
- PyTorch implementation of parity loss as constraints function to realize the fairness of machine learning.☆71Updated last year
- ☆61Updated 3 years ago